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 .
Claims 1-20 are currently pending.
Please refer to the action below.
Examiner Notes
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. However, the claimed subject matter, not the specification, is the measure of the invention.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3, 6, 8-9, 11, 14-17, and 20 is/are rejected under 35 U.S.C. 102 (a)(2) as being unpatentable by Shang et al. (US 2023/0215202, A1).
Regarding claim 1, Shang teaches at least in the Abstract a computer-implemented method for performing character recognition in images,
the computer-implemented method comprising:
receiving an input image displaying an input text comprising one or more input characters (received input images 202 of para. 0059-0060 configured to be displayed on a display screen including said input text comprising the one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (at least para. 0060 and 0090 further comprises performed pre-processing of the input image before the performing of an OCR process further comprises said performing set of transformations including at least rescaling, or other image modifications on said input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least para. 0061-0063 based on at least an OCR process a set of candidate text predictions by performing text recognition on each transformed image implied further in para. 0060 of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions
for each candidate text prediction from the set of candidate text predictions (determining further para. 0061-0063 and 0066 representative text substrings information as said representative text prediction for the set of candidate text predictions);
determining edits that transform the representative text prediction to the candidate text prediction (determining further in at least para. 0009-0012, and 0072-0074 based on at least one or more stored Levenshtein edit distance as a set of edit operations that transform the representative text prediction to the candidate text prediction);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (a regular expression of at least para. 0085 is determined and search based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction);
using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further configures in at least para. 0085-0086 as further supported by para. 0069-0070 and 0074 for using the regular expression to identify and match a text string from an implied stored database as a final text predicted based on the input image).
Regarding claim 3 (according to claim 1), Shang further teaches wherein further comprising: for each character of the representative text prediction, storing a set of edit operations, each edit operation performed to transform the representative text prediction to at least one of the set of candidate text predictions (stored edits of further para. 0009-0012, and 0100 further supported by para. 0071-0072 further utilized for each character of the representative text prediction, as each of the said edit operation performed to transform the representative text prediction to at least one of the set of candidate text predictions); wherein the regular expression is determined based on the sets of edit operations associated with each character of the representative text prediction (the system of at least para. 0074 further supported by para. 0069-0070 further illustrates a case wherein the regular expression is matched or determined based on the sets of edit operations associated with each character of the representative text prediction).
Regarding claim 6 (according to claim 3), Shang further teaches wherein the regular expression includes a term corresponding to a character of the representative text prediction (the Abstract further teaches the obtained regular expression which includes obviously a term corresponding to a character of the representative text prediction),
wherein a type of match performed using the term depends on the sets of edit operations associated with the character (the system as shown in the Abstract retrieves or find a substring as a type of match performed using the term depends on the sets of edit operations of at least para. 0009-0010 associated with the character).
Regarding claim 8 (according to claim 1), Shang further teaches wherein using the regular expression to identify a text string from a database as the final text predicted based on the input image comprises: matching the regular expression against text values in the database (performed fuzzy matching of further para. 0074 further supported by para. 0069-0070 of the regular expression against text values in a known database);
selecting one or more text values from the database based on the matching (select substrings of further para. 0070-0074); and returning the one or more text values as results of recognition of text of the input image (para. 0070-0074).
Regarding claim 9, Shang teaches in at least para. 0041-0042 a computer readable non-transitory storage medium storing instructions that when executed by one or more computer processors cause the one or more computer processors to perform steps comprising:
receiving an input image displaying an input text comprising one or more input characters (received input images 202 of para. 0059-0060 configured to be displayed on a display screen including said input text comprising the one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (at least para. 0060 and 0090 further comprises performed pre-processing of the input image before the performing of an OCR process further comprises said performing set of transformations including at least rescaling, or other image modifications on said input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least para. 0061-0063 based on at least an OCR process a set of candidate/sensitive text predictions by performing text recognition on each transformed image implied further in para. 0060 of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions (determining further para. 0061-0063 and 0066 representative text substrings information as said representative text prediction for the set of candidate text predictions);
for each candidate text prediction from the set of candidate text predictions, determining edits that transform the representative text prediction to the candidate text prediction (determined further in para. 0064, 0072 at least a Levenshtein edit that transform the representative text prediction to the candidate text prediction);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (a regular expression of at least para. 0085 is determined and search based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction);
and using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further configures in at least para. 0085-0086 as further supported by para. 0069-0070 and 0074 for using the regular expression to identify and match a text string from an implied stored database as a final text predicted based on the input image).
