Image analysis for results of textual image queries

1. An image query processing method, comprising:

determining, by a computing system comprising one or more computing devices, using a user query, an image category for images responsive to the user query;

selecting, by the computing system, using data that associates a plurality of images with a corresponding category, a subset of the images that each belong to the image category, each image in the plurality of images belonging to one of two or more categories;

analyzing, by the computing system, using the user query, data for the images in the subset of the images to determine images responsive to the user query;

determining, by the computing system, a response to the user query using the images responsive to the user query;

determining, by the computing system, an output type that identifies a type of content responsive to the user query; and

providing, by the computing system, the response to the user query for presentation based on the output type.

2. The method of claim 1 , comprising:

determining, by the computing system, using the user query, one or more key phrases for the user query; and

wherein analyzing, using the user query, data for the images in the subset of the images to determine images responsive to the user query comprises analyzing, using the one or more key phrases, data for the images in the subset of the images to determine images responsive to the user query.

3. The method of claim 1 , wherein the output type comprises at least one of an image, an annotated image, a total cost, or a textual summary.

4. The method of claim 1 , wherein selecting the subset of the images comprises selecting the subset of the images using the output type and the image category.

5. The method of claim 1 , wherein providing, by the computing system, the response to the user query for presentation comprises:

generating instructions for an audible presentation of the data responsive to the user query; and

providing the instructions to a speaker to cause the speaker to provide the audible presentation of the data responsive to the user query.

6. The method of claim 1 , wherein providing, by the computing system, the response to the user query for presentation comprises:

generating instructions for a visual presentation of the data responsive to the user query; and

providing the instructions to a display to cause the display to provide the visual presentation of the data responsive to the user query.

7. The method of claim 1 , wherein:

generating the instructions comprises generating, for at least one of the images responsive to the user query, instructions for an audible presentation of the data responsive to the user query and that indicates a location of the portion of the at least one of the images that depicts the data responsive to the query; and

providing the instructions comprises providing the instructions to the speaker to cause the speaker to provide, for the at least one of the images responsive to the user query, the audible presentation of the data responsive to the user query and that indicates a location of the portion of the image that depicts the data responsive to the query.

8. The method of claim 1 , wherein:

determining the response to the user query using the images responsive to the user query comprises selecting for each image responsive to the user query using the output type, a portion of the image that depicts data responsive to the user query; and

providing, using the output type, the response to the user query for presentation comprises:

generating instructions for presentation of a user interface that emphasizes, for each image responsive to the user query, the portion of the image that depicts the data responsive to the user query; and

providing the instructions to a display to cause the display to present the user interface and at least one of the images responsive to the user query.

9. The method of claim 8 , wherein selecting the portion of the image that depicts data responsive to the user query comprises:

determining a bounding box for the image that surrounds the data responsive to the user query; and

selecting the portion of the image defined by the bounding box.

10. The method of claim 8 , wherein selecting the portion of the image that depicts data responsive to the user query comprises cropping, for at least one of the images responsive to the user query, the image to remove content that is not responsive to the user query.

11. The method of claim 10 , wherein cropping the image to remove content that is not responsive to the user query comprises cropping the image so that the data responsive to the user query comprises a fixed size or a percent of the cropped image.

12. The method of claim 11 , the operations comprising:

determining, by the computing system, the percent of the cropped image using context depicted in the image.

13. The method of claim 12 , wherein determining the percent of the cropped image using context depicted in the image comprises determining the percent of the cropped image using at least one of the data responsive to the query depicted in the image, text depicted in the image, or a boundary of an object depicted in the image.

14. The method of claim 8 , wherein generating the instructions for presentation of the user interface comprises:

determining an output format using a quantity of the images responsive to the user query or the output type or both; and

generating the instructions for presentation of the user interface using the output format.

15. The method of claim 14 , wherein determining the output format comprises:

determining that a single image from an image database depicts data responsive to the user query; and

in response to determining that a single image from the image database depicts data responsive to the user query, selecting an output format that depicts, in the user interface, only data from the image.

16. The method of claim 14 , wherein:

determining the output format comprises:

determining that multiple images from the plurality of images depict data responsive to the user query; and

in response to determining that multiple images from the plurality of images depict data responsive to the user query, selecting a summary output format that depicts, in the user interface, a) a summary of the data responsive to the user query from the multiple images and b) data from each of the multiple images; and

generating the instructions for presentation of the user interface using the output format comprises generating the instructions for presentation of the user interface that includes a) the summary of the data responsive to the user query and b) the data from each of the multiple images.

17. The method of claim 16 , wherein the user interface comprises a navigation control that enables a user to scroll through presentation of the data from each of the multiple images.

18. The method of claim 8 , wherein providing the instructions to a display to cause the display to present the user interface and at least one of the images responsive to the user query comprises providing the instructions to a display to cause the display to present an answer to the user query in the user interface.

19. The method of claim 1 , comprising:

for each of two or more images in the plurality of images:

analyzing, by the computing system, image data for the image using object recognition to determine an initial image category for the image from the two or more categories; and

determining, by the computing system, whether the initial image category is included in a particular group of image categories;

for at least one image from the two or more images for which the initial image category is included in the particular group of image categories:

determining, by the computing system, to use the initial image category as the image category for the image;

for at least one image from the two or more images for which the initial image category is not included in the particular group of image categories:

analyzing, by the computing system, the image data for the image using text recognition to determine a second image category for the image from the two or more categories; and

determining, by the computing system, the image category for the image using the initial image category and the second image category; and

storing, by the computing system, for each of the two or more images, data in a database that associates the image with the image category for the image.

20. The method of claim 19 , the operations comprising:

for each of the two or more images:

receiving the image data before the image data is stored in an image database; and

storing the image data in the image database, wherein analyzing the image data is responsive to receiving the image data.