# US 10,455,117 B2 · Image processing apparatus, 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 10,455,117 B2 - Document ID: US10455117B2 - Status: Granted - Kind: B2 - Application number: 15/719,311 - Filed: 2017-09-28 - Published: 2018-01-18 - Granted: 2019-10-22 - Earliest claimed: 2013-12-19 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Reiji Misawa; Koya Shimamura - Web page: https://patentgrep.com/patent/US10455117B2 ## CPC - H04N 1/403: Discrimination between the two tones in the picture signal of a two-tone original - G06T 5/30: Erosion or dilatation, e.g. thinning - G06T 7/13: Edge detection - G06T 7/136: involving thresholding - G06V 30/15: {Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques} - G06V 30/168: Smoothing or thinning of the pattern; Skeletonisation - H04N 1/40062: {Discrimination between different image types, e.g. two-tone, continuous tone} - H04N 1/405: Halftoning, i.e. converting the picture signal of a continuous-tone original into a corresponding signal showing only two levels - H04N 1/642: {Adapting to different types of images, e.g. characters, graphs, black and white image portions} - H04N 1/648: {Transmitting or storing the primary (additive or subtractive) colour signals; Compression thereof (H04N1/642 - H04N1/646 take precedence)} - G06T 2207/10008: from scanner, fax or copier - G06T 2207/30176: Document - G06V 30/10: Character recognition - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of the region identified based on the character segmentation rectangle information is acquired. Whether each character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not is determined based on a result of a logical AND of the thinned image and the edge detected image. ## Claims ### Claim 1 An image processing method comprising: analyzing an image; based on the analysis, determining an attribute of a region within the image from among at least a character attribute and an image attribute; further analyzing the region whose attribute has been determined to be the character attribute; if a result of the further analysis indicates that the region whose attribute has been determined to be the character attribute is a first type of a character region, performing a binary compression processing on the region; if the result of the further analysis indicates that the region whose attribute has been determined to be the character attribute is a second type of a character region, performing a multivalued compression processing on the region; and generating a file for the image based on at least image data of the region whose attribute has been determined to be the character attribute and which has been subject to either one of the binary compression processing and the multivalued compression processing. ### Claim 2 (depends on 1) The image processing method according to claim 1, wherein the binary compression processing is not performed on the region whose attribute has been determined to be the character attribute, if the result of the further analysis indicates that the region whose attribute has been determined to be the character attribute is the second type of a character region. ### Claim 3 (depends on 1) The image processing method according to claim 1, wherein the first type of character region is a region where a character is not present within the region whose attribute has been determined to be the character attribute, and the second type of character region is a region where a character is present within the region whose attribute has been determined to be the character attribute. ### Claim 4 (depends on 1) The image processing method according to claim 1, further comprising: performing a character recognition processing on the region whose attribute has been determined to be the character attribute, wherein the generating generates the file for the image including a character code obtained by the character recognition processing. ### Claim 5 (depends on 1) The image processing method according to claim 1, further comprising: performing the multivalued compression processing on a region whose attribute has been determined to be the image attribute, wherein the generating generates the file for the image, based on at least image data of the region whose attribute has been determined to be the character attribute and which has been subject to either one of the binary compression processing and the multivalued compression processing and image data of the region whose attribute has been determined to be the image attribute and which has been subject to the multivalued compression processing. ### Claim 6 (depends on 1) The image processing method according to claim 1, further comprising reading a paper document to obtain the image. ### Claim 7 An image processing method comprising: analyzing an image; based on the analysis, determining an attribute of a region within the image from among at least a character attribute and an image attribute; performing edge pixel counting in the region whose attribute has been determined to be the character attribute; based on a result of the edge pixel counting, determining whether or not to perform a binary compression processing on the region whose attribute has been determined to be the character attribute; performing a character recognition processing on the region whose attribute has been determined to be the character attribute; and generating a file for the image, based on at least image data of the region whose attribute has been determined to be the character attribute and which has not been subject to the binary compression processing according to the determination and character code obtained by the character recognition processing. ### Claim 8 A printing apparatus comprising: a reading unit that reads a paper document to obtain an image of the paper document; a first analyzing unit that analyzes the image; a determining unit that determines, based on the analysis, an attribute of a region within the image from among at least a character attribute and an image attribute; a second analyzing unit that analyzes the region whose attribute has been determined to be the character attribute; a binary compression unit that performs a binary compression processing; a multivalued compression unit that performs a multivalued compression processing; a generating unit that generates an electronic file for the paper document, based on at least image data of the region whose attribute has been determined to be the character attribute and which has been subject to either one of the binary compression processing and the multivalued compression processing, wherein the image data is obtained by the binary compression processing if a result of the analysis by the second analyzing unit indicates that the region whose attribute has been determined to be the character attribute is a first type of a character region, and the image data is obtained by the multivalued compression processing if the result of the analysis by the second analyzing unit indicates that the region whose attribute has been determined to be the character attribute is a second type of a character region, and an output unit that outputs the generated electronic file to a destination. ### Claim 9 (depends on 7) The image processing method according to claim 7, wherein the binary compression processing is not performed on the region whose attribute has been determined to be the character attribute, if the result of the further analysis indicates that the region whose attribute has been determined to be the character attribute is a predetermined type of a character region, the predetermined type of the character region being a region where a character is present within the region whose attribute has been determined to be the character attribute. ### Claim 10 (depends on 7) The image processing method according to claim 7, further comprising: performing the multivalued compression processing on a region whose attribute has been determined to be the image attribute, wherein the generating generates the file for the image, based on image data of the region whose attribute has been determined to be the character attribute and which has been not subject to the binary compression processing according to the determination, image data of the region whose attribute has been determined to be the image attribute and which has been subject to the multivalued compression processing, and the character code obtained by the character recognition processing. ### Claim 11 (depends on 7) The image processing method according to claim 7, further comprising reading a paper document to obtain the image. ### Claim 12 An image processing apparatus comprising: a first analyzing unit that analyzes an image; a first determining unit that determines, based on the analysis, an attribute of a region within the image from among at least a character attribute and an image attribute; a second analyzing unit that performs edge pixel counting in the region whose attribute has been determined to be the character attribute; a second determining unit that determines, based on a result of the edge pixel counting, whether or not to perform a binary compression processing on the region whose attribute has been determined to be the character attribute; a character recognition unit that performs a character recognition processing on the region whose attribute has been determined to be the character attribute; and a generating unit that generates a file for the image, based on at least image data of the region whose attribute has been determined to be the character attribute and which has not been subject to the binary compression processing according to the determination and character code obtained by the character recognition unit. ### Claim 13 (depends on 12) The image processing apparatus according to claim 12, wherein the binary compression processing is not performed on the region whose attribute has been determined to be the character attribute, if the result of the further analysis indicates that the region whose attribute has been determined to be the character attribute is a predetermined type of a character region, the predetermined type of the character region being a region where a character is present within the region whose attribute has been determined to be the character attribute. ### Claim 14 (depends on 12) The image processing apparatus according to claim 12, further comprising: a compression unit that performs the multivalued compression processing on a region whose attribute has been determined to be the image attribute, wherein the generating unit generates the file for the image, based on image data of the region whose attribute has been determined to be the character attribute and which has been not subject to the binary compression processing according to the second determination unit, image data of the region whose attribute has been determined to be the image attribute and which has been subject to the multivalued compression processing, and the character code obtained by the character recognition unit. ### Claim 15 (depends on 12) The image processing apparatus according to claim 12, further comprising a reading unit that reads a paper document to obtain the image.