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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/26/2024 have been entered and considered. Initialed copy/copies of the PTO-1449 by the Examiner is/are attached.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
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. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that use the word “means” or “step” but are nonetheless not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph because the claim limitation(s) recite(s) sufficient structure, materials, or acts to entirely perform the recited function.
Such claim limitation(s) is/are:
(i) “backbone network….” have a neural network structure associated with it.
Because this/these claim limitation(s) is/are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are not being interpreted to cover only the corresponding structure, material, or acts described in the specification as performing the claimed function, and equivalents thereof.
If applicant intends to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to remove the structure, materials, or acts that performs the claimed function; or (2) present a sufficient showing that the claim limitation(s) does/do not recite sufficient structure, materials, or acts to perform the claimed function.
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.
Claims 1, 3, 6-7, 9-10, 13, 17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Weihong et al (English Translation of CN 111507351) in view of Tiantian et al (English Translation of CN 112784830 A).
Regarding independent claim 1, Weihong teaches a method for recognizing an ancient book (method for digitalizing an ancient book document – see abstract), comprising: obtaining a target ancient book image to be recognized (collecting image data of ancient book documents – see page 5, s1, [p][006]), and extracting classification features of the target ancient book image (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) according to a backbone network to obtain backbone classification features (universal target detection frame YOLO-v3 - see page 5, s2, [p][006]); detecting the backbone classification features (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) and determining individual character positions (carrying out single character marking - see page 5, s2, [p][006]) and text line positions included in the target ancient book image (text line marking on the image data at the space level - see page 5, s2, [p][006]); recognizing the individual character positions to obtain content information of individual characters (single character in step S1 includes the position of the single character – see page 6, [p][003]), obtain a reading order of characters in the text line positions (specifically including text line-level labeling and single character-level labeling according to a reading sequence – see page 7, [p][002]); and arranging, according to a ratio between the individual character positions and the text line positions, following the reading order of the characters in the text line positions the content information of the individual characters to obtain a recognition result of characters in the target ancient book image ([e]xtracting a layout straight line: the image processing method is combined with the projection method to detect the straight line position in the document, the parts of different region blocks of the ancient book document content are extracted, and finally the position relation of each region block is obtained, and the obtained effect graph is shown in figure 5 – see page 8, [p][002]).
Weihong does not explicitly teach predicting the text line positions However, Lianjie explicitly teach predicting the text line positions (a predicted value obtaining unit, configured to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed – see page 2, [p][011]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Lianjie predicting the text line positions.
Wherein having Weihong predicting the text line positions.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model to process each pixel point in the image to be processed to obtain a predicted value of each pixel point since both Weihong and Lianjie to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Lianjie to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Lianjie et al (English Translation of CN 112784830 A), see page 2, [p][011]).
Regarding claim 3, Weihong in view of Lianjie teaches the method according to claim 1, Weihong explicitly teaches wherein recognizing the individual character positions to obtain content information of individual characters comprises: obtaining, by image cropping, individual character image areas corresponding to the individual character positions from the target ancient book image (s1 acquiring data: collecting image data of ancient book documents, and carrying out single character marking – see page 5, [p][007]); and recognizing the individual characters in the individual character image areas through a neural network classifier to obtain the content information corresponding to the individual characters (classifying the single character classification model: in the step S1, the single character labeling obtains a picture of a single character, a convolutional neural network is used for constructing a single character classification model - see page 5, [p][007]).
Regarding claim 7, Weihong in view of Lianjie teaches the method according to claim 1, Weihong explicitly teaches, further comprising: receiving a correction operation for the content information of the individual characters to obtain corrected content information corresponding to the individual characters (step S3, the straight lines on the ancient book document are extracted according to the morphological dilation-erosion method in combination with the projection method, so as to obtain the position relationship between the blocks – see page 6, [p][005]).
