DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Status
Claims 1-20 are pending for examination in the Application No. 18/999,753 filed December 23rd, 2024.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on February 27th, 2025, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS is being considered and attached by the examiner.
Claim Objections
Claims 7-9, 14, and 19 are objected to because of the following informalities failing to comply with 37 CFR 1.71(a) for "full, clear, concise, and exact terms" (see MPEP § 608.01(m)):
The examiner respectfully suggests amending the phrase “The method of claim 6” in claim 7 to recite “The computer-implemented method of claim 6” to maintain consistency in terminology with the claims;
The examiner respectfully suggests amending the phrase “a result of comparison” in line 6 of claim 8 to recite “a result of the comparison” to prevent confusion regarding antecedent basis of the “comparison” recited in the phrase; and
In line 4 of claims 9, 14, and 19, “an year” should be “a year”.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
It is noted that claims 16-20 are considered eligible subject matter. Claims 16-20 claim a computer program product (CPP) that cannot be interpreted as non-statutory subject matter. Paragraph [0039] of the instant Specification recites a CPP excludes transitory forms of signal transmission, often referred to as "signals per se" (e.g., “…not to be construed as storage in the form of transitory signals per se…”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3-9, 11-12, 14, and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Ming et al. (Ming; US 2020/0250405 A1) in view of Shen et al. (Shen; CN 106599905 A).
Regarding claim 1, Ming discloses a computer-implemented method, comprising:
determining, by a computer, a match between a first number plate of at least one first vehicle and a second number plate of at least one second vehicle (para(s). [0090], recite(s)
[0090] “…S203, when the current license plate corresponding to the current license plate information is found in the license plate information database, and is appeared at a second checkpoint in the preset time, determining whether fake license plate vehicle exists between the current vehicle and a vehicle corresponding to the current license plate captured at the second checkpoint …”
, where the “current license plate information” is a first number plate of at least one first vehicle and the current license plate “appeared at a second checkpoint” is a second number plate of at least one second vehicle; wherein determining the “appear[ance]” of the same “current license plate” at a “second checkpoint” is determining a match between the two number plates of the at least two vehicles);
determining, by the computer, a geo-location disparity factor between the at least one first vehicle and the at least one second vehicle based on the determined match (para(s). [0091], recite(s)
[0091] “…determining possibility of a same vehicle appeared in two lane checkpoints within the time interval, which can be analyzed via a corresponding calculation formula or an exclusive method in the specific implementation, For example, the distance between the current lane checkpoint and the second lane checkpoint is 200 kilometers, the time that the current license plate is appeared in the current second lane checkpoint is 10:00 am, while the time that the current license plate is also appeared in the current lane checkpoint is 10:20 am on a same day, in this way, it is impossible for a same vehicle to appear in the two lane checkpoints respectively according to the above two times. …”
, where the “distance between the current lane checkpoint and the second lane checkpoint” within a certain “time interval” is a geo-location disparity factor between the at least one first and second vehicles), vehicle information of the at least one first vehicle and the at least one second vehicle (para(s). [0090]—see citation in claim limitation “determining… a match…” above—, where the “license plate information” is vehicle information), timestamp data of the at least one first vehicle and the at least one second vehicle at one or more positions, and location coordinates of the one or more positions (para(s). [0091], further recite(s):
[0091] “…if the current license plate found in the license plate information database is also appeared in the second lane checkpoint in the preset time, first obtaining the time and the location of the current license plate appeared in the second lane checkpoint, and then according to position information of the current lane checkpoint and the second lane checkpoint, road condition information between the current lane checkpoint and the second lane checkpoint, speed information of the current license plate and time interval of the current license plate appeared between the current lane checkpoint and the second lane checkpoint, determining possibility of a same vehicle appeared in two lane checkpoints within the time interval… For example, the distance between the current lane checkpoint and the second lane checkpoint is 200 kilometers, the time that the current license plate is appeared in the current second lane checkpoint is 10:00 am, while the time that the current license plate is also appeared in the current lane checkpoint is 10:20 am on a same day, in this way, it is impossible for a same vehicle to appear in the two lane checkpoints respectively according to the above two times.”
