Three-Dimensional Indexing Protocol

• US 20150052027A1
• Filed: 08/14/2013
• Published: 02/19/2015
• Est. Priority Date: 08/14/2013
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Pavani, Sri Kaushik, Garg, Anshul
• Granted Patent: US 9,400,968 B2
• Time in Patent Office: Days
• US Class Current: 705/28
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 40/12 Accounting
• CPC Class Codes: G06T 7/0004 Industrial image inspection

Abstract

The disclosure includes a system and method for indexing synthetically modified images of a high quality image. An image recognition application receives images of a product, crops background regions from the images, scales the image based on a minimum value among width and height of the image and generates multiple image sizes, blurs the images, brightens the image and indexes the images as being associated with the product. The images can be of box-shaped packages that include four or six images or cylindrical packages that include, for example, eight images of the packages. The images can be indexed in a k-dimensional tree for faster retrieval.

Claims

1. A computer-implemented method comprising:

receiving, with one or more processors, images of a product;

cropping, with the one or more processors, background regions from the images;

scaling, with the one or more processors, the images based on a minimum value among width and height and generating multiple image sizes;

blurring, with the one or more processors, the images;

brightening, with the one or more processors, the images; and

indexing the images as being associated with the product.

2. The method of claim 1, wherein box-like products include at least four images of the product.

3. The method of claim 1, wherein cylindrical products include at least eight images of the product with at least 45 degree rotation of the cylindrical products between images.

4. The method of claim 1 further comprising instructing a user to reacquire the image if there are specular highlights due to reflection.

5. The method of claim 1, wherein the product is a first product and further comprising repeating steps for a second product that is a different type of product from the first product and generating a planogram of the first and second products.

6. The method of claim 5, further comprising:

receiving query images of products;

identifying the products from the query images; and

analyzing the products based on the query images and the planogram.

7. The method of claim 6, further comprising:

determining whether changes in product inventory exceed a threshold; and

responsive to determining that the changes in product inventory exceed the threshold, notifying a user to restock the product.

8. A system comprising:

one or more processors;

a controller stored on a memory and executable by the one or more processors, the controller configured to receive images of a product;

an image processor coupled to the controller and configured to crop background regions from the images, scale the images based on a minimum value among width and height and generate multiple image sizes, blur the images and brighten the images; and

an indexer coupled to the image processor, the indexer configured to index the images as being associated with the product.

9. The system of claim 8, wherein box-like products include at least four images of the product.

10. The system of claim 8, wherein cylindrical products include at least eight images of the product with at least 45 degree rotation of the cylindrical products between images.

11. The system of claim 8, further comprising a notification engine coupled to the image processor, the notification engine configured to instruct a user to reacquire the image if there are specular highlights due to reflection.

12. The system of claim 8, wherein the product is a first product, wherein the indexer indexes a second product that is a different type of product from the first product and further comprising an analyzer configured to generate a planogram of the first and second products.

13. The system of claim 12, wherein the analyzer is further configured to receive query images of products, identify the products from the query images and analyze the products based on the query images and the planogram.

14. The system of claim 13, wherein the analyzer is further configured to determine whether changes in product inventory exceed a threshold and responsive to determining that the changes in product inventory exceed the threshold, notifying a user to restock the product.

15. A computer program product comprising a computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive images of a product;

crop background regions from the images;

scale the images based on a minimum value among width and height and generating multiple image sizes;

blur the images;

brighten the images; and

index the images as being associated with the product.

16. The computer program product of claim 15, wherein box-like products include at least four images of the product and wherein cylindrical products include at least eight images of the product with at least 45 degree rotation of the cylindrical products between images.

17. The computer program product of claim 15, wherein the computer readable program when executed on the computer causes the computer to also instruct a user to reacquire the image if there are specular highlights due to reflection.

18. The computer program product of claim 15, wherein the product is a first product, wherein the computer readable program when executed on the computer causes the computer to also index a second product that is a different type of product from the first product and further comprising an analyzer configured to generate a planogram of the first and second products.

19. The computer program product of claim 15, wherein the computer readable program when executed on the computer causes the computer to also receive query images of products, identify the products from the query images and analyze the products based on the query images and the planogram.

20. The computer program product of claim 19, wherein the computer readable program when executed on the computer causes the computer to also determine whether changes in product inventory exceed a threshold and responsive to determining that the changes in product inventory exceed the threshold, notifying a user to restock the product.