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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d).
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 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 of this title, 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.
Claim(s) 1, 2, 5 – 8 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) and further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang).
Regarding independent claim 1; Lin teaches:
An image inspection system inspecting an image recorded on a recording medium by a recording device (See ¶ 10-12 wherein an image inspection system (apparatus ‘10’ in figure 1, which carries out a print quality assessment of a printed document) inspects an image recorded on a recording medium by a recording device (printed image/document printed by a printer))
one or more hardware processors; and one or more memories storing one or more programs configured to be executed by the one or more hardware processors, the one or more programs including instructions (See ¶ 26, wherein there are one or more hardware processors (processor ‘40a’ in figure 2), and one or more memories (memory storage unit ‘35a’ in figure 2) storing one or more programs (instructions), wherein the instructions are executed by the processor to carry out processes needed in the assessment of print quality)
storing a first trained model that is generated by machine learning based on learning recorded images that are images for machine learning, recorded on recording media; (See ¶ 16, 22 – 24 wherein a machine learning model/CNN is trained on learned recorded images/test images recorded on recording media (printed image documents as a part of the test set))
acquiring a first probability of a defect being in an actual recorded image that is an object of inspection by the first trained model; (See ¶ 16 – 19, 24 – 28 wherein a defect probability is determined in an actual recorded image (image patch of recorded image) that is an object of inspection by the first trained model/Trained CNN).
acquiring a first estimation result that is an evaluation result regarding whether the actual recorded image is normal or abnormal by a first estimating portion on the basis of the first probability; (See ¶ 27 wherein an estimation result is acquired, being the determination of whether an image is labeled as defective or non-defective (normal/abnormal) on the basis of the first probability (being the defect probability that is compared to a threshold) by a first estimation portion (processing engine ‘27a’ in figure 2))
acquiring a second estimation result that is an evaluation result regarding whether the actual recorded image is normal or abnormal by a second estimating portion; (See ¶ 27 wherein a second estimation result is acquired, being the determination of whether an image is labeled as defective or non-defective (normal/abnormal) by a second estimation portion (processing engine ‘27a’ in figure 2), wherein a plurality of estimation results including a second estimation result, are acquired via the plurality of image patches being compared to a threshold leading to a plurality of estimation results).
Lin does not explicitly disclose storing a second trained model that is generated by machine learning based on recording information that is different from the learning recorded images and that is information relating to at least one of the recording device and the recording medium at a time of recording the learning recorded images.
However, Kawano teaches of storing a second trained model that is generated by machine learning based on recording information that is different from the learning recorded images and that is information relating to at least one of the recording device and the recording medium at a time of recording the learning recorded images (See ¶ 65 – 70, 75 and 76, wherein a second model (one of the two machine learning models ‘421A’ and ‘421B’ in figure 7) is generated by machine learning based on recording information being information related to the recording device (first control information ‘403’ in figure 7) and the recording medium (medium information ‘402’ in figure 7) at a time of recording the learning recorded images)
As taught by Kawano the use of two machine learning devices, wherein recording information is used for training for the models, allows for the machine learning device to reduce an amount of data required for the learning process needed to generate the two learning models that are used for generating accurate control information for a recording device. (See ¶ 76 wherein the amount of data required for the learning process to generate the two machine learning models is reduced). As both the teachings of Lin and Kawano deal with the technical field of image processing regarding the use of machine learning models for recorded images, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin with Kawano to teach of storing a second trained model that is generated by machine learning based on recording information that is different from the learning recorded images and that is information relating to at least one of the recording device and the recording medium at a time of recording the learning recorded images in order for the amount of data required for the learning process to generate the two machine learning models to be reduced.
Lin in view of Kawano does not explicitly disclose acquiring a second probability of a defect being in the actual recorded image by the second trained model.
However, Kikuta teaches of acquiring a second probability of a defect being in the actual recorded image by the second trained model (See ¶ 83, 84, 22, 18, 23, wherein a probability of a defect occurring is determined via a machine learning model using inspection parameters related to information regarding the recording device).