, where the “time[s]” that the “current license plate” appeared at each lane checkpoint are timestamps and the “position information” are location coordinates);
obtaining, by the computer, an outcome(para(s). [0091]—see citation in claim limitation “determining… a geo-location disparity…” above—, where para(s). [0091] further recite(s):
[0091] “…For example, the distance between the current lane checkpoint and the second lane checkpoint is 200 kilometers, the time that the current license plate is appeared in the current second lane checkpoint is 10:00 am, while the time that the current license plate is also appeared in the current lane checkpoint is 10:20 am on a same day, in this way, it is impossible for a same vehicle to appear in the two lane checkpoints respectively according to the above two times. Therefore, it can be determined that there is a fake license plate vehicle between the current vehicle and the vehicle corresponding to the current license plate captured at the second lane checkpoint. So, the analysis result can be pushed to the police for further analysis. …”
, where the “determin[ation] that there is a fake license plate vehicle” based on at least the distance between the two checkpoints is obtaining an outcome based on the geo-location disparity factor);
determining, by the computer,(para(s). [0091]—see citation in preceding limitation immediately above—, where determining that “there is a fake license plate vehicle between the current vehicle and the vehicle corresponding to the current license plate captured at the second lane checkpoint” is determining vehicle cloning of at least one of the two vehicles based on the outcome); and
outputting, by the computer, at least one alert based on the determination(para(s). [0091]—see citation in preceding limitation immediately above—, where para(s). [0083] and [0091] further recite(s):
[0083] “…if the current vehicle is determined as the fake license plate vehicle, the relevant information of the current vehicle and its driver driving the current vehicle can be stored for subsequent forensic analysis by the police, or warning messages can be actively pushed to the police.”
[0091] “…So, the analysis result can be pushed to the police for further analysis. …”
, where “push[ing]” the determination and/or analysis of vehicle cloning to the “police” is outputting at least an alert based on the determination of vehicle cloning of one of the at least two vehicles).
Where Ming does not specifically disclose
determining, by the computer, a confidence score for the geo-location disparity factor, based on at least one of the vehicle information, the timestamp data, or the location coordinates;
comparing, by the computer, the confidence score with a threshold disparity score;
obtaining, by the computer, an outcome of the comparison of the confidence score with the threshold disparity score;
determining, by the computer, that the confidence score indicates vehicle cloning of one of the at least one first vehicle or the at least one second vehicle based on the outcome; and
…that the confidence score is indicative of vehicle cloning of one of the at least one first vehicle or the at least one second vehicle;
Shen teaches in the same field of endeavor of vehicle cloning determination based on a geo-location disparity factor
determining, by the computer, a confidence score for the geo-location disparity factor, based on at least one of the vehicle information, the timestamp data, or the location coordinates (description, para(s). [0036], recite(s)
[0036] “…if vehicles with the same license plate are obtained from the vehicle identification system and pass through checkpoints A and B one after the other or simultaneously, a value is calculated using the spatiotemporal rule
d
1
-
d
2
s
1
-
s
2
based on the shortest distance from checkpoint A to checkpoint B
d
1
-
d
2
and the time difference between passing through checkpoints A and B
s
1
-
s
2
. If this value is greater than a set threshold θ, it can be determined as a suspected cloned vehicle. The θ is the maximum driving speed set by the maximum speed limit information of the relevant road.”
, where the “value using the spatiotemporal rule” or
d
1
-
d
2
s
1
-
s
2
is a confidence score for a geo-location disparity factor (e.g.,
d
1
-
d
2
,
s
1
-
s
2
, and/or the “value” itself) based on at least location coordinates (e.g.,
d
1
and
d
2
));
comparing, by the computer, the confidence score with a threshold disparity score (description, para(s). [0036]—see preceding limitation immediately above—, where determining if the “value is greater than a set threshold
θ
” is comparing the confidence score with a threshold disparity score (e.g., the “set threshold
θ
”));
obtaining, by the computer, an outcome of the comparison of the confidence score with the threshold disparity score (description, para(s). [0036]—see citation above—, where determining if the “value is greater” than the “set threshold
θ
” is an outcome obtained by comparing the confidence score (e.g., the “value using the spatiotemporal rule”) with the threshold disparity score (e.g., “set threshold
θ
”));
determining, by the computer, that the confidence score indicates vehicle cloning of one of the at least one first vehicle or the at least one second vehicle based on the outcome; and
…that the confidence score is indicative of vehicle cloning of one of the at least one first vehicle or the at least one second vehicle (description, para(s). [0036]—see citation above—, where determining “a suspected clone vehicle” when the “value is greater than a set threshold
θ
” is determining that the confidence score (e.g., the “value using the spatiotemporal rule”) indicates vehicle cloning of at least a vehicle based on the outcome).
Since each of Ming and Shen disclose a geo-location disparity factor between at least a first and a second vehicle with matching license plate information (see rejection above), it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ming to incorporate determining a confidence score for the geo-location disparity factor based on at least one of the vehicle information, the timestamp data, or the location coordinates, comparing the confidence score with a threshold disparity score, obtaining an outcome of the comparison of the confidence score with the threshold disparity score, determining that the confidence score indicates vehicle cloning of one of the at least one first vehicle or the at least one second vehicle based on the outcome, and outputting at least one alert based on the determination that the confidence score is indicative of vehicle cloning to improve accuracy in vehicle cloning determination by incorporating spatiotemporal rules as taught by Shen (description, para(s). [0046], recite(s)
[0046] “…It combines spatiotemporal rules with secondary recognition to achieve accurate identification of cloned vehicles. …”
).