Regarding claim 11 (according to claim 9), Shang further teaches wherein the instructions further cause the one or more computer processors to perform steps comprising: for each character of the representative text prediction, storing a set of edit operations, each edit operation performed to transform the representative text prediction to at least one of the set of candidate text predictions (the system at least in para. 0009-0010 stores a set of edit operations for at least replacing, deleting, such as to transform the representative text prediction to at least one of the set of candidate text predictions);
wherein the regular expression is determined based on the sets of edit operations associated with each character of the representative text prediction (a regular expression process of at least para. 0010 is used or determined based on the sets of Levenshtein edit operations associated with each character of the representative text prediction).
Regarding claim 14 (according to claim 11), Shang further teaches wherein the regular expression includes a term corresponding to a character of the representative text prediction (the Abstract further teaches the obtained regular expression which includes obviously a term corresponding to a character of the representative text prediction),
wherein a type of match performed using the term depends on the sets of edit operations associated with the character (the system as shown in the Abstract retrieves or find a substring as a type of match performed using the term depends on the sets of edit operations of at least para. 0009-0010 associated with the character).
Regarding claim 15 (according to claim 9), Shang further teaches wherein using the regular expression to identify a text string from a database as the final text predicted based on the input image comprises: matching the regular expression against text values in the database (the system further in para. 0066-0068 teaches obtaining matched or sufficiently similar text strings corresponding to the used regular expression to identify said text string from an implied database as the final text predicted based on the input image),
selecting one or more text values from the database based on the matching (select substrings of further para. 0070-0074); and returning the one or more text values as results of recognition of text of the input image (para. 0070-0074).
Regarding claim 16, Shang teaches in at least para. 0041-0042 a computer-implemented system comprising: one or more computer processors (at least para. 0042); and a computer readable non-transitory storage medium (para. 0041-0042) storing instructions that when executed by the one or more computer processors cause the one or more computer processors to perform steps comprising:
receiving an input image displaying an input text comprising one or more input characters (received input images 202 of para. 0059-0060 configured to be displayed on a display screen including said input text comprising the one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (at least para. 0060 and 0090 further comprises performed pre-processing of the input image before the performing of an OCR process further comprises said performing set of transformations including at least rescaling, or other image modifications on said input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least para. 0061-0063 based on at least an OCR process a set of candidate/sensitive text predictions by performing text recognition on each transformed image implied further in para. 0060 of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions (determining further para. 0061-0063 and 0066 representative text substrings information as said representative text prediction for the set of candidate text predictions);
for each candidate text prediction from the set of candidate text predictions, determining edits that transform the representative text prediction to the candidate text prediction (determined further in para. 0064, 0072 at least a Levenshtein edit that transform the representative text prediction to the candidate text prediction);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (a regular expression of at least para. 0085 is determined and search based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction);
and using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further configures in at least para. 0085-0086 as further supported by para. 0069-0070 and 0074 for using the regular expression to identify and match a text string from an implied stored database as a final text predicted based on the input image).
Regarding claim 17 (according to claim 16), Shang further teaches wherein the instructions further cause the one or more computer processors to perform steps comprising: for each character of the representative text prediction, storing a set of edit operations, each edit operation performed to transform the representative text prediction to at least one of the set of candidate text predictions (the system at least in para. 0009-0010 stores a set of edit operations for at least replacing, deleting, such as to transform the representative text prediction to at least one of the set of candidate text predictions);
wherein the regular expression is determined based on the sets of edit operations associated with each character of the representative text prediction (a regular expression process of at least para. 0010 is used or determined based on the sets of Levenshtein edit operations associated with each character of the representative text prediction).
Regarding claim 20 (according to claim 16), Shang further teaches wherein using the regular expression to identify a text string from a database as the final text predicted based on the input image comprises: matching the regular expression against text values in the database (performed fuzzy matching of further para. 0074 further supported by para. 0069-0070 of the regular expression against text values in a known database);
selecting one or more text values from the database based on the matching (select substrings of further para. 0070-0074); and returning the one or more text values as results of recognition of text of the input image (para. 0070-0074).
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, 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) 2, and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable and obvious over Shang in view of Calapodescu et al. (US 2017/0300565, A1).
Regarding claim 2 (according to claim 1), and claim 10 (according to claim 9), Shang is silent regarding wherein the representative text prediction is a medoid of the set of candidate text predictions.
Calapodescu teaches in at least the Abstract, and para. 0085, and 0140-0143 performing text recognition and extraction of an image document, the system further uses a set of medoids as representative text predictions of the set of candidate text predictions for searching and matching closely related texts. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Calapodescu to include wherein representative text prediction is a medoid of the set of candidate text predictions, as discussed above, as Shang in view of Calapodescu are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Calapodescu complements the text image recognition process of Shang with a supplemented representative text prediction being a medoid of the set of candidate text predictions, where the medoids closely match related texts based on known matching techniques to further output said text representation according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Claim(s) 4-5, 7, 12-13, and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable and obvious over Shang in view of Soldevilla et al. (US 2016/0210532, A1).