Regarding independent claim 9, Weihong teaches a device (system for digitalizing an ancient book document – see abstract), comprising: one or more programs (an algorithm shown by pseudo codes – see page 8, [p][003]) comprising instructions (an algorithm shown by pseudo codes – see page 8, [p][003]) which, when executed by the processor, cause the device to perform a method comprising: obtaining a target ancient book image to be recognized (collecting image data of ancient book documents – see page 5, s1, [p][006]), and extracting classification features of the target ancient book image (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) according to a backbone network to obtain backbone classification features (universal target detection frame YOLO-v3 - see page 5, s2, [p][006]); detecting the backbone classification features (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) and determining individual character positions (carrying out single character marking - see page 5, s2, [p][006]) and text line positions included in the target ancient book image (text line marking on the image data at the space level - see page 5, s2, [p][006]); recognizing the individual character positions to obtain content information of individual characters (single character in step S1 includes the position of the single character – see page 6, [p][003]), obtain a reading order of characters in the text line positions (specifically including text line-level labeling and single character-level labeling according to a reading sequence – see page 7, [p][002]); and arranging, according to a ratio between the individual character positions and the text line positions, following the reading order of the characters in the text line positions the content information of the individual characters to obtain a recognition result of characters in the target ancient book image ([e]xtracting a layout straight line: the image processing method is combined with the projection method to detect the straight line position in the document, the parts of different region blocks of the ancient book document content are extracted, and finally the position relation of each region block is obtained, and the obtained effect graph is shown in figure 5 – see page 8, [p][002]).
Weihong does not explicitly teach a processor, a memory wherein the memory stores and predicting the text line positions However, Lianjie explicitly teach a processor (see page 7, [p][001]), a memory (see page 7, [p][001]) wherein the memory stores (see page 7, [p][001]) and predicting the text line positions (a predicted value obtaining unit, configured to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed – see page 2, [p][011]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Lianjie predicting the text line positions.
Wherein having Weihong predicting the text line positions.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model to process each pixel point in the image to be processed to obtain a predicted value of each pixel point since both Weihong and Lianjie to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Lianjie to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Lianjie et al (English Translation of CN 112784830 A), see page 2, [p][011]).
Regarding independent claim 10, Weihong teaches, when executed by a device (system for digitalizing an ancient book document – see abstract), cause the device to perform a method comprising: obtaining a target ancient book image to be recognized (collecting image data of ancient book documents – see page 5, s1, [p][006]), and extracting classification features of the target ancient book image (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) according to a backbone network to obtain backbone classification features (universal target detection frame YOLO-v3 - see page 5, s2, [p][006]); detecting the backbone classification features (carrying out single character marking and text line marking on the image data at the space level - see page 5, s2, [p][006]) and determining individual character positions (carrying out single character marking - see page 5, s2, [p][006]) and text line positions included in the target ancient book image (text line marking on the image data at the space level - see page 5, s2, [p][006]); recognizing the individual character positions to obtain content information of individual characters (single character in step S1 includes the position of the single character – see page 6, [p][003]), obtain a reading order of characters in the text line positions (specifically including text line-level labeling and single character-level labeling according to a reading sequence – see page 7, [p][002]); and arranging, according to a ratio between the individual character positions and the text line positions, following the reading order of the characters in the text line positions the content information of the individual characters to obtain a recognition result of characters in the target ancient book image ([e]xtracting a layout straight line: the image processing method is combined with the projection method to detect the straight line position in the document, the parts of different region blocks of the ancient book document content are extracted, and finally the position relation of each region block is obtained, and the obtained effect graph is shown in figure 5 – see page 8, [p][002]).
Weihong does not explicitly teach a non-transitory computer-readable storage medium storing instructions which and predicting the text line positions. However, Lianjie explicitly teach a non-transitory computer-readable storage (see page 7, [p][001]) medium storing instructions (see page 7, [p][001]) which and predicting the text line positions (a predicted value obtaining unit, configured to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed – see page 2, [p][011]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Lianjie predicting the text line positions.