Regarding claim 3, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Shen further teaches the computer-implemented method of claim 1 further comprising:
determining, by the computer, a difference between the location coordinates of the at least one first vehicle and the location coordinates of the at least one second vehicle while the at least one first vehicle and the at least one second vehicle are moving through the one or more positions (description, para(s). [0036]—see citation in claim 1 above—, where the “distance from checkpoint A to checkpoint B
d
1
-
d
2
” is a difference between the location coordinates of the two vehicles moving through (i.e., “pass[ing] through”)); and
determining, by the computer, the geo-location disparity factor between the at least one first vehicle and the at least one second vehicle based on the difference between the location coordinates of the at least one first vehicle and the at least one second vehicle, the timestamp data, and the vehicle information, wherein the geo-location disparity factor corresponds to a composite metric that quantitatively assesses spatial and temporal discrepancies between the at least one first vehicle and the at least one second vehicle (description, para(s). [0036]—see citation in claim 1 above—, where the “value using the spatiotemporal role” or
d
1
-
d
2
s
1
-
s
2
is a geo-location disparity factor based on the difference between the location coordinates of the two vehicles (e.g.,
d
1
-
d
2
), timestamp data (e.g.,
s
1
-
s
2
), and the vehicle information (e.g., “same license plate”)).
Regarding claim 4, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Shen further teaches the computer-implemented method of claim 1 further comprising:
generating, by the computer, the threshold disparity score based on the vehicle information, the timestamp data, the location coordinates of the one or more positions, and vehicle record data (description, para(s). [0036]—see citation in claim 1 above—, where determining a “set threshold
θ
” is generating a threshold disparity based on the vehicle information (e.g., “same license plate”), the location coordinates of the one or more positions (e.g.,
d
1
and
d
2
), and vehicle record data (e.g., “maximum speed limit information of the relevant road”)), wherein the threshold disparity score corresponds to a value that indicates a maximum level of geographic discrepancy between the location coordinates of the at least one first vehicle and the at least one second vehicle over time (description, para(s). [0036]— see citation in claim 1 above—, where the “maximum driving speed” is a maximum level of geographic discrepancy); and
comparing, by the computer, the confidence score with the generated threshold disparity score (description, para(s). [0036]— see citation in claim 1 above—, where determining if the “value is greater than a set threshold
θ
” is comparing the confidence score (e.g., the “value”) with the generated threshold disparity score (i.e., the “set threshold
θ
”)).
Regarding claim 5, Ming in view of Shen discloses the computer-implemented method of claim 4, wherein Shen further teaches the vehicle record data comprises at least one of vehicle history reports of the at least one first vehicle and the at least one second vehicle, spatial maps of the at least one first vehicle and the at least one second vehicle, insurance records of the at least one first vehicle and the at least one second vehicle, registration records of the at least one first vehicle and the at least one second vehicle, permitted speed limits at the one or more positions, weather data of the one or more positions, traffic data of the one or more positions, Department of Motor Vehicles (DMV) records of the at least one first vehicle and the at least one second vehicle, or service records of the at least one first vehicle and the at least one second vehicle (description, para(s). [0036]— see citation in claim 1 above—, where the “maximum speed limit information of the relevant road” is a vehicle record data comprising at least permitted speed limits at the one or more positions), and wherein the one or more positions correspond to specific locations where one or more data capture devices capture a set of images of the at least one first vehicle and the at least one second vehicle (description, para(s). [0036]— see citation in claim 1 above—, where the “checkpoints A and B” are specific locations; wherein para(s). [0004], [0062], [0089], and [0115] of Ming—see citations in claim 2 limitation “receiving… a set of images…” above—discloses the specific locations are where one or more data capture devices (e.g., “capturing unit (that is, integrated into the camera)”) capture a set of images of the two vehicles (e.g., “captured vehicle pictures” at the “current lane checkpoint” and the “second checkpoint”)).
Regarding claim 6, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Shen further teaches the computer-implemented method of claim 1 further comprising:
determining, by the computer, that the confidence score for the geo-location disparity factor exceeds the threshold disparity score based on the outcome of the comparison (description, para(s). [0036]— see citation in claim 1 above—, where determining if the “value is greater than a set threshold
θ
” is determining that the confidence score (e.g., the “value”) exceeds the threshold disparity score (e.g., “set threshold
θ
”)).
