# US 10,121,252 B2 · Image processing apparatus and image processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,252 B2 - Document ID: US10121252B2 - Status: Granted - Kind: B2 - Application number: 15/343,319 - Filed: 2016-11-04 - Published: 2017-02-23 - Granted: 2018-11-06 - Earliest claimed: 2014-08-20 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Masahiro Ariizumi; Noriyasu Hashiguchi - Web page: https://patentgrep.com/patent/US10121252B2 ## CPC - G06T 7/11: Region-based segmentation - G06F 18/23213: with fixed number of clusters, e.g. K-means clustering - G06T 1/60: Memory management - G06T 7/174: involving the use of two or more images - G06T 7/187: involving region growing; involving region merging; involving connected component labelling - G06T 7/40: Analysis of texture (depth or shape recovery from texture G06T7/529) - G06T 7/90: Determination of colour characteristics - G06T 2207/10024: Color image - G06T 2207/20021: Dividing image into blocks, subimages or windows - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Plural block images are generated by dividing an input image into blocks each of which has a predetermined size. Clustering of pixels contained in the plural block images is performed based on a representative point associated with each of those block images to apply region segmentation to those block images. The representative point is a part of plural representative points disposed in the input image. The clustering in a target block image of the region segmentation is performed by referring to a representative point in the target block image, a representative point of a processed block image, and a representative point of an unprocessed block image. The processed and unprocessed block images are adjacent to the target block image. ## Claims ### Claim 1 An image processing apparatus for performing region segmentation of an image, comprising: a setting unit configured to set a plurality of representative points on an input image; a selection unit configured to sequentially select a block from a plurality of blocks, which are generated by dividing the input image, as a target block; and a segmentation unit configured to perform region segmentation of the input image by clustering of pixels contained in the target block by referring to information of a representative point in the target block, and information of a representative point in at least one block adjacent to the target block including an unprocessed block in which the clustering of pixels has not been performed yet, wherein at least one of the setting unit, the selection unit, and the segmentation unit is implemented using a processor. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein the information of the representative point in the target block includes position information. ### Claim 3 (depends on 1) The apparatus according to claim 1, wherein the information of the representative point in the target block includes color information. ### Claim 4 (depends on 1) The apparatus according to claim 1, wherein the segmentation unit performs clustering of a pixel of interest in the target block by referring to information of representative points which exist in a predetermined range around a position of the pixel of interest. ### Claim 5 (depends on 1) The apparatus according to claim 1, further comprising an update unit configured to update the information of the representative point in the target block after the clustering of pixels in the target block, wherein the update unit is implemented using a processor. ### Claim 6 (depends on 5) The apparatus according to claim 5, wherein, until it is determined that the clustering in the target block has converged, the segmentation unit repeats the clustering of pixels in the target block by referring to the updated information of the representative point in the target block, and the update unit repeats the update of the information of the representative point in the target block. ### Claim 7 (depends on 5) The apparatus according to claim 5, wherein the update unit is configured to update information of the representative point as an average value of information of pixels clustered to the representative point. ### Claim 8 (depends on 1) The apparatus according to claim 1, wherein the segmentation unit performs the region segmentation by further referring to information of a representative point in at least one block adjacent to the target block including a processed block in which the clustering of pixels has already been performed. ### Claim 9 (depends on 8) The apparatus according to claim 8, further comprising an update unit configured to update the information of the representative points in the target block and the processed block adjacent to the target block after the clustering of pixels in the target block, wherein the update unit is implemented using a processor. ### Claim 10 (depends on 9) The apparatus according to claim 9, wherein the update unit does not update information of the representative point in the unprocessed block adjacent to the target block. ### Claim 11 (depends on 1) The apparatus according to claim 1, further comprising an initialization unit configured to initialize position information of the plurality of representative points so that those representation points are disposed in a grid shape in the input image, wherein the initialization unit is implemented using a processor. ### Claim 12 (depends on 11) The apparatus according to claim 11, wherein the initialization unit initializes color information of each of the plurality of representative points based on color information of a pixel corresponding to the representative point and color information of surrounding pixels of the corresponding pixel. ### Claim 13 (depends on 1) The apparatus according to claim 1, wherein the plurality of blocks are generated by dividing the input image so that a pixel does not overlap between blocks adjacent to each other. ### Claim 14 (depends on 1) The apparatus according to claim 1, wherein the plurality of blocks are generated by dividing the input image so that at least one pixel overlaps between blocks adjacent to each other. ### Claim 15 (depends on 1) The apparatus according to claim 1, further comprising: a first buffer configured to hold an image of the target block; and a second buffer configured to hold the information of the representative point in the target block and the information of the representative point in the unprocessed block adjacent to the target block, wherein the segmentation unit performs the clustering of pixels in the image of the target block held in the first buffer by referring to the information of the representative points held in the second buffer. ### Claim 16 (depends on 15) The apparatus according to claim 15, wherein the second buffer is configured to further hold the information of the representative point in the processed block adjacent to the target block. ### Claim 17 An image processing method of performing region segmentation of an image, comprising: setting a plurality of representative points on an input image; sequentially selecting a block from a plurality of blocks, which are generated by dividing the input image, as a target block; and performing region segmentation of the input image by clustering of pixels contained in the target block by referring to information of a representative point in the target block, and information of a representative point in at least one block adjacent to the target block including an unprocessed block in which the clustering of pixels has not been performed yet. ### Claim 18 A non-transitory computer readable medium storing a computer-executable program for causing a computer to perform an image processing method, the method comprising steps of: setting a plurality of representative points on an input image; sequentially selecting a block from a plurality of blocks, which are generated by dividing the input image, as a target block; and performing region segmentation of the input image by clustering of pixels contained in the target block by referring to information of a representative point in the target block, and information of a representative point in at least one block adjacent to the target block including an unprocessed block in which the clustering of pixels has not been performed yet.