As taught by Kikuta the use of defect detection using a trained model allows for a determination on what items are free of defects that can be delivered as final products. (See ¶ 31 wherein final products can be delivered based on the information regarding the determination of defects). As both the teachings of Lin in view of Kawano and Kikuta deal with the technical field of image processing regarding analysis of recorded images using machine learning models, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano with Kikuta to teach of acquiring a second probability of a defect being in the actual recorded image by the second trained model in order for a determination on what items are free of defects that can be delivered as final products to be done.
Lin in view of Kawano and Kikuta does not explicitly disclose detecting a defect in the actual recorded image on the basis of the first estimation result and the second estimation result.
However, Tang teaches of detecting a defect in the actual recorded image on the basis of the first estimation result and the second estimation result (See ¶47 wherein a defect in an image is based on the basis of a first estimation and second estimation result, being the defect probability results output by the multiple models which are compared to each other).
As taught by Tang, having multiple models generate multiple estimation results of a defect allows for a comparison to be made between the multiple models before arriving at a conclusion on the detected defect. (See ¶ 47 wherein multiple models generate multiple defect probabilities that are compared to each other before a final determination of the defect is made). As both the teachings of Lin in view of Kawano and Kikuta and Tang deal with the technical field of image processing using machine learning models for defect detection in images, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano and Kikuta with Tang with to teach of detecting a defect in the actual recorded image on the basis of the first estimation result and the second estimation result in order for a comparison to be made between the multiple models before arriving at a conclusion on the detected defect.
Regarding dependent claim 2, Lin in view of Kawano, Kikuta, and Tang teaches:
In a case in which the first probability is no lower than a first threshold value, the first estimating portion sets the first estimation result to the effect that the actual recorded image has an abnormality, and in a case in which the second probability is no lower than a second threshold value, the second estimating portion sets the second estimation result to the effect that the actual recorded image has an abnormality. (See Lin ¶ 27, 41, wherein the first and second probabilities (defect probabilities of a plurality of image patches) are each compared to threshold values (first and second threshold) and based on the comparison with the threshold an estimation result of the recoded image being abnormal or normal is determined (determination of printed image document being a defective or a non-defective image)).
Regarding dependent claim 5, Lin in view of Kawano, Kikuta, and Tang teaches:
A data generating portion that divides image data acquired from the actual recorded image into a plurality and generates divided image data, wherein the first estimating portion estimates whether each of the plurality of the divided image data is normal or abnormal, and acquires the first estimation result on the basis of the estimation results thereof. (See Lin ¶ 27, 10 – 17, wherein a plurality of image patches (divided image data portions) are generated from the actual recorded image (printed image document) and wherein each image patch is identified as containing a defect or not (abnormal or normal) which is used to classify the whole image as abnormal or normal (acquiring first estimation result)).
Regarding dependent claim 6, Lin in view of Kawano, Kikuta, and Tang teaches:
The data generating portion divides the image data of the actual recorded image by a predetermined vertical width, a predetermined lateral width, and a predetermined shifting amount, and generates the divided image data. (See Lin ¶ 13, 15, 37, wherein the image data of the actual recorded image (printed image document) is divided into patches of 64x64 pixels (predetermined length and width) and wherein a predetermined shifting amount (displacement stride distance after generation of each patch) is also determined in the generation of the divided image data (image patch patches)).
Regarding dependent claim 7, Lin in view of Kawano, Kikuta, and Tang teaches:
When it is determined that one or more pieces of the divided image data is abnormal, the first estimating portion decides that the first estimation result indicates that the actual recorded image has an abnormality. (See Lin ¶ 27, wherein once it is determined that one of the image patches has a defect (divided image data is abnormal) area over a threshold, the entire image (actual recorded image) is determined to have an abnormality (first estimation result)).