Regarding claim 4 (according to claim 3), Shang is silent regarding wherein further comprising: for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction.
Soldevilla teaches in at least para. 0047 applying at least a string of edit operations to for each character of para. 0044-0044 and 0052-0055 associating with potential or representative text prediction, determining or generating further in at least para. 0052-0053, 0063 and 0074 for each character of the representative text prediction, a similarity measure as an indicative confidence score based on in a case the set of edit string operations associated with the character, wherein a regular expression match in the form of a wildcard expression of para. 0013 or a license plate number is determined based on the calculated similarity measure or confidence score of at least para. 0052-0053, 0063 and 0074 associated with each character of the representative text prediction. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 5 (according to claim 4), Shang is silent regarding wherein the regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value.
Soldevilla further teaches at least in the Abstract and para. 0008-0013 a regular expression in the form of at least cited wild cards expression includes at least a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match of least para. 0008-0013 if a similarity score or confidence score of further para. 0052-0053, 0063 and 0074 associated with the character is obviously greater than a threshold value. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction in relation to a match wildcard or regular expression score including at least a comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 7 (according to claim 5), Shang is silent regarding wherein the term corresponding to a character of the representative text prediction performs a wild card match if a number of edits in the set of edits is above a threshold value.
Soldevilla further teaches in at least para. 0008-0010, 0041, and 0180 performing a set of edits operation to a regular or wildcard expression to arrive to a character of the representative text prediction wherein term of said expression corresponds to a character of the representative text prediction further performs a wild card match of further para. 0013, 0041, if a number of edits in the set of edits is as understood in the art is above a threshold value. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein term corresponding to a character of the representative text prediction performs a wild card match if a number of edits in the set of edits is above a threshold value, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented wild card match performing process corresponding to a representative text prediction including at least a comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 12 (according to claim 11), Shang is silent regarding wherein the instructions further cause the one or more computer processors to perform steps comprising: for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction.
Soldevilla teaches in at least para. 0047 applying at least a string of edit operations to for each character of para. 0044-0044 and 0052-0055 associating with potential or representative text prediction, determining or generating further in at least para. 0052-0053, 0063 and 0074 for each character of the representative text prediction, a similarity measure as an indicative confidence score based on in a case the set of edit string operations associated with the character, wherein a regular expression match in the form of a wildcard expression of para. 0013 or a license plate number is determined based on the calculated similarity measure or confidence score of at least para. 0052-0053, 0063 and 0074 associated with each character of the representative text prediction. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 13 (according to claim 12), Shang is silent regarding wherein the regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value.
Soldevilla further teaches at least in the Abstract and para. 0008-0013 a regular expression in the form of at least cited wild cards expression includes at least a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match of least para. 0008-0013 if a similarity score or confidence score of further para. 0052-0053, 0063 and 0074 associated with the character is obviously greater than a threshold value. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction in relation to a match wildcard or regular expression score including at least a comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 18 (according to claim 17), Shang is silent regarding wherein the instructions further cause the one or more computer processors to perform steps comprising: for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction.
Soldevilla teaches in at least para. 0047 applying at least a string of edit operations to for each character of para. 0044-0044 and 0052-0055 associating with potential or representative text prediction, determining or generating further in at least para. 0052-0053, 0063 and 0074 for each character of the representative text prediction, a similarity measure as an indicative confidence score based on in a case the set of edit string operations associated with the character, wherein a regular expression match in the form of a wildcard expression of para. 0013 or a license plate number is determined based on the calculated similarity measure or confidence score of at least para. 0052-0053, 0063 and 0074 associated with each character of the representative text prediction. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein for each character of the representative text prediction, determining a confidence score based on the set of edit operations associated with the character, wherein the regular expression is determined based on the confidence score associated with each character of the representative text prediction, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Regarding claim 19 (according to claim 18), Shang is silent regarding wherein the regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value.
Soldevilla further teaches at least in the Abstract and para. 0008-0013 a regular expression in the form of at least cited wild cards expression includes at least a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match of least para. 0008-0013 if a similarity score or confidence score of further para. 0052-0053, 0063 and 0074 associated with the character is obviously greater than a threshold value. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Shang in view of Soldevilla to include wherein regular expression includes a term corresponding to a character of the representative text prediction, wherein the term of the regular expression performs an exact match if the confidence score associated with the character is greater than a threshold value, as discussed above, as Shang in view of Soldevilla are in the same of endeavor of performing text recognition and extracting candidate texts from an input image using a pre-process and a post-process to output a final result, Soldevilla complements the text image recognition process of Shang with a supplemented representative text prediction in relation to a match wildcard or regular expression score including at least a comparison and similarity score calculation which when applied to the text recognition of Shang further advantageously generate an exact character expression match correlating to at least a wildcard expression thereby generating closely related text prediction matches according to further known methods to yield predictable results since known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art as said combination is thus the adaptation of an old idea or invention using newer technology that is either commonly available and understood in the art thereby a variation on already known art (See MPEP 2143, KSR Exemplary Rationale F).