Wherein having Weihong predicting the text line positions.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model to process each pixel point in the image to be processed to obtain a predicted value of each pixel point since both Weihong and Lianjie to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Lianjie to process each pixel point in the image to be processed to obtain a predicted value of each pixel point, where the predicted value of the pixel point is used to indicate a relationship between the pixel point and a character in the image to be processed (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Lianjie et al (English Translation of CN 112784830 A), see page 2, [p][011]).
Regarding claim 13, which corresponds to claim 3 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 3 is
fully applicable to claim 13.
Regarding claim 17, which corresponds to claim 7 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 7 is
fully applicable to claim 17.
Regarding claim 19, which corresponds to claim 4 except for reciting a different
statutory category of non-transitory computer readable storage medium. Therefore, the
rejection analysis of claim 4 is fully applicable to claim 19.
Claims 2, 10 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Weihong et al (English Translation of CN 111507351) in view of Lianjie et al (English Translation of CN 112784830 A) as applied to claims 1 and 10 further in view of Yong et al (English Translation of CN 112990204) further in view of Ding et al (English Translation of CN 101710418) further in view of Zhijun et al (English Translation of CN112016546A).
Regarding claim 2, Weihong in view of Lianjie teaches the method according to claim 1, Weihong explicitly teaches wherein detecting the backbone classification features and determining individual character positions included in the target ancient book image comprises: inputting the backbone classification features into a convolution layer to obtain an individual character (a convolutional neural network is used for constructing a single character classification model – see page 3, [p][001]).
Weihong in view of Lianjie does not explicitly teach an individual character probability feature map and a background threshold feature map; determining, for each pixel in the target ancient book image, a probability that the pixel belongs to an individual character and a probability that the pixel belongs to a background according to the individual character probability feature map and the background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background
However, Xiang explicitly teaches an individual character probability feature map (first detection module to obtain a probability map of the contracted text region and a threshold map of the text region - see page 7, [p][011]); and determining, for each pixel in the target ancient book image, a probability that the pixel belongs to an individual character and a probability that the pixel belongs to a background according to the individual character probability feature map (S103, inputting the characteristic image into a second detection module to obtain a score map for representing the probability whether the pixel belongs to the text region or not and a regression prediction map for representing the coordinates of the text region required by regression processing – see page 8, [p][002])
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong as modified by Lianjie of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Yong an individual character probability feature map and a background threshold feature map; determining, for each pixel in the target ancient book image, a probability that the pixel belongs to an individual character and a probability that the pixel belongs to a background according to the individual character probability feature map and the background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background
Wherein having Weihong an individual character probability feature map and a background threshold feature map; determining, for each pixel in the target ancient book image, a probability that the pixel belongs to an individual character and a probability that the pixel belongs to a background according to the individual character probability feature map and the background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background
The motivation behind the modification would have been obtain a single character output result to obtain a score map for representing the probability of whether the pixel belongs to the text region or not and a regression prediction map for representing the coordinates of the text region required by regression processing; since both Weihong and Yong to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Yong obtains a score map for representing the probability of whether the pixel belongs to the text region or not and a regression prediction map for representing the coordinates of the text region required by regression processing (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Yong et al (English Translation of CN 112990204), see Abstract).
Weihong in view of Lianjie and Xiang does not explicitly teach a background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background.
However, Ding explicitly teaches a background threshold feature map (constructing a foreground information and background information probability model by using the image prior information and calculating the foreground probability of each pixel by using the probability model – see Abstract); and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background (constructing a foreground information and background information probability model by using the image prior information and calculating the foreground probability of each pixel by using the probability model – see Abstract).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong as modified by Lianjie, and Yong of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Ding a background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background
Wherein having Weihong a background threshold feature map; and determining, according to the probability that the pixel belongs to the individual character and the probability that the pixel belongs to the background the individual character and the probability that the pixel belongs to the background.