Regarding claim 7, Ming in view of Shen discloses the computer-implemented method of claim 6, wherein Shen further teaches the computer-implemented method of claim 6 further comprising:
determining, by the computer, that the confidence score indicates the vehicle cloning of the one of the at least one first vehicle or the at least one second vehicle based on the determination that the confidence score for the geo-location disparity factor exceeds the threshold disparity score (para description, para(s). [0036]— see citation in claim 1 above—, where determining “a suspected clone vehicle” when the “value is greater than a set threshold
θ
” is determining that the confidence score indicates vehicle cloning of at least one of the two vehicles; wherein the “value using the spatiotemporal rule” is at least a confidence score and the “set threshold
θ
” is at least a threshold disparity score).
Regarding claim 8, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Ming further discloses the computer-implemented method of claim 1 further comprising:
comparing, by the computer, the vehicle information of the at least one first vehicle and the at least one second vehicle with vehicle record data(para(s). [0080] and [0101], recite(s)
[0080] “After obtaining the above information, comparing the brand information, the model information, the color information and the license plate information of the current vehicle with the brand information, the model information, the color information and the license plate information of each vehicle in the vehicle information of all the vehicles, one by one, to determine whether a vehicle having structure information consistent with the current vehicle structure information and license plate information inconsistent with the current license plate information exists in all the vehicles.”
[0101] “a comparing judgment module 30 configured to obtain vehicle information of all vehicles under a name of a driver corresponding to the driver information, and compare the current vehicle information with the vehicle information of all the vehicles to determine whether a vehicle having structure information consistent with the current vehicle structure information and license plate information inconsistent with the current license plate information exists in all the vehicles …”
, where comparing the “current vehicle information with the information of all vehicles” is comparing vehicle information of the at least two vehicles (i.e., “current vehicle”) with vehicle record data (i.e., “vehicle information of all vehicles”));
classifying, by the computer, one of the at least one first vehicle or the at least one second vehicle as a cloned vehicle based on a result of comparison of the vehicle information of the at least one first vehicle and the at least one second vehicle with the vehicle record data (description, para(s). [0081], recite(s)
[0081] “S 104 , if there is a vehicle having the structure information consistent with the current structure information and the license plate information inconsistent with the current license plate information exists in all the vehicles, marking the current vehicle as a fake license plate vehicle.”
, where determining that a “current vehicle as a fake license plate vehicle” is classifying at least one of the at least two vehicles as a cloned vehicle; and determining the “license plate information” in the comparison as “inconsistent” is a result of the comparison of the vehicle information of one of the at least two vehicles (e.g., “current structure information”) with vehicle record data (e.g., “structure information”)); and
generating, by the computer, one or more classification alerts to notify law enforcement authorities that one of the at least one first vehicle or the at least one second vehicle is classified as the cloned vehicle (para(s). [0083], recite(s)
[0083] “…if the current vehicle is determined as the fake license plate vehicle, the relevant information of the current vehicle and its driver driving the current vehicle can be stored for subsequent forensic analysis by the police, or warning messages can be actively pushed to the police.”
, where pushing “warning messages” to notify the “police” is generating one or more classification alerts to notify law enforcement authorities; and the determined “fake license plate vehicle” is a classified cloned vehicle).
Where Ming does not specifically disclose
comparing, by the computer, the vehicle information of the at least one first vehicle and the at least one second vehicle with vehicle record data based on the determination that the confidence score indicates the vehicle cloning; and
classifying, by the computer, one of the at least one first vehicle or the at least one second vehicle as a cloned vehicle based on a result of the comparison of the vehicle information of the at least one first vehicle and the at least one second vehicle with the vehicle record data based on the determination that the confidence score indicates vehicle cloning;
Shen teaches in the same field of endeavor of classifying a vehicle as a cloned vehicle
comparing, by the computer, the vehicle information of the at least one first vehicle and the at least one second vehicle with vehicle record data based on the determination that the confidence score indicates the vehicle cloning (description, para(s). [0017-0021], recite(s)
[0017] “a) Establish a feature model
f
(
F
0
)
based on the features of the vehicle image registered by the vehicle management department corresponding to the license plate, and set the feature similarity threshold σ;”
[0018] “b) Based on the image features of the suspected cloned vehicle, such as license plate color, vehicle color, vehicle logo, headlight outline, front face outline, and overall shape outline, establish a suspected cloned vehicle model
f
(
F
x
)
.”
[0019] “c) Compare the suspected cloned vehicle model
f
(
F
x
)
with the feature model
f
(
F
0
)
one by one, and calculate the similarity of each feature;”
[0020] “d) Accumulate the similarity of each feature to obtain the total feature similarity of the suspected cloned vehicle model
f
(
F
x
)
. If the total feature similarity is less than the feature similarity threshold σ, the suspected cloned vehicle is determined to be a cloned vehicle; if the total feature similarity is greater than or equal to the feature similarity threshold σ, the vehicle is determined not to be a cloned vehicle.”
