Finding products that are similar to a product selected from a plurality of products
A system and method extracts relevant image features about listed products in a network-based publication system for enabling image similarity searching of such listed products. When a seller lists a product, an image of the product is uploaded and may be sent to a picture processing service, which generates several digests. The digests are compressed data structures each representing a particular image feature of a listed product such as edge, color, texture, or words. These digests are then stored in a database, where the digests can be used to retrieve listings of products by image similarity at scale. A similar process can be performed for a query by image similarity searching the database for products similar to the query. When a product is located by image similarity search, a selectable icon is provided to enable more products like the located product to be located by image similarity search.
1. A computer-implemented method comprising:
performing a first database image similarity search for images similar to a first query image;
providing to a client machine a first plurality of images that result from the first database search, the first plurality of images selectable for providing a second query image;
responsive to selection of one of the first plurality of images, performing a second database image similarity search for images similar to the second query image;
providing to the client machine the second plurality of images that result from the second image similarity search and at least one selectable icon to find more images of products like at least one of the second plurality of images of products;
responsive to selection of one of the at least one selectable icon, performing a third database image similarity search for images similar to the at least one of the second plurality of images of products; and
providing to the client machine the third plurality of images that result from the third database image similarity search.
2. The method of claim 1 wherein one of the first query image, the second query image or the third query image is provided by a user.
3. The method of claim 1 wherein at least one of the first query image, the second query image, or the third query image comprises video content.
4. The method of claim 2 further comprising tracking selection by the user of the second query image and the third query image by use of a tracking trail to enable the user, after the selection of the second query image and the third query image to select the second query image.
5. The method of claim 1 wherein the images similar to the first query image and the images similar to the second query image and the images similar to the third query image comprise pixels, and similarity is determined by detecting regions of visually perceptible color change by computing a color gradient using a plurality of windows of computation to compute the distance between histograms of at least some of the pixels of the first query image, of the second query image, and of the third query image.
6. The method of claim 5 further comprising using individual windows of the plurality of windows of computation to divide the pixels of at least one of the listing images into a plurality of areas, and computing a difference in intensity of blackness versus whiteness of at least some of the plurality of areas.
7. The method of claim 6 wherein each window of computation is a circle and the diameter of each window divides an area of the listing image within the circle into a plurality of regions, the method further comprising computing the histograms of the pixels that lie in each of the plurality of regions.
8. One or more computer-readable hardware storage device having embedded therein a set of instructions which, when executed by one or more processors of a computer, causes the computer to execute operations comprising:
performing a first database image similarity search for images similar to a first query image;
providing to a client machine a first plurality of images that result from the first database search, the first plurality of images selectable for providing a second query image;
responsive to selection of one of the first plurality of images, performing a second database image similarity search and at least one selectable icon to find more images of products like at least one of the second plurality of images of products;
responsive to selection of one of the at least one selectable icon, performing a third database image similarity search for images similar to the at least one of the second plurality of images of products; and
providing to the client machine the third plurality of images that result from the third database image similarity search and at least one second selectable icon to find more images of products like at least one of the third plurality of images of products.
9. The one or more computer-readable hardware storage device of claim 8 wherein one of the first query image, the second query image or the third query image is provided by a user.
10. The one or more computer-readable hardware storage device of claim 8 wherein at least one of the first query image, the second query image, or the third query image comprises video content.
11. The one or more computer-readable hardware storage device of claim 9 the operations further comprising tracking selection by the user of the second query image and the third query image by use of a tracking trail to enable the user, after the selection of the second query image and the third query image to select the second query image.
12. The one or more computer-readable hardware storage device of claim 8 wherein the images similar to the first query image and the images similar to the second query image and the images similar to the third query images comprise pixels, and similarity is determined by detecting regions of visually perceptible color change by computing a color gradient using a plurality of windows of computation to compute the distance between histograms of at least some of the pixels of the first query image, of the second query image, and of the third query image.
13. The one or more computer-readable hardware storage device of claim 12 the operations further comprising using individual windows of the plurality of windows of computation to divide the pixels of at least one of the listing images into a plurality of areas, and computing a difference in intensity of blackness versus whiteness of at least some of the plurality of areas.
14. The one or more computer-readable hardware storage device of claim 13 wherein each window of computation is a circle and the diameter of each window divides an area of the listing image within the circle into a plurality of regions, the operations further comprising computing the histograms of the pixels that lie in each of the plurality of regions.
15. A system comprising:
one or more computer processors and storage configured to
perform a first database image search for images similar to a first query image;
provide to a client machine a first plurality of images that result from the first database search, the first plurality of images selectable for providing a second query image;
responsive to selection of one of the first plurality of images, perform a second database image similarity search for images similar to the second query image;
provide to the client machine the second plurality of images that result from the second image similarity search and at least one selectable icon to find more images of products like at least one of the second plurality of images of products;
responsive to selection of one of the at least one selectable icon, perform a third database image similarity search for images similar to the at least one of the second plurality of images of products; and
provide to the client machine the third plurality of images that result from the third database image similarity search.
16. The system of claim 15 wherein one of the first query image, the second query image or the third query image is provided by a user.
17. The system of claim 15 wherein at least one of the first query image, the second query image, or the third query image comprises video content.
18. The system of claim 16 the one or more computer processor and storage further configured to track selection by the user of the second query image and the third query image by use of a tracking trail to enable the user, after the selection of the second query image and the third query image to select the second query image.
19. The system of claim 15 wherein the images similar to the first query image and the images similar to the second query image and the images similar to the third query image comprise pixels, and similarity is determined by detecting regions of visually perceptible color change and the at least one computer processor and storage is further configured to compute a color gradient using a plurality of windows of computation to compute the distance between histograms of at least some of the pixels of the first query image, of the second query image, and of the third query image.
20. The system of claim 19 the at least one computer processor and storage is further configured to use individual windows of the plurality of windows of computation to divide the pixels of at least one of the listing images into a plurality of areas, and to compute a difference in intensity of blackness versus whiteness of at least some of the plurality of areas.