The motivation behind the modification would have been obtain a single character output result using an interactive mode image partitioning method based on a geodesic distance since both Weihong and Ding to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Ding to implement an interactive mode image partitioning method based on a geodesic distance (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Ding et al (English Translation of CN 101710418), see Abstract).
Weihong in view of Lianjie, Ding and Yong does not explicitly teach a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character.
Zhijun explicitly teaches a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character (determining the minimum circumscribed rectangle of each text connected domain – see page 6, line 5).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong in view of Lianjie, Ding and Yong of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Zhijun a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character.
Wherein having Weihong a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model to improve the accuracy of positioning the text region since both Weihong, Lianjie and Yong to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Zhijun improves the accuracy of positioning the text region (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Zhijun et al (English Translation of CN112016546A), see Abstract).
Regarding claim 10, which corresponds to claim 2 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 2 is
fully applicable to claim 10.
Regarding claim 18, which corresponds to claim 2 except for reciting a different
statutory category of non-transitory computer readable storage medium. Therefore, the
rejection analysis of claim 2 is fully applicable to claim 18.
Claims 4, 14 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Weihong et al (English Translation of CN 111507351) in view of Lianjie et al (English Translation of CN 112784830 A) as applied to claims 1 and 10 further in view of Tiantian et al (English Translation of CN113313064A)
Regarding claim 4, Weihong in view of Lianjie teaches the method according to claim 1, wherein predicting the text line positions to obtain a reading order of characters in the text line positions comprises: Weihong in view of Lianjie teach does not explicitly teach predicting the text line positions to obtain corresponding character area mask images; and predicting the reading order of the characters in text areas in the text line positions according to the character area mask images.
However, Tiantian explicitly teaches predicting the text line positions to obtain corresponding character area mask images (acquiring a character mask image and a text line mask image corresponding to the text image to be recognized – see page 16, 1st full para); and predicting the reading order of the characters in text areas in the text line positions according to the character area mask images (the character recognition efficiency can be effectively improved by taking the identification result of the undetermined character as a prediction basis through the preset non-autoregressive model, and the accuracy of the character recognition result can be improved by effectively combining context semantic information – see page 8, [p][005]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong in view of Lianjie, Ding and Xiang of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Zhijun a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character.
Wherein having Weihong a minimum bounding rectangle of each individual character by obtaining a connected domain, as an individual character position corresponding to each individual character.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model to improve the accuracy of positioning the text region since both Weihong, Lianjie and Xiang to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Tiantian for predicting the text line positions to obtain corresponding character area mask images; and predicting the reading order of the characters in text areas in the text line positions according to the character area mask images (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Zhijun et al (English Translation of CN112016546A), see Abstract).
Regarding claim 14, which corresponds to claim 4 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 4 is
fully applicable to claim 14.
Regarding claim 20, which corresponds to claim 4 except for reciting a different
statutory category of non-transitory computer readable storage medium. Therefore, the
rejection analysis of claim 4 is fully applicable to claim 20.
Claims 5, 15 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Weihong et al (English Translation of CN 111507351) in view of Lianjie et al (English Translation of CN 112784830 A) as applied to claims 1 and 10 further in view of Xiang et al (English Translation of CN106156711B) in view of Seeger et al (Pub No.: US20030185448).
Regarding claim 5, Weihong in view of Lianjie teaches the method according to claim 1, wherein predicting the text line positions to obtain a reading order of characters in the text line positions comprises: Weihong in view of Lianjie does not explicitly teach dividing the text line positions into squares having a preset size.
Xiang explicitly teaches dividing the text line positions into squares having a preset size (a 3 x 3 square region may be constructed with the pixel at the center of the square region – see page 4, 1st full para).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong in view of Lianjie of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Xiang dividing the text line positions into squares having a preset size.
Wherein having Weihong dividing the text line positions into squares having a preset size.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model for determining the position of text line since both Weihong and Xiang are directed to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Xaing for determining the position of text line (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Xiang et al (English Translation of CN106156711B), see Abstract).