[0021] “…This invention uses spatiotemporal rules for initial judgment, followed by deep learning to build a model for vehicle type identification. The combination of spatiotemporal rules and deep learning results in higher recognition accuracy and shorter computation time required for image recognition after training, significantly improving the accuracy and speed of vehicle identification and enhancing the identification effect of cloned vehicles.”
, where performing “feature similarity” comparison following an “initial judgment” using “spatiotemporal rules” is comparing vehicle information (e.g., the “suspected cloned vehicle [feature] model”) with vehicle record data (e.g., a “feature model… corresponding to the license plate”) based on the determination that the confidence score indicates vehicle cloning (i.e., the “initial judgment” using “spatiotemporal rules” as previously taught by Shen in claim 1 above—see the teachings of Shen in claim 1 above)); and
classifying, by the computer, one of the at least one first vehicle or the at least one second vehicle as a cloned vehicle based on a result of the comparison of the vehicle information of the at least one first vehicle and the at least one second vehicle with the vehicle record data based on the determination that the confidence score indicates vehicle cloning (description, para(s). [0020]—see citation in preceding limitation immediately above—, where determining a “suspected cloned vehicle” as a “cloned vehicle” is classifying at least a vehicle as a cloned vehicle based on a result of the comparison of the vehicle information of the two vehicles with vehicle record data (e.g., “feature similarity” comparison)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ming to further incorporate comparing the vehicle information of the at least one first vehicle and the at least one second vehicle with vehicle record data based on the determination that the confidence score indicates the vehicle cloning to improve the identification of cloned vehicles as taught by para. [0021] of Shen above.
Regarding claim 9, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Ming further discloses the vehicle information comprises at least one of a license plate number of the at least one first vehicle and the at least one second vehicle, a brand of the at least one first vehicle and the at least one second vehicle, a model of the at least one first vehicle and the at least one second vehicle, an year of manufacture of the at least one first vehicle and the at least one second vehicle, a color of the at least one first vehicle and the at least one second vehicle, a Vehicle Identification Number (VIN) of the at least one first vehicle and the at least one second vehicle, an engine type of the at least one first vehicle and the at least one second vehicle, a fuel type of the at least one first vehicle and the at least one second vehicle, interior features of the at least one first vehicle and the at least one second vehicle, exterior features of the at least one first vehicle and the at least one second vehicle, registration details of the at least one first vehicle and the at least one second vehicle, or an insurance status of the at least one first vehicle and the at least one second vehicle (para(s). [0090]—see citation in claim 1 limitation “determining… a match…” above—, where the “license plate information” of a vehicle appearing at a “current” checkpoint and a “second” checkpoint is vehicle information comprising at least license plate numbers of the two vehicles).
Regarding claim 11, the claim recites similar limitations to claims 1 and 8, except in the form of a computer system. Therefore, claim 11 recites similar limitations to claim 1 and 8 and is rejected for similar rationale and reasoning (see the analysis for claims 1 and 8 above).
Regarding claim 12, the claim recites similar limitations to claim 5 and is rejected for similar rationale and reasoning (see the analysis for claim 5 above).
Regarding claim 14, the claim recites similar limitations to claim 9 and is rejected for similar rationale and reasoning (see the analysis for claim 9 above).
Regarding claim 16, the claim differs from claim 1 in that the claim is in the form of a computer program product. Therefore, claim 16 recites similar limitations to claim 1 and is rejected for similar rationale and reasoning (see the analysis for claim 1 above).
Regarding claim 17, the claim recites similar limitations to claim 8 and is rejected for similar rationale and reasoning (see the analysis for claim 8 above).
Regarding claim 18, the claim recites similar limitations to claim 5 and is rejected for similar rationale and reasoning (see the analysis for claim 5 above).
Regarding claim 19, the claim recites similar limitations to claim 9 and is rejected for similar rationale and reasoning (see the analysis for claim 9 above).
Claims 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Ming in view of Shen as applied to claims 1 and 11 above, and further in view of Hyug et al. (Hyug; KR 20220124430 A).
