# US 2021/0241503 A1 · Method and apparatus for automatic line drawing coloring and graphical user interface thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241503 A1 - Document ID: US20210241503A1 - Status: Published application - Kind: A1 - Application number: 17/239,278 - Filed: 2021-04-23 - Published: 2021-08-05 - Earliest claimed: 2017-05-23 - Assignees: Preferred Networks, Inc. - Applicants: Preferred Networks, Inc. - Inventors: Taizan YONETSUJI - Web page: https://patentgrep.com/patent/US20210241503A1 ## CPC - G06T 11/10: Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) - G06T 7/90: Determination of colour characteristics - G06T 9/002: {using neural networks} - G06T 11/20: Drawing from basic elements - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/10024: Color image - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20092: Interactive image processing based on input by user - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An apparatus and a method for coloring line drawing is disclosed for: acquiring line drawing data; performing reduction processing on the line drawing data to be a predetermined reduced size to obtain reduced line drawing data; coloring the reduced line drawing data based on a first learned model which is learned in advance using sample data; and coloring original line drawing data with the colored reduced data and the original line drawing data as inputs based on a second learned model which is learned in advance. ## Claims ### Claim at position 1 1-17. (canceled) ### Claim 18 A coloring apparatus comprising: at least one memory; and at least one processor configured to: perform a coloring process on target data based on a first model to generate first data; perform a coloring process on the target data based on a second model to generate second data; and synthesize the first data and the second data into synthesized colored data. ### Claim 19 (depends on 18) The coloring apparatus according to claim 18, wherein the first model is trained in advance by a first sample data group, and the second model is trained in advance by a second sample data group that is at least partially different from the first sample data group. ### Claim 20 (depends on 18) The coloring apparatus according to claim 18, wherein the target data includes a first layer and a second layer, and the at least one processor is configured to: generate the first data by performing the coloring process on the first layer of the target data based on the first model, and generate the second data by performing the coloring process on the second layer of the target data based on the second model. ### Claim 21 (depends on 20) The coloring apparatus according to claim 20, wherein the first model is trained in advance by a first sample data group, and the second model is trained in advance by a second sample data group that is at least partially different from the first sample data group. ### Claim 22 (depends on 20) The coloring apparatus according to claim 20, wherein the first layer represents a background of the target data, and the second layer represents a person appearing in the target data. ### Claim 23 (depends on 18) The coloring apparatus according to claim 18, wherein the at least one processor is further configured to select the first model from a plurality of models, and select the second model from the plurality of models. ### Claim 24 (depends on 18) The coloring apparatus according to claim 18, wherein the at least one processor is configured to synthesize the first data and the second data into the synthesized colored data based on a synthesis ratio. ### Claim 25 A coloring apparatus comprising: at least one memory; and at least one processor configured to: perform a coloring process on a first layer of target data based on a first model to generate first data; perform a coloring process on a second layer of the target data based on a second model to generate second data; and obtain one colored data based on the first data and the second data. ### Claim 26 (depends on 25) The coloring apparatus according to claim 25, wherein the first model is the same model as the second model. ### Claim 27 (depends on 25) The coloring apparatus according to claim 25, wherein the first layer represents a background of the target data, and the second layer represents a person appearing in the target data. ### Claim 28 (depends on 25) The coloring apparatus according to claim 25, wherein the first data is generated by performing the coloring process on a part of the first layer of the target data based on the first model. ### Claim 29 (depends on 25) The coloring apparatus according to claim 25, wherein the second data is generated by performing the second coloring process on a part of the second layer of the target data based on the second model. ### Claim 30 (depends on 25) The coloring apparatus according to claim 25, wherein the one colored data is generated by superimposing the second data on the first data. ### Claim 31 A coloring method comprising: performing a coloring process on target data based on a first model to generate first data; performing a coloring process on the target data based on a second model to generate second data; and synthesizing the first data and the second data into synthesized colored data. ### Claim 32 (depends on 31) The coloring method according to claim 31, wherein the target data includes a first layer and a second layer, the first data is generated by performing the coloring process on the first layer of the target data based on the first model, and the second data is generated by performing the coloring process on the second layer of the target data based on the second model. ### Claim 33 (depends on 32) The coloring method according to claim 32, wherein the first layer represents a background of the target data, and the second layer represents a person appearing in the target data. ### Claim 34 (depends on 31) The coloring method according to claim 31, further comprising: selecting the first model from a plurality of models; and selecting the second model from the plurality of models. ### Claim 35 A coloring method comprising: performing a coloring process on a first layer of target data based on a first model to generate first data; performing a coloring process on a second layer of the target data based on a second model to generate second data; and obtaining one colored data based on the first data and the second data. ### Claim 36 (depends on 35) The coloring method according to claim 35, wherein the first model is the same model as the second model. ### Claim 37 (depends on 35) The coloring method according to claim 35, wherein the first layer represents a background of the target data, and the second layer represents a person appearing in the target data. ### Claim 38 A non-transitory recording medium storing program instructions for causing at least one computer to perform: performing a coloring process on target data based on a first model to generate first data; performing a coloring process on the target data based on a second model to generate second data; and synthesizing the first data and the second data into synthesized colored data. ### Claim 39 A non-transitory recording medium storing program instructions for causing at least one computer to perform: performing a coloring process on a first layer of target data based on a first model to generate first data; performing a coloring process on a second layer of the target data based on a second model to generate second data; and obtain one colored data based on the first data and the second data.