Regarding dependent claim 8, Lin in view of Kawano, Kikuta, and Tang teaches:
The recording information includes at least one of ink concentration at a time of recording the image, environment temperature, environment humidity, thickness of an actual recording medium on which the actual recorded image is recorded, and coating type of the actual recording medium. (See Kawano ¶ 69, wherein the recording information (medium information ‘402’ in figure 7) includes thickness of print medium (thickness of an actual recording medium on which the actual recorded image is recorded), furthermore the use of “at least one of”, makes it so that only one of the recording information possibilities is required to be taught by the prior art.)
Regarding dependent claim 19, Lin in view of Kawano, Kikuta, and Tang teaches:
When the first estimation result is abnormal, the second estimating portion acquires the second estimation result. (See Lin ¶ 27, 17 – 19, wherein, the analyzation of all image patches is done regardless of the estimation result of a previous patch, therefore when the first estimation result is abnormal (defect detected), the next image patch is still analyzed resulting in a second estimation result being acquired).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang) and further in view of Darvish; Zadeh et al. (WO 2021232149 A1; hereinafter simply referred to as Darvish; Translated via Espacenet).
Regarding dependent claim 4, Lin in view of Kawano, Kikuta, and Tang teaches:
The first trained model is generated by machine learning based on the learning recorded images (See Lin ¶ 22 – 24, 31 – 33 wherein, the first trained model (Convolutional neural network) is generated by machine learning based on the learning recorded images (training of model via printed image documents)).
Lin in view of Kawano, Kikuta, and Tand does not explicitly disclose Generating machine learning model based on learning using an evaluation result regarding whether the learning recorded images are normal or abnormal and wherein the evaluation result is data in which a probability of a defect being in the actual recorded image is 100% in a case in which the recorded image is abnormal, and is data in which a probability of a defect being in the actual recorded image is 0% in a case in which the recorded image is normal.
However, Darvish teaches of Generating machine learning model based on learning using an evaluation result regarding whether the learning recorded images are normal or abnormal, (See ¶ 61 wherein the machine learning model is trained using tagged/labeled image data (evaluation results) regarding whether the recorded images are normal or abnormal (having defects or no defects))
and wherein the evaluation result is data in which a probability of a defect being in the actual recorded image is 100% in a case in which the recorded image is abnormal, and is data in which a probability of a defect being in the actual recorded image is 0% in a case in which the recorded image is normal. (See ¶ 61, wherein the evaluation result data (labels/tags) are representative of an image 100% having a defect making it abnormal represented by one of the 1 to n labels and 0% in a case in which the recorded image is normal represented by the 0 label when the image is non-defective and therefore normal).
As taught by Darvish the labelling of images with an evaluation result for training a machine learning model to detect defects allows for multiple different types of defects to be learnt by the model with the use of different labels. (See ¶ 61 wherein multiple different labels can be used in the training of the machine learning model allowing the model to detect if an image has a defect and what type of defect it is). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Darvish deal with the technical field of image processing regarding the use of machine learning models for detecting image defects, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Darvish to teach of generating machine learning model based on learning using an evaluation result regarding whether the learning recorded images are normal or abnormal and wherein the evaluation result is data in which a probability of a defect being in the actual recorded image is 100% in a case in which the recorded image is abnormal, and is data in which a probability of a defect being in the actual recorded image is 0% in a case in which the recorded image is normal in order for multiple different labels to be used in the training of the machine learning model allowing the model to detect if an image has a defect and what type of defect it is.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang) and further in view of Murray; Richard (US 8251475 B2; hereinafter simply referred to as Murray).
Regarding dependent claim 9, Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose:
The recording information includes at least one of position information of a liquid discharge head that discharges liquid, which the recording device is equipped with, at a time of recording the image, count of times of cleaning a nozzle of the liquid discharge head, and a roller diameter of a roller making up a conveying path for the recording medium, which the recording device is equipped with.
However, Murray teaches of the recording information includes at least one of position information of a liquid discharge head that discharges liquid, which the recording device is equipped with, at a time of recording the image, count of times of cleaning a nozzle of the liquid discharge head, and a roller diameter of a roller making up a conveying path for the recording medium, which the recording device is equipped with. (See Col 1 Lines 50 – 61, wherein recording information includes at least one of feed roller diameter of a roller making up a conveying path for the recording medium which the recording device (printer) is equipped with; furthermore the use of “at least one of”, makes it so that only one of the recording information possibilities is required to be taught by the prior art).
