Architecture for responding to a visual query
View Patent ↗A visual query such as a photograph, a screen shot, a scanned image, a video frame, or an image created by a content authoring application is submitted to a visual query search system. The search system processes the visual query by sending it to a plurality of parallel search systems, each implementing a distinct visual query search process. These parallel search systems may include but are not limited to optical character recognition (OCR), facial recognition, product recognition, bar code recognition, object-or-object-category recognition, named entity recognition, and color recognition. Then at least one search result is sent to the client system. In some embodiments, when the visual query is an image containing a text element and a non-text element, at least one search result includes an optical character recognition result for the text element and at least one image-match result for the non-text element.
1. A computer-implemented method of processing a visual query comprising:
at a computing device having one or more processors and memory storing one or more programs for execution by the one or more processors:
obtaining a visual query having two or more objects including:
(i) a first object having a first object type; and
(ii) a second object having a second object type distinct from the first object type,
the first and second object types are selected from the group consisting of:
OCR characters, a person's face, a non-human object, and a bar code;
partitioning the visual query into two or more regions including a first region and a second region, wherein
the first region includes the first object, and
the second region includes the second object;
processing the visual query by concurrently obtaining visual query search results including:
(i) a first set of results generated in accordance with the first object;
(ii) a second set of results generated in accordance with the second object;
formatting for concurrent display (i) the first set of results and (ii) the second set of results to a user;
obtaining one or more user annotations of a particular result in the first set of results or in the second set of results, wherein the one or more user annotations indicate an action taken by a user indicating a respective search result's relevancy, or lack thereof, to the visual query;
obtaining a second visual query; and
in response to obtaining the second visual query, obtaining a second plurality of search results based on at least one annotation in the one or more user annotations.
2. The computer-implemented method of claim 1 , wherein the visual query is selected from the group consisting of: a photograph, a screen shot, a scanned image, a video frame, and a plurality of video frames.
3. The method of claim 1 , wherein the one or more user annotations include a user-indicated portion of the visual query, and corresponding user-provided information identifying an object displayed in the portion of the visual query.
4. The method of claim 3 , wherein the corresponding user-provided information includes text identifying the first object or the second object.
5. The method of claim 1 , wherein the first set of results and the second set of results are grouped into different groups when displayed to the user.
6. The method of claim 1 , wherein the one or more user annotations are selected from the group consisting of: user description of the visual query, user description of a portion of the visual query, user review, and user correction of a respective search result.
7. A computer system, for processing a visual query, comprising:
one or more central processing units for executing programs;
memory storing one or more programs to be executed by the one or more central processing units;
the one or more programs comprising instructions for:
obtaining a visual query having two or more objects including:
(i) a first object having a first object type; and
(ii) a second object having a second object type distinct from the first object type,
the first and second object types are selected from the group consisting of:
OCR characters, a person's face, a non-human object, and a bar code;
partitioning the visual query into two or more regions including a first region and a second region, wherein
the first region includes the first object, and
the second region includes the second object;
processing the visual query by concurrently obtaining visual query search results including:
(i) a first set of results generated in accordance with the first object;
(ii) a second set of results generated in accordance with the second object;
formatting for concurrent display (i) the first set of results and (ii) the second set of results to a user;
obtaining one or more user annotations of a particular result in the first set of results or in the second set of results, wherein the one or more user annotations indicate an action taken by a user indicating a respective search result's relevancy, or lack thereof, to the visual query;
obtaining a second visual query; and
in response to obtaining the second visual query, obtaining a second plurality of search results based on at least one annotation in the one or more user annotations.
8. The system of claim 7 , wherein the visual query is selected from the group consisting of: a photograph, a screen shot, a scanned image, a video frame, and a plurality of video frames.
9. The system of claim 7 , wherein the one or more user annotations include a user-indicated portion of the visual query, and corresponding user-provided information identifying an object displayed in the portion of the visual query.
10. The system of claim 9 , wherein the corresponding user-provided information includes text identifying the first object or the second object.
11. The system of claim 7 , wherein the first set of results and the second set of results are grouped into different groups when displayed to the user.
12. The system of claim 7 , wherein the one or more user annotations are selected from the group consisting of: user description of the visual query, user description of a portion of the visual query, user review, user correction of a respective search result.
13. A non-transitory computer readable storage medium for processing a visual query storing one or more programs configured for execution by a computer, the one or more programs comprising instructions for:
obtaining a visual query having two or more objects including:
(i) a first object having a first object type; and
(ii) a second object having a second object type distinct from the first object type,
the first and second object types are selected from the group consisting of: OCR characters, a person's face, a non-human object, and a bar code;
partitioning the visual query into two or more regions including a first region and a second region, wherein
the first region includes the first object, and
the second region includes the second object;
processing the visual query by concurrently obtaining visual query search results including:
(i) a first set of results generated in accordance with the first object;
(ii) a second set of results generated in accordance with the second object;
formatting for concurrent display (i) the first set of results and (ii) the second set of results to a user;
obtaining one or more user annotations of a particular result in the first set of results or in the second set of results, wherein the one or more user annotations indicate an action taken by a user indicating a respective search result's relevancy, or lack thereof, to the visual query;
obtaining a second visual query; and
in response to obtaining the second visual query, obtaining a second plurality of search results based on at least one annotation in the one or more user annotations.
14. The non-transitory computer readable storage medium of claim 13 , wherein the visual query is selected from the group consisting of: a photograph, a screen shot, a scanned image, a video frame, and a plurality of video frames.
15. The non-transitory computer readable storage medium of claim 13 , wherein the one or more user annotations include a user-indicated portion of the visual query, and corresponding user-provided information identifying an object displayed in the portion of the visual query.
16. The non-transitory computer readable storage medium of claim 15 , wherein the corresponding user-provided information includes text identifying the first object or the second object.
17. The non-transitory computer readable storage medium of claim 13 , wherein the first set of results and the second set of results are grouped into different groups when displayed to the user.
18. The non-transitory computer readable storage medium of claim 13 , wherein the one or more user annotations are selected from the group consisting of: user description of the visual query, user description of a portion of the visual query, user review, and user correction of a respective search result.