# US 5,353,132 A · Image processing device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 5,353,132 A - Document ID: US5353132A - Status: Granted - Kind: A - Application number: 07/902,558 - Filed: 1992-06-22 - Granted: 1994-10-04 - Earliest claimed: 1989-02-06 - Assignees: Canon Kabushiki Kaisha - Inventors: Makoto Katsuma - Web page: https://patentgrep.com/patent/US5353132A ## CPC - H04N 1/41: Bandwidth or redundancy reduction (by scanning H04N1/17 {; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00}) - G06T 7/90: Determination of colour characteristics - G06T 9/005: {Statistical coding, e.g. Huffman, run length coding} - G06T 2207/10008: from scanner, fax or copier - G06T 2207/30176: Document - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract The type of color image is identified on the basis of a distribution of color information for each color. A plurality of different types of data compression algorithms prepared beforehand are changed according to the results of the identification. Preferably, the difference between the maximum value and the minimum value of each picture element of respective color separation data of a color image is determined, and further, a histogram of frequency of color information obtained for each color is determined. On the basis of the histogram, the type of the color image is identified by the fact that whether or not the histogram contains a peak greater than a predetermined value or whether or not the deviation of the histogram is greater than a predetermined value. ## Claims ### Claim 1 An image processing device comprising: input means for inputting a plurality of color component signals representing a color image; identification means for identifying a type of the color image on the basis of the plurality of color component signals from said input means; first compression means for compressing the color component signals from said input means by using an information-preserving-type of encoding method; second compression means for compressing the color component signals from said input means by using an information-non-preserving-type of encoding method; selection means for selecting one of said first and second compression means in accordance with the type of the color image identified by said identification means; and storage means for storing compressed color component signals from said first or second compression means together with identification data representing the type of the color image identified by said identification means. ### Claim 2 (depends on 1) An image processing device according claim 1, further comprising addition means for adding the identification data to the compressed color component signals. ### Claim 3 (depends on 2) An image processing device according to claim 2, wherein said storage means stores the compressed color component signals to which the identification data is added. ### Claim 4 (depends on 1) An image processing device according to claim 1, further comprising decompression means for decompressing the compressed color component signals stored in said storage means. ### Claim 5 (depends on 4) An image processing device according to claim 4, wherein said decompression means has a plurality of different types of decompression algorithms, and said decompression means decompresses the compressed color component signals by using a decompression algorithm which is selected in accordance with the identification data associated with the compressed color component signals. ### Claim 6 (depends on 1) An image processing device according to claim 1, wherein said identification means identifies the type of the color image on the basis of a histogram of frequency of the color component signals. ### Claim 7 (depends on 1) An image processing device according to claim 1, wherein said information-non-preserving-type of encoding method is a vector quantization method. ### Claim 8 An image processing device comprising: input means for inputting a plurality of color component signals representing a color image; identification means for identifying a type of the color image on the basis of the plurality of color component signals from said input means; first compression means for compressing the color component signals from said input means by using an information-preserving-type of encoding method; second compression means for compressing the color component signals from said input means by using an information-non-preserving-type of encoding method; selection means for selecting one of said first and second compression means in accordance with the type of the color image identified by said identification means; storage means for storing compressed color component signals from said first or second compression means together with identification data representing the type of the color image identified by said identification means; and decompression means for decompressing the compressed color component signals stored in said storage means in accordance with the identification data. ### Claim 9 (depends on 8) An image processing device according to claim 8, further comprising addition means for adding the identification data to the compressed color component signals. ### Claim 10 (depends on 9) An image processing device according to claim 9, wherein said storage means stores the compressed color component signals to which the identification data is added. ### Claim 11 (depends on 8) An image processing device according to claim 8, wherein said decompression means has a plurality of different types of decompression algorithms, and said decompression means decompresses the compressed color component signals by using any one of the decompression algorithm which is selected in accordance with the identification data associated with the compressed color component signals. ### Claim 12 (depends on 8) An image processing device according to claim 8, wherein said identification means identifies the type of the color image on the basis of a histogram of frequency of the color component signals. ### Claim 13 (depends on 8) An image processing device according to claim 8, wherein said information-preserving-type of encoding method is a run length encoding method. ### Claim 14 (depends on 8) An image processing device according to claim 8, wherein said information-non-preserving-type of encoding method is a vector quantization method. ### Claim 15 An image processing method comprising the steps of: inputting a plurality of color component signals representing a color image; identifying a type of the color image on the basis of the plurality of color component signals; selecting one of an information-preserving-type of encoding method and an information-non-preserving-type of encoding method in accordance with the type of the color image identified in said identifying step; compressing the color component signals by using the selected encoding method; and storing the compressed color component signals in a memory together with identification data representing the type of the color image identified in said identifying step. ### Claim 16 (depends on 15) An image processing method according to claim 15, wherein said information-preserving-type of encoding method is a run length encoding method. ### Claim 17 (depends on 15) An image processing method according to claim 15, wherein said information-non-preserving-type of encoding method is a vector quantization method. ### Claim 18 An image processing method comprising the steps of: inputting a plurality of color component signals representing a color image; identifying a type of the color image on the basis of the plurality of color component signals; selecting one of an information-preserving-type of encoding method and an information-non-preserving type of encoding method in accordance with the type of the color image identified by said identifying step; compressing the color component signals by using the selected encoding method; storing the compressed color component signals in a memory together with identification data representing the type of the color image identified by said identifying step; and decompressing the compressed color component signals stored in said memory in accordance with the identification data. ### Claim 19 (depends on 1) An image processing device according to claim 1, wherein said information-preserving-type of encoding method is a run length encoding method. ### Claim 20 (depends on 18) An image processing method according to claim 18, wherein said information-preserving-type of encoding method is a run length encoding method. ### Claim 21 (depends on 18) An image processing method according to claim 18, wherein said information-non-preserving-type of encoding method is a vector quantization method.