Weihong in view of Lianjie and Xaing does not explicitly teach sequentially connecting midpoints of the squares to obtain the reading order of the characters in text areas in the text line positions.
Seeger explicitly teaches sequentially connecting midpoints of the squares to obtain the reading order of the characters in text areas in the text line positions (see [p][0053-0054]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong in view of Lianjie and Seeger of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Seeger sequentially connecting midpoints of the squares to obtain the reading order of the characters in text areas in the text line positions
Wherein having Seeger sequentially connecting midpoints of the squares to obtain the reading order of the characters in text areas in the text line positions.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model for selecting a text region in an image since both Weihong and Seeger are directed to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Seeger for selecting a text region from an image (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Seeger et al (Pub No.: US20030185448) , see Abstract).
Regarding claim 15, which corresponds to claim 5 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 5 is
fully applicable to claim 15.
Regarding claim 21, which corresponds to claim 5 except for reciting a different
statutory category of non-transitory computer readable storage medium. Therefore, the
rejection analysis of claim 5 is fully applicable to claim 21.
Claims 6, 16 and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Weihong et al (English Translation of CN 111507351) in view of Lianjie et al (English Translation of CN 112784830 A) as applied to claims 1 and 10 further in view of Yang et al (English Translation of CN 113158808 A).
Regarding claim 6, Weihong in view of Lianjie teaches the method according to claim 1, Weihong explicitly teaches wherein arranging, according to a ratio between the individual character positions and the text line positions (e]xtracting a layout straight line: the image processing method is combined with the projection method to detect the straight line position in the document, the parts of different region blocks of the ancient book document content are extracted, and finally the position relation of each region block is obtained, and the obtained effect graph is shown in figure 5 – see page 8, [p][002]), the content information of the individual characters following the reading order of the characters in the text line positions to obtain a recognition result of characters in the target ancient book image (convert the location of a text line in the image to be processed into the location of the character, and aim at the image to be processed which the text line location is difficult to be performed such as a curved text, an irregular text and the like, the character positioning is carried out, and the character recognition difficulty is reduced – see page 2, [p][010]) comprises: Weihong in view of Lianjie does not explicitly teach calculating an area of intersection of the individual character positions and the text line positions, and a ratio between the area of intersection and the individual character positions; and arranging, when the ratio satisfies a preset condition, the content information of the individual characters in the individual character positions according to the reading order of the characters in the text line positions, to obtain the recognition result of the characters in the target ancient book image.
Yang explicitly teaches calculating an area of intersection of the individual character positions and the text line positions, and a ratio between the area of intersection and the individual character positions (grouping the characters with the vertical direction spacing smaller than t times of the average width of the characters into a group, counting the intersection ratio IoU of the adjacent characters in the character group – see page 7, last para); and arranging, when the ratio satisfies a preset condition (s3b, constructing an adjacent area by using the upper and lower boundaries of adjacent characters in the character vertical array, and if the adjacent area meets threshold conditions of height, gray average value and intersection ratio, classifying the adjacent area into a candidate area – see page 9, [p][002]), the content information of the individual characters in the individual character positions according to the reading order of the characters in the text line positions ((4) In the ancient Chinese book character segmentation method, the prediction bounding boxes of all characters are subjected to segmentation clustering and reading sequence recovery according to the reading sequence of the ancient books and the semantic sentence groups of the characters to obtain the ancient book text content without punctuation marks – see page 11, step 4), to obtain the recognition result of the characters in the target ancient book image (obtain the text recognition result which has accurate character recognition and clear sentence reading and conforms to the reconstruction of the layout of the modern reading system – see page 6, [p][006]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Weihong in view of Lianjie of a method for recognizing an ancient book, comprising: obtaining a target ancient book image to be recognized of Yang calculating an area of intersection of the individual character positions and the text line positions, and a ratio between the area of intersection and the individual character positions; and arranging, when the ratio satisfies a preset condition, the content information of the individual characters in the individual character positions according to the reading order of the characters in the text line positions, to obtain the recognition result of the characters in the target ancient book image
Wherein having Weihong calculating an area of intersection of the individual character positions and the text line positions, and a ratio between the area of intersection and the individual character positions; and arranging, when the ratio satisfies a preset condition, the content information of the individual characters in the individual character positions according to the reading order of the characters in the text line positions, to obtain the recognition result of the characters in the target ancient book images.
