Segmentation of an image based on color and color differences
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/34
G06T-007/11
G06T-007/187
G06T-007/90
G06T-011/00
G06K-009/46
G06Q-030/06
출원번호
US-0388163
(2016-12-22)
등록번호
US-9905012
(2018-02-27)
발명자
/ 주소
Harvill, Young
출원인 / 주소
Zazzle Inc.
대리인 / 주소
Hickman Palermo Becker Bingham LLP
인용정보
피인용 횟수 :
0인용 특허 :
14
초록▼
An input image is partitioned into a plurality of image regions based on color and color differences. The partitioning comprises assigning a color difference value to plurality of locations within the input image. The partitioning further comprises assigning each of the plurality of locations to an
An input image is partitioned into a plurality of image regions based on color and color differences. The partitioning comprises assigning a color difference value to plurality of locations within the input image. The partitioning further comprises assigning each of the plurality of locations to an image region of the plurality of image regions, where the assigning occurs according to a particular order. The particular order is based at least in part on color difference values associated with the plurality of locations. The input image may comprise markup. Data representing at least a particular portion of the markup in the input image based on the partitioning is identified. Data representing at least the portion of the markup may be used in a visualization of a customizable product or a manufacturing control associated with a customizable product.
대표청구항▼
1. A computer-implemented method, comprising: using one or more computing devices, receiving an input image comprising a digital image photograph of a customizable product with markup;using the one or more computing devices, partitioning the input image into a plurality of image regions based on col
1. A computer-implemented method, comprising: using one or more computing devices, receiving an input image comprising a digital image photograph of a customizable product with markup;using the one or more computing devices, partitioning the input image into a plurality of image regions based on color and color differences of pixels of the input image and generating region information that specifies how the input image is partitioned into the plurality of image regions;based at least in part on the region information that specifies how the input image is partitioned into the plurality of image regions, determining data that represents at least a particular portion of the markup in the input image;wherein the data that represents at least the particular potion of the markup in the input image comprises information about a set of image locations that are within the particular portion of the markup, and is determined based on a region array and a region list included in the information that specifies how the input image is partitioned into the plurality of image regions, and indicates a color of the particular portion of the markup embellished in the input image;based at least in part on the data, determining rendering instructions for rendering a computer-generated visualization of the customizable product; andsending the rendering instructions for rendering the computer-generated visualization of a customizable product to a web server. 2. The computer-implemented method of claim 1, further comprising removing luminance information from the input image before partitioning the input image into the plurality of image regions. 3. The computer-implemented method of claim 1, further comprising: assigning a color difference value to each location of a plurality of locations within the input image, wherein a particular color difference value assigned to a particular location is determined based in part on the input image and indicates how different a color of the particular location is from colors of other locations neighboring the particular location;assigning each location of the plurality of locations to an image region of the plurality of image regions according to a particular order, wherein the particular order is based at least in part on color difference values associated with the plurality of locations;selecting a particular image region for assignment to the particular location based in part on the color of the particular location, wherein the color of the particular location is determined based at least in part on the input image. 4. The computer-implemented method of claim 1, further comprising: determining that a first location adjacent to a certain location is assigned to a first region and a second location adjacent to the certain location is assigned to a second region different from the first location;assigning the certain location to a selected region of the first region and the second region based on determining that a color of the certain location is more similar to a color representing the selected region than a color representing a non-selected region of the first region and the second region. 5. The computer-implemented method of claim 1, further comprising: determining that a certain adjacent location is the only location, of a plurality of locations adjacent to a certain location, that has been assigned a region;in response to the determination, assigning the certain location to a region assigned to the certain adjacent location. 6. The computer-implemented method of claim 1, further comprising: determining that a first location adjacent to a certain location is assigned to a first region and a second location adjacent to the certain location is assigned to a second region different from the first location;determining whether to merge the first region and the second region, wherein the determining whether to merge the first region and the second region comprises comparing a color representing the first region with a color representing the second region. 7. The computer-implemented method of claim 1, further comprising: storing, in a plurality of separate data structures in computer memory, information describing the plurality of image regions, the plurality of data structures including a first data structure which identifies, for each image region of the plurality of image regions: a representative color value identifying a color that represents the image region; a size of the image region; or a single location assigned to the image region. 8. The computer-implemented method of claim 7, wherein the plurality of separate data structures include a second data structure comprising a plurality of entries, each entry of the plurality of entries representing a single corresponding location of a plurality of locations and identifies either a corresponding next location relative to the corresponding location, wherein the next location relative to the corresponding location is a location different than the corresponding location and is assigned to the same image region as the corresponding location; or a value indicating that there is no next location relative to the corresponding location. 