# US 2010/0166325 A1 · Image segmentation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2010/0166325 A1 - Document ID: US20100166325A1 - Status: Published application - Kind: A1 - Application number: 12/345,669 - Filed: 2008-12-30 - Published: 2010-07-01 - Earliest claimed: 2008-12-30 - Assignees: Yahoo! Inc. - Inventors: Srinivasan H. SENGAMEDU; Sravanthi BONDUGULA - Web page: https://patentgrep.com/patent/US20100166325A1 ## CPC - G06T 7/11: Region-based segmentation - G06T 7/194: involving foreground-background segmentation - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract An example of a method of identifying objects having desired characteristics includes obtaining images of objects and metadata associated with each image. Further, the method includes automatically initializing a portion of the each image as at least one of a foreground portion and a background portion according to the metadata associated with the each image. Furthermore, the method includes segmenting the each image into the foreground portion and the background portion. In addition, the method includes determining at least one foreground portion depicting an object of the desired characteristics. Further, the method includes electronically providing an image corresponding to the at least one foreground portion. ## Claims ### Claim 1 An article of manufacture comprising: a machine-readable medium; and instructions carried by the medium and operable to cause a programmable processor to perform: obtaining images of objects and metadata associated with each image; automatically initializing a portion of the each image as at least one of a foreground portion and a background portion according to the metadata associated with the each image; segmenting the each image into the foreground portion and the background portion; determining at least one foreground portion depicting an object of the desired characteristics; and providing an image corresponding to the at least one foreground portion. ### Claim 2 (depends on 1) The article of manufacture of claim 1, wherein the desired characteristics comprises: category and color of the object. ### Claim 3 (depends on 1) The article of manufacture of claim 1, wherein the automatically initializing comprises: identifying corner portions of the image as the background portion. ### Claim 4 (depends on 1) The article of manufacture of claim 1, wherein the automatically initializing comprises: identifying portions associated with skin color as the background portion. ### Claim 5 (depends on 1) The article of manufacture of claim 1, wherein the automatically initializing comprises: identifying central portion of the image as the foreground portion. ### Claim 6 (depends on 1) The article of manufacture of claim 1, wherein the automatically initializing comprises: identifying edges associated with the image from the metadata; and determining portions around the edges as the foreground portion. ### Claim 7 (depends on 1) The article of manufacture of claim 1, wherein the automatically initializing comprises: detecting a color texture in the image; and identifying portions associated with the color texture as the background portion. ### Claim 8 (depends on 1) The article of manufacture of claim 1, wherein the segmenting is performed based on GrabCut technique. ### Claim 9 (depends on 1) The article of manufacture of claim 1, wherein the segmenting comprises: building a color distribution; and identifying portions of the image matching a color based on the color distribution as the foreground portion. ### Claim 10 (depends on 1) The article of manufacture of claim 1 further comprising instructions operable to cause a programmable processor to perform: identifying one or more colors in the foreground portion; and associating the image with the one or more colors. ### Claim 11 A method of identifying objects having desired characteristics, the method comprising: receiving electronically, in a computer system, a request for objects having desired characteristics; obtaining images of objects and metadata associated with each image; automatically initializing a portion of the each image as at least one of a foreground portion and a background portion according to the metadata associated with the each image; segmenting the each image into the foreground portion and the background portion; determining at least one foreground portion depicting an object of the desired characteristics; and electronically providing an image corresponding to the at least one foreground portion. ### Claim 12 (depends on 11) The method of claim 11, wherein the desired characteristics comprise: category and color of the object. ### Claim 13 (depends on 11) The method of claim 11, wherein the automatically initializing comprises: identifying corner portions of the image as the background portion. ### Claim 14 (depends on 11) The method of claim 11, wherein the automatically initializing comprises: identifying portions associated with skin color as the background portion. ### Claim 15 (depends on 11) The method of claim 11, wherein the automatically initializing comprises: identifying central portion of the image as the foreground portion. ### Claim 16 (depends on 11) The method of claim 11, wherein the automatically initializing comprises: identifying edges associated with the image from the metadata; and determining portions around the edges as the foreground portion. ### Claim 17 (depends on 11) The method of claim 11, wherein the automatically initializing comprises: identifying a color texture in the image; and determining portions associated with the color texture as the background portion. ### Claim 18 (depends on 11) The method of claim 11, wherein the segmenting is performed based on GrabCut technique. ### Claim 19 (depends on 11) The method of claim 11, wherein the segmenting comprises: building a color distribution; and identifying portions of the image matching a color based on the color distribution as the foreground portion. ### Claim 20 (depends on 11) The method of claim 11 further comprising: identifying one or more colors in the foreground portion; associating the image with the one or more colors. ### Claim 21 A system for identifying objects having desired characteristics, the system comprising: one or more remote electronic devices; a communication interface in electronic communication with the one or more remote electronic devices for receiving a request for an object having the desired characteristics; one or more storage devices for storing images of objects; a memory for storing instructions; and a processor responsive to the instructions to automatically segment each image into a foreground portion and a background portion, to determine at least one foreground portion depicting the object having the desired characteristics, and to provide an image corresponding to the at least one foreground portion.