# US 7,466,455 B2 · Image processing method and system for performing monochrome/color judgement of a pixelised image > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 7,466,455 B2 - Document ID: US7466455B2 - Status: Granted - Kind: B2 - Application number: 10/720,443 - Filed: 2003-11-25 - Published: 2004-06-03 - Granted: 2008-12-16 - Earliest claimed: 2002-11-27 - Assignees: Oce-Technologies B.V. - Inventors: Hubertus M. J. M. Boesten; Peter M. Van Der Sanden - Web page: https://patentgrep.com/patent/US7466455B2 ## CPC - H04N 1/56: Processing of colour picture signals (H04N1/52 takes precedence) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract An image processing system and method are provided for judging whether a pixelised image or a part thereof is a monochrome or a color image. To increase the reliability of the judgement, instead of making the judgement on the level of an individual pixel, the judgement is made for substantially all the pixels of the image or image part at the same time by analyzing the cumulative histogram, wherein the distance of each pixel to the gray axis versus the logarithm of the cumulative pixel count is plotted. An advantage of the present system and the method of operating this system is their high sensitivity for detecting small color objects in monochrome images. ## Claims ### Claim 1 An image processing method for processing a pixelised image, the method comprising the steps of: analyzing pixel data representative of said pixelised image in a color space and based thereon, determining a gray axis defined as a straight line connecting a white point with a black point; determining for each pixel of said pixelised image a shortest distance to said gray axis; forming a cumulative histogram by plotting for the pixels of said pixelised image a value of said shortest distance versus a cumulative pixel count being the number of associated pixels having at least said value of said shortest distance; and analyzing a relationship between the pixels in said cumulative histogram and based thereon judging whether said pixelised image is to be processed as a monochrome image or a color image. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein in the step of analyzing the relationship between the pixels in said cumulative histogram, only the pixels of said cumulative histogram having an associated cumulative pixel count value equal to or greater than a predetermined threshold are taken into account. ### Claim 3 (depends on 1) The method as recited in claim 1, wherein in the step of analyzing a relationship between the pixels in said cumulative histogram, the relationship between the pixels in said cumulative histogram is determined by applying a linear regression analysis to said pixels in said cumulative histogram. ### Claim 4 (depends on 3) The method as recited in claim 3, wherein the step of judging whether said pixelised image is to be processed as a monochrome image or a color image is based on a result of comparing a value of at least one regression parameter with a predetermined threshold value of said at least one regression parameter. ### Claim 5 (depends on 4) The method as recited in claim 4, wherein said at least one regression parameter is selected from a group of parameters comprising: a correlation coefficient (R), a coefficient of determination (R2), a slope of a regression line, and an intercept of the regression line. ### Claim 6 (depends on 1) The method as recited in claim 1, further comprising the step of: converting said pixel data representative of said pixelised image in said color space to pixel data representative of said pixelised image in a CIE color space. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein the judging step judges based on whether or not there is a linear relationship between the value of said shortest distance and the cumulative pixel count for the pixels of said pixelised image. ### Claim 8 (depends on 7) The method as recited in claim 7, wherein the judging step judges whether said pixelised image is a monochrome image if the linear relationship exists. ### Claim 9 (depends on 7) The method as recited in claim 7, wherein the judging step judges that said pixelised image is a color image if the linear relationship does not exist. ### Claim 10 An image processing system for processing a pixelised image, the system comprising: a pre-processor for analyzing pixel data representative of said pixelised image in a color space and based thereon determining a gray axis defined as a straight line connecting a white point with a black point, and determining for each pixel of said pixelised image the shortest distance to said gray axis; an analyzer for analyzing a relationship between the pixels of said pixelised image in a cumulative histogram, said cumulative histogram being formed by plotting for the pixels of said pixelised image a value of said shortest distance versus a cumulative pixel count being the number of associated pixels having at least said value of said shortest distance; and a judging unit for judging, based on said relationship between the pixels in said cumulative histogram, whether said pixelised image is to be processed as a monochrome image or a color image. ### Claim 11 (depends on 10) The system as recited in claim 10, further comprising: a fitting unit wherein the relationship between the pixels in said cumulative histogram is determined by applying a linear regression analysis to said pixels in said cumulative histogram. ### Claim 12 (depends on 10) The system as recited in claim 10, further comprising: a converter for converting said pixel data representative of said pixelised image in said color space to pixel data representative of said pixelised image in a CIE color space. ### Claim 13 (depends on 10) The system as recited in claim 10, wherein the analyzer takes into account only the pixels of said cumulative histogram having an associated cumulative pixel count value equal to or greater than a predetermined threshold. ### Claim 14 (depends on 10) The system as recited in claim 10, wherein the judging unit judges based on a result of comparing a value of at least one regression parameter with a predetermined threshold value of said at least one regression parameter. ### Claim 15 (depends on 14) The system as recited in claim 14, wherein said at least one regression parameter is selected from a group of parameters comprising: a correlation coefficient (R), a coefficient of determination (R2), a slope of a regression line, and an intercept of the regression line. ### Claim 16 (depends on 10) The system as recited in claim 10, wherein the judging unit judges based on whether or not there is a linear relationship between the value of said shortest distance and the cumulative pixel count for the pixels of said pixelised image. ### Claim 17 (depends on 16) The system as recited in claim 16, wherein the judging unit judges that said pixelised image is a monochrome image if the linear relationship exists. ### Claim 18 (depends on 16) The system as recited in claim 16, wherein the judging step judges that said pixelised image is a color image if the linear relationship does not exist. ### Claim 19 (depends on 10) The system as recited in claim 10, further comprising: a scanner to scan an original image to provide said pixelised image.