9. The computer-implemented method of claim 8, further comprising: determining which regions are assigned to locations adjacent to a certain location of the plurality of locations;assigning the certain location to a certain image region of the plurality of image regions based, in part, on the regions that are assigned to the locations adjacent to the certain location. 10. A computer system comprising: one or more processors;a non-transitory computer-readable storage medium storing one or more sequences of instructions which when executed by the one or more processors cause the one or more processors to perform:using one or more computing devices, receiving an input image comprising a digital image photograph of a customizable product with markup;using the one or more computing devices, partitioning the input image into a plurality of image regions based on color and color differences of pixels of the input image and generating region information that specifies how the input image is partitioned into the plurality of image regions;based at least in part on the region information that specifies how the input image is partitioned into the plurality of image regions, determining data that represents at least a particular portion of the markup in the input image;wherein the data that represents at least the particular potion of the markup in the input image comprises information about a set of image locations that are within the particular portion of the markup, and is determined based on a region array and a region list included in the information that specifies how the input image is partitioned into the plurality of image regions, and indicates a color of the particular portion of the markup embellished in the input image;based at least in part on the data, determining rendering instructions for rendering a computer-generated visualization of the customizable product; andsending the rendering instructions for rendering the computer-generated visualization of a customizable product to a web server. 11. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform removing luminance information from the input image before partitioning the input image into the plurality of image regions. 12. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: assigning a color difference value to each location of a plurality of locations within the input image, wherein a particular color difference value assigned to a particular location is determined based in part on the input image and indicates how different a color of the particular location is from colors of other locations neighboring the particular location;assigning each location of the plurality of locations to an image region of the plurality of image region according to a particular order, wherein the particular order is based at least in part on color difference values associated with the plurality of locations;selecting a particular image region for assignment to the particular location based in part on the color of the particular location, wherein the color of the particular location is determined based at least in part on the input image. 13. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: determining that a first location adjacent to a certain location is assigned to a first region and a second location adjacent to the certain location is assigned to a second region different from the first location;assigning the certain location to a selected region of the first region and the second region based on determining that a color of the certain location is more similar to a color representing the selected region than a color representing a non-selected region of the first region and the second region. 14. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: determining that a certain adjacent location is the only location, of a plurality of locations adjacent to a certain location, that has been assigned a region;in response to the determination, assigning the certain location to a region assigned to the certain adjacent location. 15. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: determining that a first location adjacent to a certain location is assigned to a first region and a second location adjacent to the certain location is assigned to a second region different from the first location;determining whether to merge the first region and the second region, wherein the determining whether to merge the first region and the second region comprises comparing a color representing the first region with a color representing the second region. 16. The computer system of claim 10, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: storing, in a plurality of separate data structures in computer memory, information describing the plurality of image regions, wherein the plurality of data structures includes a first data structure, which identifies, for each image region of the plurality of image regions: a representative color value identifying a color that represents the image region; a size of the image region; or a single location assigned to the image region. 17. The computer system of claim 16, wherein the plurality of separate data structures include a second data structure comprising a plurality of entries, wherein each entry of the plurality of entries represents a single corresponding location of a plurality of locations and identifies either a corresponding next location relative to the corresponding location, wherein the next location relative to the corresponding location is a location different than the corresponding location and is assigned to the same image region as the corresponding location; or a value indicating that there is no next location relative to the corresponding location. 18. The computer system of claim 17, the storage medium storing additional instructions which when executed by the one or more processors cause the one or more processors to perform: determining which regions are assigned to locations adjacent to a certain location of the plurality of locations;assigning the certain location to a certain image region of the plurality of image regions based, in part, on the regions that are assigned to the locations adjacent to the certain location.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (14)
Edwards, Eric; Fisher, Clay Harvey, Automatic color adjustment of a template design.
Yamaguchi, Takashi; Miki, Takeo; Miyazaki, Kenji, Image processing method and image processing device for embedding invisible sub information into main images.
Vantaram, Sreenath Rao; Saber, Eli; Dianat, Sohail; Shaw, Mark; Bhaskar, Ranjit, Methods for adaptive and progressive gradient-based multi-resolution color image segmentation and systems thereof.
Davidson Leonard (Los Angeles CA) Russell Matt (Glendale CA) Allred Scott (Riverside CA) Russell Michael S. (Glendale CA), System for creating and producing custom card products.
Ackley, Jonathan M.; Dubin, Jason; Romero, Nuria E.; Van Gilder, Amy K.; Williams, Jay D.; Aviv, Oren R.; Wieland, Alexis P., Systems and methods for decoding an image to determine a digital identifier.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.