Claim(s) 1, 9, and 16 is/are further rejected under 35 U.S.C. 102 (a)(1) as being unpatentable by Soldevilla.
Regarding claim 1, Soldevilla teaches at least in para. 0040 a computer-implemented method for performing character recognition in images,
the computer-implemented method comprising:
receiving an input image displaying an input text comprising one or more input characters (received image of further para. 0040, 0052-0055 and Figs. 1 and 3 as said an input image displaying an input text 14 comprising one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (performed set of transformations of at least para. 0043 and 0054 on the input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least Fig. 3 and para. 0054 sets of set of candidate text predictions by performing text recognition on each pre-processed or transformed image of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions (determining further in at least Fig. 3 and para. 0054 determining representative text strings or prediction for the set of candidate text predictions);
for each candidate text prediction from the set of candidate text predictions, determining edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0054, 0150, and 0180 determined edits that transform the representative text prediction to the candidate text prediction for each of the said candidate text prediction from the set of candidate text predictions);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 for determining a regular expression in the form of a wildcard character expression based on the representative text prediction and the set of edits operations that transform the representative text prediction to the candidate text prediction); and
using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further adapted for using the regular expression of at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 to identify a text string from a cited database as a final text predicted based on the input image).
Regarding claim 9, Soldevilla teaches at least in para. 0058 a computer readable non-transitory storage medium storing instructions that when executed by one or more computer processors cause the one or more computer processors to perform steps comprising:
receiving an input image displaying an input text comprising one or more input characters (received image of further para. 0040, 0052-0055 and Figs. 1 and 3 as said an input image displaying an input text 14 comprising one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (performed set of transformations of at least para. 0043 and 0054 on the input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least Fig. 3 and para. 0054 sets of set of candidate text predictions by performing text recognition on each pre-processed or transformed image of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions (determining further in at least Fig. 3 and para. 0054 determining representative text strings or prediction for the set of candidate text predictions);
for each candidate text prediction from the set of candidate text predictions, determining edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0054, 0150, and 0180 determined edits that transform the representative text prediction to the candidate text prediction for each of the said candidate text prediction from the set of candidate text predictions);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 for determining a regular expression in the form of a wildcard character expression based on the representative text prediction and the set of edits operations that transform the representative text prediction to the candidate text prediction); and
using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further adapted for using the regular expression of at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 to identify a text string from a cited database as a final text predicted based on the input image).
Regarding claim 16, Soldevilla teaches at least in para. 0058 a computer-implemented system comprising:
one or more computer processors (para. 0058); and
a computer readable non-transitory storage medium (para. 0058) storing instructions that when executed by the one or more computer processors cause the one or more computer processors to perform steps comprising:
receiving an input image displaying an input text comprising one or more input characters (received image of further para. 0040, 0052-0055 and Figs. 1 and 3 as said an input image displaying an input text 14 comprising one or more input characters);
performing a set of transformations on the input image to obtain a set of transformed images (performed set of transformations of at least para. 0043 and 0054 on the input image to obtain a set of transformed images);
determining a set of candidate text predictions by performing text recognition on each transformed image of the set of transformed images (determining further in at least Fig. 3 and para. 0054 sets of set of candidate text predictions by performing text recognition on each pre-processed or transformed image of the set of transformed images);
determining a representative text prediction for the set of candidate text predictions (determining further in at least Fig. 3 and para. 0054 determining representative text strings or prediction for the set of candidate text predictions);
for each candidate text prediction from the set of candidate text predictions, determining edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0054, 0150, and 0180 determined edits that transform the representative text prediction to the candidate text prediction for each of the said candidate text prediction from the set of candidate text predictions);
determining a regular expression based on the representative text prediction and a set of edits that transform the representative text prediction to the candidate text prediction (the system may further in at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 for determining a regular expression in the form of a wildcard character expression based on the representative text prediction and the set of edits operations that transform the representative text prediction to the candidate text prediction); and
using the regular expression to identify a text string from a database as a final text predicted based on the input image (the system further adapted for using the regular expression of at least para. 0008-0013 further supported by at least para. 0150, and 0180 and Fig. 3 to identify a text string from a cited database as a final text predicted based on the input image).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARCELLUS AUGUSTIN whose telephone number is (571)270-3384. The examiner can normally be reached 9 AM- 5 PM.
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, BENNY TIEU can be reached at 571-272-7490. 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.
/MARCELLUS J AUGUSTIN/
Primary Examiner, Art Unit 2682 10/28/2025