# US 11,908,215 B2 · Information processing apparatus, information processing method, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,215 B2 - Document ID: US11908215B2 - Status: Granted - Kind: B2 - Application number: 17/540,888 - Filed: 2021-12-02 - Published: 2022-06-16 - Granted: 2024-02-20 - Earliest claimed: 2020-12-11 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Yuki Narumi - Web page: https://patentgrep.com/patent/US11908215B2 ## CPC - G06V 30/22: characterised by the type of writing - G06T 7/11: Region-based segmentation - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 30/153: {using recognition of characters or words} - G06V 30/1801: {Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections (extracting features by contour coding G06V30/182)} - G06V 30/222: of characters separated by spaces - G06V 30/32: Digital ink - G06T 2207/30176: Document - G06V 30/1908: {Region based matching} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An object is to improve character recognition accuracy of handwritten characters, originally a single continuous character string, described discontinuously. An image area corresponding to a handwritten character is separated from a document image obtained by scanning a document and a character block including characters having the same baseline is extracted. Then, in a case where a plurality of character blocks is extracted from the first image area, a single character block is generated by combining character blocks based on a position relationship of the plurality of character blocks. ## Claims ### Claim 1 An information processing apparatus comprising: one or more memories that store a program; and one or more processors that execute the program to automatically perform: separating a first image area including handwritten characters from a document image obtained by scanning a document; extracting one or more character blocks each of which consists of some of the handwritten characters in proximity to one another and having a common baseline from the separated first image area; generating, in a case where a plurality of character blocks is extracted from the first image area in the extracting, a combined single character block by combining character blocks based on a position relationship of the plurality of character blocks; and performing optical character recognition processing for the generated combined single character block to obtain a character recognition result of the generated combined single character block. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein in the generating: the plurality of extracted character blocks is grouped; a character block forming a main character row of character blocks configuring a group is determined to be a first character block; and in a case where a second character block other than the first character block, which is a character block configuring the group, satisfies a predetermined condition, the combined single character block is generated by combining the second character block with the first character block. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein in the separating, a second image area representing a state of the document before the handwritten character is entered is further separated from the document image and the grouping is processing to group the plurality of extracted character blocks into groups for each blank area corresponding to an entry field for handwriting relating to a specific item in the second image area. ### Claim 4 (depends on 3) The information processing apparatus according to claim 3, wherein the character block forming the main character row is a character block located at a starting position from which a character is written in the blank area or a character block whose block length or block size is the largest. ### Claim 5 (depends on 4) The information processing apparatus according to claim 4, wherein the predetermined condition includes that the second character block exists at a line change position of the first character block. ### Claim 6 (depends on 5) The information processing apparatus according to claim 5, wherein the predetermined condition further includes that in a case where the second character block is combined with the first character block, a character block after combination exceeds the blank area. ### Claim 7 (depends on 5) The information processing apparatus according to claim 5, wherein the predetermined condition further includes at least that a ratio of a character size of the second character block to a character size of the first character block is within a predetermined range. ### Claim 8 (depends on 2) The information processing apparatus according to claim 2, wherein the predetermined condition includes that the second character block is continuous in an extension direction of the first character block and a baseline of the second character block is shifted from a baseline of the first character block. ### Claim 9 (depends on 8) The information processing apparatus according to claim 8, wherein the predetermined condition further includes that a black pixel area in the first image area exists in the extension direction of the first character block. ### Claim 10 (depends on 8) The information processing apparatus according to claim 8, wherein the predetermined condition further includes at least that a ratio of a character size of the second character block to a character size of the first character block is within a predetermined range. ### Claim 11 (depends on 1) The information processing apparatus according to claim 1, wherein in the generating: the plurality of extracted character blocks is grouped; a character block forming a main character row of character blocks configuring a group is determined to be a first character block; and in a case where a second character block and a third character block other than the first character block, which are character blocks configuring the group, satisfy a predetermined condition, the combined single character block is generated by combining the second character block and the third character block with the first character block. ### Claim 12 (depends on 11) The information processing apparatus according to claim 11, wherein in the separating, a second image area representing a state of the document before the handwritten character is entered is further separated from the document image and the grouping is processing to group the plurality of extracted character blocks into groups for each blank area corresponding to an entry field for handwriting relating to a specific item in the second image area. ### Claim 13 (depends on 11) The information processing apparatus according to claim 11, wherein the predetermined condition includes that the second and the third character blocks exist in an extension direction of the first character block. ### Claim 14 (depends on 13) The information processing apparatus according to claim 13, wherein, the predetermined condition further includes that the third character block exists at a line change position of the second character block. ### Claim 15 (depends on 13) The information processing apparatus according to claim 13, wherein the predetermined condition further includes that in a case where the third character block is combined with the second character block, a character block after combination exceeds the blank area. ### Claim 16 (depends on 13) The information processing apparatus according to claim 13, wherein the predetermined condition further includes at least that a ratio of a character size of the second character block to a character size of the first character block is within a predetermined range. ### Claim 17 A control method of an information processing apparatus, the control method comprising: separating a first image area including handwritten characters from a document image obtained by scanning a document; extracting one or more character blocks each of which consists of some of the handwritten characters in proximity to one another and having a common baseline from the separated first image area; generating, in a case where a plurality of character blocks is extracted from the first image area in the extracting, a combined single character block by combining character blocks based on a position relationship of the plurality of character blocks; and performing optical character recognition processing for the generated combined single character block to obtain a character recognition result of the generated combined single character block. ### Claim 18 A non-transitory computer readable storage medium storing a program for causing a computer to perform a control method of an information processing apparatus, the control method comprising: separating a first image area including handwritten characters from a document image obtained by scanning a document; extracting one or more character blocks each of which consists of some of the handwritten characters in proximity to one another and having a common baseline from the separated first image area; generating, in a case where a plurality of character blocks is extracted from the first image area in the extracting, a combined single character block by combining character blocks based on a position relationship of the plurality of character blocks; and performing optical character recognition processing for the generated combined single character block to obtain a character recognition result of the generated combined single character block.