As taught by Murray it is common for feed roller diameter errors to occur and thus the recording/monitoring of the feed roller allows for knowledge to be had on a printing device component that often causes errors. (See Col 1 Lines 50 – 61 wherein the monitoring of the feed roller allows for knowledge to be had about a printing device component that often causes errors). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Murray deal with the technical field of image processing regarding the errors in a printed medium, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawana, Kikuta, and Tang with Murray to teach of the recording information includes at least one of position information of a liquid discharge head that discharges liquid, which the recording device is equipped with, at a time of recording the image, count of times of cleaning a nozzle of the liquid discharge head, and a roller diameter of a roller making up a conveying path for the recording medium, which the recording device is equipped with in order to allow for knowledge to be had about a printing device component that often causes errors.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang) and further in view of Portnoy; Vitaly et al. (US 11774895 B2; hereinafter simply referred to as Portnoy).
Regarding dependent claim 10, Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose:
The second estimating portion includes the recording information at a plurality of points in time at time of recording the image.
However, Portnoy teaches of the second estimating portion includes the recording information at a plurality of points in time at time of recording the image. (See Col 3 Lines 65 – 67, Col 4 Lines 1 – 9, Col 5 Lines 26 – 37, Col 4 Lines 47 – 67, wherein the second estimation portion (machine learning model ‘116’ in figure 1) includes the recording information (physical characteristic measurements ‘112’ in figure 1) at a plurality of points in time at time of recording the image).
As taught by Portnoy, the second estimation portion including recording information at a plurality of points in time at time of recording the image allows for a machine learning model to maximize the lifespan of replaceable items using the characteristic measurements (recording information) (See Col 4 Lines 47 – 67, Col 5 Lines 1 – 5 wherein the recording information including a plurality of points in time at time of recording the image allows for the machine learning model to maximize the lifespan of replaceable items based on characteristic measurements). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Portnoy deal with the technical field of image processing regarding machine learning to assess recording devices, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Portnoy to teach of the second estimating portion includes the recording information at a plurality of points in time at time of recording the image in order to allow for the maximization of lifespans of replaceable items.
Claim 11 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang) and further in view of Kyoso; Tadashi et al. (US 20150336381 A1; hereinafter simply referred to as Kyoso).
Regarding dependent claim 11, Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose:
The second estimating portion estimates whether or not each of the recording information at the plurality of points in time is normal, and acquires the second estimation result on the basis of the estimation results thereof.
However, Kyoso teaches of the second estimating portion estimates whether or not each of the recording information at the plurality of points in time is normal, and acquires the second estimation result on the basis of the estimation results thereof. (See ¶ 176, 179, 117, 160 wherein the reading unit ‘24’ in figure 1, (second estimating portion) estimates whether or not each of the recording information at a plurality of points in time is normal (continuous in real time checking of defective ejector being normal/abnormal) and acquires the second estimation result on the basis of the estimation results (determination of the ejector being normal or not based on continues comparing with a threshold)).
As taught by Kyoso, once an estimation result is received action can be taken if the estimation result is abnormal in order to perform a correction process. (See ¶ 178 wherein a correction process is performed once an estimation result is received called non-ejection correction). As both the teachings of Lin in view of Kawano, Kikuta, and Tang deal with the technical field of image processing regarding printing devices, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kyoso to teach of the second estimating portion estimates whether or not each of the recording information at the plurality of points in time is normal, and acquires the second estimation result on the basis of the estimation results thereof in order for a correction process to be performed once an estimation result is received.
Regarding dependent claim 12, Lin in view of Kawano, Kikuta, Tang, and Kyoso teaches:
When it is determined that one or more pieces of recording information of the recording information at the plurality of points in time is abnormal, the second estimating portion decides that the second estimation result is to the effect that the actual recorded image has an abnormality. (See Kyoso ¶ 176 - 179, 117, 160, 124 wherein once it is determined that one or more pieces of recording information of the recording information at the plurality of point in time is abnormal (defective/abnormal ejector being determined after continuously checked during printing process) the actual recorded image is determined to have an abnormality, being the streaks on the printed image).