Regarding claim 2, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Ming further discloses the computer-implemented method of claim 1 further comprising:
receiving, by the computer, a set of images of the at least one first vehicle and the at least one second vehicle from one or more data capturing devices, wherein the one or more data capturing devices are positioned at a set of locations (para(s). [0004], [0062], [0089], and [0115], recite(s)
[0004] “At present, vehicle capturing systems are installed on main roads, intercity checkpoints, and high-speed entrances and exits, etc, so that it can capture all passing vehicles in various complex scenes under conventional technologies…”
[0062] “…the current vehicle picture can be detected and identified via license plate number recognition technology. It can be pointed out that the license plate number recognition technology can also be integrated into the capturing unit (that is, integrated into the camera) at the current lane checkpoint, because it is relatively mature,”
[0089] “…all the vehicles captured at the lane checkpoint can be stored and analyzed… for example, all the captured vehicle pictures…”
[0115] “a determining module 60 configured to: determine whether a fake license plate vehicle exists between the current vehicle and a vehicle corresponding to the current license plate captured at the second checkpoint…”
, where the “captured vehicle pictures” at least at the “current lane checkpoint” and the “second checkpoint” are a set of images of the two vehicles and the “capturing unit (that is, integrated into the camera) at the current lane checkpoint” or “vehicle capturing systems… installed on… intercity checkpoints…, etc.” are capturing devices);
detecting, by the computer, the first number plate and the second number plate in the set of images (para(s). [0090]—see citation in claim 1 limitation “determining… a match between a first number plate…and a second…” above—, where determining a “license plate” at a current checkpoint and a second checkpoint is detecting the first and second number plates in the set of images; wherein para(s). [0062]—see citation in preceding limitation immediately above—, recites detecting the number plates in the set of images by “license plate number recognition”);
detecting, by the computer, a first image of the first number plate(para(s). [0086], recite(s)
[0086] “S201 , performing vehicle identification analysis on the current vehicle picture captured by the capturing unit at the current lane checkpoint, so as to obtain current vehicle information corresponding to the current vehicle, the current vehicle information including current license plate information;”
, where the “current vehicle picture” capturing “current license plate information” is at least a first image of the first number plate);
determining, by the computer, the match between the first number plate and the second number plate(para(s). [0090]—see citation in claim 1 limitation “determining… a match between a first number plate…and a second…” above—, where determining the “appear[ance]” of the same “current license plate” at a “second checkpoint” is determining a match between the two number plates of the at least two vehicles).
Where Ming in view of Shen does not specifically disclose
detecting, by the computer, a first image of the first number plate and a second image of the second number plate…;
executing, by the computer, an Optical Character Recognition (OCR) process on the first image to extract a first set of characters from the first number plate using a first set of parameters, wherein the first set of characters is extracted based on the segmentation of the first image, and wherein the first set of parameters comprises at least one of a font of the first set of characters, a size of the first set of characters, an angle of the first set of characters, or lighting conditions of the first set of characters in the first number plate;
executing, by the computer, the OCR process on the second image to extract a second set of characters from the second number plate using a second set of parameters, wherein the second set of characters is extracted based on the segmentation of the second image, and wherein the second set of parameters comprises at least one of a font of the second set of characters, a size of the second set of characters, an angle of the second set of characters, or lighting conditions of the second set of characters in the second number plate;
comparing, by the computer, the first set of characters with the second set of characters using one of a Machine Learning (ML) model or fuzzy matching; and
determining, by the computer, the match between the first number plate and the second number plate based on the comparison of the first set of characters with the second set of characters;
Hyug teaches in the same field of endeavor of matching a first number plate of at least one first vehicle and a second number plate of at least one second vehicle
detecting, by the computer, a first image of the first number plate and a second image of the second number plate… (description, para(s). [0117], [0137-0138], and [0304], recite(s)
[0117] “…the camera system (200) can acquire a vehicle image, which is an image of a vehicle (e.g., a vehicle entering or exiting the parking space and/or a parked vehicle) related to a parking space (parking lot, etc.)…”
[0137] “…the license plate application (111) can obtain a vehicle image, which is an image of a vehicle entering a parking space (e.g., a vehicle entering a parking space) from a camera system (200) and/or its own image sensor (161).”
[0138] “Here, the vehicle image captured according to the embodiment may be an image including an image of the license plate of the vehicle within the image.”
[0304] “…the license plate application (111) can perform a comparison process to detect entry replacement image information that satisfies a predetermined matching rate (e.g., a preset value or higher) with the warping license plate image of the exiting vehicle among at least one previously stored entry replacement image information…”
, where the “image of the license plate” of a “vehicle entering a parking space” is at least a first image of a first number plate and the “image of the license plate” of an “exiting vehicle” is at least a second image of a second number plate);
executing, by the computer, an Optical Character Recognition (OCR) process on the first image to extract a first set of characters from the first number plate using a first set of parameters, wherein the first set of characters is extracted based on the segmentation of the first image, and wherein the first set of parameters comprises at least one of a font of the first set of characters, a size of the first set of characters, an angle of the first set of characters, or lighting conditions of the first set of characters in the first number plate (description, para(s). [0091], [0224-0225], and [0229-0230], recite(s)
[0091] “…vehicle image, license plate image, warped license plate image, text data based on optical character recognition (OCR), incoming vehicle information and/or outgoing vehicle information, etc.”