The motivation behind the modification would have been obtain a single character output result by simultaneously training a single character classification model for identifying some unusual special characters in ancient books very accurately, and overcomes the problems of misjudgment, omission and the like in ancient book document identification since both Weihong and Yang are directed to character recognition, wherein Weihong to obtain a single character output result by simultaneously training a single character classification model, outputting a classification result to the detected single character, and finally obtaining a document identification result by combining the detection and identification results of the single character while Yang for identifying some unusual special characters in ancient books very accurately, and overcomes the problems of misjudgment, omission and the like in ancient book document identification (Please see Weihong et al (English Translation of CN 111507351), see Abstract and Yang et al (English Translation of CN 113158808 A) , see Abstract).
Regarding claim 16, which corresponds to claim 6 except for reciting a different
statutory category of a device. Therefore, the rejection analysis of claim 6 is
fully applicable to claim 16.
Regarding claim 22, which corresponds to claim 6 except for reciting a different
statutory category of non-transitory computer readable storage medium. Therefore, the
rejection analysis of claim 6 is fully applicable to claim 22.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu et al (Pub No.: 20190138860) discloses a training system has a non-transitory computer-readable storage medium that stores instructions executable by a processor to generate a set of text images based on selecting one or more glyphs, selecting a digital font for each glyph, and rendering each glyph written in the selected digital font. The processor generates a font recognition neural network configured to classify digital fonts. The processor trains the font recognition neural network to learn discriminative features that effectively differentiate digital fonts by using adversarial training based on the set of text images.
TORRES et al (Pub No.: 20210073532) discloses a document extraction system executed by a processor, may process documents using manual and automated systems. The document extraction system may efficiently route tasks to the manual and automated systems based on a predicted probability that the results generated by the automated system meet some baseline level of accuracy. To increase document processing speed, documents having a high likelihood of accurate automated processing may be routed to an automated system. To ensure a baseline level of accuracy, documents having a smaller likelihood of accurate automated processing may be routed to a manual system.
Azulai et al (Pub No.: 20230245481) discloses a method, computer system, and a computer program product for text detection is provided. The present invention may include training a text detection model. The present invention may include performing text detection on an inputted image using the trained text detection model. The present invention may include determining whether at least one of a plurality of bounding boxes generated using the inputted image has an aspect ratio above a threshold. The present invention may include based upon determining that at least one of the plurality of bounding boxes generated using the inputted image has the aspect ratio above the threshold, upscaling any text within the at least one bounding box and performing text detection on a new image using the trained text detection model. The present invention may include outputting an output image.
Kao et al (Pub No.: 20180150956) discloses a character recognition method is provided, including the steps of: recognizing a character string, which includes one or more characters, in a region of interest (ROI) using a first convolutional neural network (CNN) model to generate a recognized character string; and comparing the recognized character string with a plurality of character strings in a character database to find a character string corresponding to the recognized character string, wherein each of the character strings includes one or more characters; wherein if the character string corresponding to the recognized character string is found, the recognized character string is used as a character recognition result, otherwise, using a second CNN model to correct the recognized string and generate a new recognized character string as the character recognition result.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDRAE S ALLISON whose telephone number is (571)270-1052. The examiner can normally be reached on Monday-Friday 9am-5pm EST.
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, Chineyere Wills-Burns, can be reached on (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANDRAE S ALLISON/Primary Examiner, Art Unit 2673
July 8, 2026
Prosecution Insights