Claims 13 – 18 are rejected under 35 U.S.C. 103 as being unpatentable over Lin Qian et al. (US 20210337073 A1; hereinafter simply referred to as Lin) in view of Kawano Akimitsu et al. (US 20210195033 A1; hereinafter imply referred to as Kawano) further in view of Kikuta Kyohei et al. (JP 2021180404 A; hereinafter simply referred to as Kikuta) further in view of Tang Peng et al. (US 20210209414 A1; hereinafter simply referred to as Tang) and further in view of Kobayashi; Masato et al. (US 20240422268 A1; hereinafter simply referred to as Kobayashi).
Regarding dependent claim 13, Lin in view of Kawano, Kikuta, and Tang teaches:
Both the first estimation result and the second estimation result are determined to be abnormal, (See Lin ¶ 27, 17 – 19 wherein both the first and second estimation results are determined to be abnormal (image patches having defects and the region being over a threshold resulting in the image being defective/abnormal)).
Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose the image inspection system notifies a user that there is a defect in the actual recorded image.
However, Kobayashi teaches of the image inspection system notifies a user that there is a defect in the actual recorded image (See ¶ 81 wherein the image inspection system (UI unit ‘320’ in figure 3) notifies the user that there is a defect in the actual recorded image (accentuates the defect in the image displayed to the user)).
As taught by Kobayashi notifying the user that there is a defect in the actual recorded image allows the user to see the defect that is present. (See ¶ 81 wherein the defect is displayed to the user via the image having an accentuated area that highlights the defect). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Kobayashi deal with the technical field of image processing regarding image defects, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kobayashi to teach of the image inspection system notifies a user that there is a defect in the actual recorded image in order for the user to see the defect that is present.
Regarding dependent claim 14, Lin in view of Kawano, Kikuta, Tang and Kobayashi teaches:
When there is a defect in the actual recorded image, the image inspection system notifies a user of a defect portion being present. (See Kobayashi ¶ 81 wherein the image inspection system / UI unit ‘320’ in figure 3, notifies a user of a defect portion being present, represented by the accentuating of the defect portion via broken lines or a colored frame, displayed to the user).
Regarding dependent claim 15, Lin in view of Kawano, Kikuta, and Tang teaches:
Both the first estimation result and the second estimation result are determined to be abnormal, (See Lin ¶ 27, 17 – 19 wherein both the first and second estimation results are determined to be abnormal (image patches having defects and the region being over a threshold resulting in the image being defective/abnormal)).
Lin in view of Kawano, Kikuta, and Tand does not explicitly disclose recording operations being executed by the recording device are stopped once an estimation result has been determined as abnormal due to a defect being present.
However, Kobayashi teaches of recording operations being executed by the recording device are stopped once an estimation result has been determined as abnormal due to a defect being present. (See ¶ 45 wherein once a defect has been identified, the printing/recording operations being executed are stopped).
As taught by Kobayashi, the operations being executed by the recording device are stopped once a defect has been detected, resulting in time saved by not producing a defective image. (See ¶ 45 wherein the operations being executed are stopped once a defect is detected which results in saved time from producing a defective image). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Kobayashi deal with the technical field of image processing regarding defective images, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kobayashi to teach of recording operations being executed by the recording device are stopped once an estimation result has been determined as abnormal due to a defect being present in order to save time from producing a defective image.
Regarding dependent claim 16, Lin in view of Kawano, Kikuta, and Tang teaches:
When the first estimation result is abnormal and the second estimation result is normal, or when the first estimation result is normal and the second estimation result is abnormal (See Lin ¶ 27, 17 – 19, wherein image patches are determined to contain a defect or not resulting in a plurality of estimation results (including a first and second estimation result) wherein the plurality of estimation results includes a first estimation being normal and a second estimation result being abnormal and a first estimation being abnormal and a second estimation result being normal, wherein both of these results comprise the image being determined to be abnormal and having a defect).
Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose the image inspection system notifies a user that a defect may be present in the actual recorded image.
However, Kobayashi teaches of the image inspection system notifies a user that a defect may be present in the actual recorded image. (See ¶ 81 wherein the image inspection system (UI unit ‘320’ in figure 3) notifies the user that there is a defect in the actual recorded image (accentuates the defect displayed to the user)).
As taught by Kobayashi notifying the user that there is a defect in the actual recorded image allows the user to see the defect that is present. (See ¶ 81 wherein the defect is displayed to the user via the image having an accentuated area that highlights the defect). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Kobayashi deal with the technical field of image processing regarding image defects, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kobayashi to teach of the image inspection system notifies a user that a defect may be present in the actual recorded image in order for the user to see the defect that is present.
Regarding dependent claim 17, Lin in view of Kawano, Kikuta, and Tang teaches:
When the first estimation result is abnormal and the second estimation result is normal (See Lin ¶ 27, 17 – 19 wherein a first estimation result is abnormal and the second estimation result is normal, being the plurality of estimation results gathered from the image patch defect analysis, leading to the image being determined to have a defect and being abnormal).
Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose the image inspection system notifies a user that a defect portion in the image data of the actual recorded is present.
However, Kobayashi teaches of the image inspection system notifies a user that a defect portion in the image data of the actual recorded is present (See ¶ 81 wherein the image inspection system (UI unit ‘320’ in figure 3) notifies the user that there is a defect in the actual recorded image (accentuates the defect displayed to the user)).
As taught by Kobayashi notifying the user that there is a defect in the actual recorded image allows the user to see the defect that is present. (See ¶ 81 wherein the defect is displayed to the user via the image having an accentuated area that highlights the defect). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Kobayashi deal with the technical field of image processing regarding image defects, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kobayashi to teach of the image inspection system notifies a user that a defect portion in the image data of the actual recorded is present in order for the user to see the defect that is present.
Regarding dependent claim 18, Lin in view of Kawano, Kikuta, and Tang teaches:
The first estimation result is normal and the second estimation result is abnormal (See Lin ¶ 27, 17 – 19 wherein a first estimation result is normal and the second estimation result is abnormal, being the plurality of estimation results gathered from the image patch defect analysis, leading to the image being determined to have a defect and being abnormal).
Lin in view of Kawano, Kikuta, and Tang does not explicitly disclose the image inspection system notifies a user of information representing parameter data that contributes to the abnormal determination.
However, Kobayashi teaches of the image inspection system notifies a user of information representing parameter data that contributes to the abnormal determination. (See ¶ 81 wherein the image inspection system (UI unit ‘320’ in figure 3) notifies the user that there is a defect in the actual recorded image (accentuates the defect displayed to the user) and provides parameter data that contributes to the abnormal determination (position information)).
As taught by Kobayashi notifying the user that there is a defect in the actual recorded image allows the user to see the defect that is present. (See ¶ 81 wherein the defect is displayed to the user via the image having an accentuated area that highlights the defect). As both the teachings of Lin in view of Kawano, Kikuta, and Tang and Kobayashi deal with the technical field of image processing regarding image defects, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Lin in view of Kawano, Kikuta, and Tang with Kobayashi to teach of the image inspection system notifies a user of information representing parameter data that contributes to the abnormal determination in order for the user to see the defect that is present.
Allowable Subject Matter
Claim 3 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indications of allowable subject matter:
Regarding claim 3, the reason of allowable subject matter is that the prior art fails to teach or reasonably suggest the limitations of claim 2, further comprising wherein the first threshold value and the second threshold value are 50%.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEJANDRO HERNANDEZ whose telephone number is (703)756-1876. The examiner can normally be reached M-F 8 am - 5 pm ET.
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, John M Villecco can be reached at (571) 272-7319. 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.
/ALEJANDRO HERNANDEZ/Examiner, Art Unit 2661
/AARON W CARTER/Primary Examiner, Art Unit 2661
Prosecution Insights