[0224] “…the license plate application (111) can perform Optical Character Recognition (OCR) based on a warped license plate image (hereinafter, warped license plate image).”
[0225] “Here, Optical Character Recognition (OCR) may refer to a processing that separates and detects text (e.g., numbers and/or characters) included in a license plate image into individual units.”
[0229] “…the license plate application (111) warps and corrects the license plate image obtained through segmentation map-based recognition into a form that facilitates the recognition of text within the license plate image (e.g., a form in which text within the license plate image is positioned horizontally), and performs optical character recognition (OCR) based on the warped and corrected license plate image, thereby enabling text extraction based on the license plate to be performed with high accuracy regardless of the angle from which the license plate is photographed.”
[0230] “…the license plate application (111) can generate and store entry vehicle information based on the optical character recognition (OCR) performed.”
, where the “text” extracted from the “license plate image” of an “entry vehicle” is a first set of characters from the first number plate and the “segmentation map-based recognition” correcting “warp[ing]” is a first set of parameters comprising at least an angle of the first set of characters);
executing, by the computer, the OCR process on the second image to extract a second set of characters from the second number plate using a second set of parameters, wherein the second set of characters is extracted based on the segmentation of the second image, and wherein the second set of parameters comprises at least one of a font of the second set of characters, a size of the second set of characters, an angle of the second set of characters, or lighting conditions of the second set of characters in the second number plate (description, para(s). [0091], [0224-0225], and [0229-0230]—see citations in limitation immediately above—, where description, para(s). [0289], recite(s):
[0285] “…the license plate application (111) can generate alternative image information for the exiting vehicle based on a warping license plate image for the exiting vehicle.”
[0289] “In this way, the license plate application (111) can easily obtain identification information (in the embodiment, vehicle information) for all vehicles exiting the vehicle regardless of the type of vehicle or license plate by obtaining license plate information (i.e., vehicle information in the embodiment) that specifies the vehicle exiting the vehicle, just as in the case of an incoming vehicle, using an optical character recognition (OCR) process…”
, where the OCR process described previously on a first image is used on “vehicles exiting” is executing the OCR process on the second image (i.e., exiting vehicles); where the “text” extracted from the “license plate image” of an “exiting vehicle” is a second set of characters from the second number plate and the “segmentation map-based recognition” correcting “warp[ing]” of the “license plate image for the exiting vehicle” is a second set of parameters comprising at least an angle of the second set of characters);
comparing, by the computer, the first set of characters with the second set of characters using one of a Machine Learning (ML) model or fuzzy matching (description, para(s). [0296] and [0334], recite(s)
[0296] “the license plate application (111) can compare at least one vehicle character specific information (hereinafter, incoming vehicle character specific information) within at least one incoming vehicle information stored in the license plate recognition service and the vehicle character specific information of the outgoing vehicle information (hereinafter, outgoing vehicle character specific information) when the 1) outgoing vehicle information includes vehicle character specific information.”
[0334] “The above deep learning-based vehicle license plate recognition method and system according to an embodiment of the present invention recognizes the license plate of an incoming or outgoing vehicle, which may be either a general vehicle or a special vehicle, using a deep learning neural network and performs incoming/outgoing vehicle management, thereby enabling the license plate recognition process to be performed for various types of license plates without exception, and by utilizing the vehicle identification information obtained therefrom, the effect of implementing a vehicle-related service (e.g., an incoming/outgoing vehicle management service, etc.) that accommodates all types of vehicles.”
, where the “character specific information” of the “incoming vehicle” is at least a first set of characters, the “character specific information” of the “outgoing vehicle” is at least a second set of characters, and the “deep learning-based vehicle license plate recognition method” comprising a “deep learning neural network” is at least a ML model); and
determining, by the computer, the match between the first number plate and the second number plate based on the comparison of the first set of characters with the second set of characters (description, para(s). [0322-0323], recite(s)
[0322] “…the license plate application (111) can determine the vehicle entering the vehicle corresponding to the detected vehicle entering alternative image information as the first vehicle entering the vehicle (i.e., the same vehicle) when the vehicle entering alternative image information matching the vehicle exiting alternative image information is detected through the comparison (i.e., when the vehicle entering warping license plate image that is determined to be identical to the vehicle exiting warping license plate image is detected).”
[0323] “…the license plate application (111) can detect an entry vehicle replacement image information that satisfies a predetermined matching rate (e.g., a preset value or higher) with the exit vehicle replacement image information, and can determine the entry vehicle corresponding to the detected entry vehicle replacement image information as the first entry vehicle (i.e., the same vehicle) for the exit vehicle.”
, where the “license plate image information” of the “entry vehicle” is at least a first number plate and the “license plate image information” of the “exit vehicle” is at least a second number plate).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ming in view of Shen to incorporate detecting a first image of the first number plate and a second image of the second number plate in the set of images, extracting respective set of characters of the respective number plates using a respective set of parameters comprising at least an angle of the respective set of characters of the respective number plates by executing an OCR process, comparing the first set of characters with the second set of characters using at least a ML model, and determining the match between the first and second number plates based on the comparison of their respective set of characters to recognize a same license plate number between two license plate images regardless of the angle from which the license plate is photographed as taught by Hyug (description, para. [0229]—see citation above).
Regarding claim 13, the claim recites similar limitations to claim 2 and is rejected for similar rationale and reasoning (see the analysis for claim 2 above).
Claims 10, 15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ming in view of Shen as applied to claims 1 and 11 above, and further in view of Li et al. (Li; “A framework for cloned vehicle detection,” 2020).
Regarding claim 10, Ming in view of Shen discloses the computer-implemented method of claim 1, wherein Li teaches in the same field of endeavor of vehicle cloning the computer-implemented method of claim 1 further comprising:
tracking, by the computer, data associated with one or more activities of the at least one first vehicle and the at least one second vehicle based on the vehicle information and the timestamp data (2nd para. of col. 2 on pg. 5, section 4.3 on pg. 10, and 3rd para. of col. 2 on pg. 10, recite(s)
[2nd para. of col. 2 on pg. 5] “…we attempt to discern the trajectories of different vehicles sharing the same VIN. First, the points in the mixed trajectories need to be grouped into different classes that belong to various vehicles. One critical step is to compute the possibility of the next inspection spot visited by vehicles, which can be accomplished by calculating the transition probability based on the historical trajectories between two inspection spots.”
[section 4.3 on pg. 10] “…it is imperative to identify the trajectories of different objects which use the same VIN, and then extract the moving behavior patterns of various objects. In this section, we first propose a trajectory identification method to discern the traces of objects with the same VIN, then mine the moving behavior patterns which are hidden in the traces.”
[3rd para. of col. 2 on pg. 10] “Algorithm 5 illustrates the detailed process of identifying the trajectory of each object. Figure 4 shows an example of the cloned vehicle trajectory, points
p
0
,
p
1
,
…
,
p
5
are collected by inspection spots at different timestamps. …”
, where tracking the “movement behavior patterns of various objects” including “of different vehicles sharing the same VIN” is tracking data associated with one or more activities of the at least two vehicles based on the vehicle information (e.g., “same VIN” or “cloned” license plate) and the timestamp data (i.e., the trajectories comprise of “timestamps”)); and
outputting, by the computer, the data associated with the one or more activities to law enforcement authorities based on a result of the tracking of the data (1st para. of col. 1 on pg. 2 and 2nd para. of pg. 12, recite(s)
[1st para. of col. 1 on pg. 2] “…Just imagine one vehicle cannot show up in two or more places at the same time, which is called the phenomena of spatial-temporal contradiction. According to the report, in 2016, Shanghai police detected that two Maserati with the same VIN appeared in a different area at once. It was this trail that led police to find one of them had stolen the VIN of the legal one. Based on this spot, if more than two vehicles with the same VIN are detected by different inspection spots located within a larger distance in a short time, they are identified as cloned vehicles. …”
[2nd para. of pg. 12] “The daily moving behavior pattern and the residence place of the vehicles can be used to predict the future movement of cloned vehicles and improve the accuracy of hunting for the suspect. …”
, where using the “moving behavior pattern” or predicted “future movement” of the at least two vehicles to “improve the accuracy of hunting for the suspect” such that it will lead “police to find” the “cloned vehicles” is outputting the data associated with the one or more activities to law enforcement authorities; where determining the “moving behavior pattern” or “future movement of cloned vehicles” is a result of the tracking of the data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to try tracking data associated with one or more activities of the at least one first vehicle and the at least one second vehicle based on the vehicle information and the timestamp data and outputting the data associated with the one or more activities to law enforcement authorities based on a result of the tracking of the data to improve notifying law enforcement authorities on cloned vehicles by providing data to track down the cloned vehicles as taught by Li above.
Regarding claim 15, the claim recites similar limitations to claim 10 and is rejected for similar rationale and reasoning (see the analysis for claim 10 above).
Regarding claim 20, the claim recites similar limitations to claim 10 and is rejected for similar rationale and reasoning (see the analysis for claim 10 above).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JULIA Z YAO whose telephone number is (571)272-2870. The examiner can normally be reached Monday - Friday (8:30AM - 5PM).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Emily Terrell can be reached at (571)270-3717. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.Z.Y./Examiner, Art Unit 2666
/MING Y HON/Primary Examiner, Art Unit 2666
Prosecution Insights