# US 2010/0250539 A1 · Shape based picture search

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2010/0250539 A1
- Document ID: US20100250539A1
- Status: Published application
- Kind: A1
- Application number: 12/661,773
- Filed: 2010-03-22
- Published: 2010-09-30
- Earliest claimed: 2009-03-26
- Assignees: Alibaba Group Holding Limited
- Inventors: Chunyi Zhou; Weiwei Wang; Xinfeng Zhou; Yu Dong; Xiaoying Weng; Jialong Huang
- Web page: https://patentgrep.com/patent/US20100250539A1

## CPC

- G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information}
- G06F 16/58: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F 16/5854: {using shape and object relationship}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present application relates to a method for implementing picture search and a website server thereof. A method for implementing picture search includes: classifying, according to keywords in advance in a picture database, corresponding pictures by shape of objects in the pictures, and determining a sample picture for each shape type; wherein, after a server receives a picture search request sent from a client, the method includes: searching, by the server, in the picture database for the sample picture of several shape types classified in advance corresponding to the keywords in said search request, and returning, to the client, the searched sample picture of the several shape types; receiving, by the server, the sample picture of a certain shape type determined by the client, and searching, in the picture database for the pictures which correspond to said keywords and satisfy a predetermined request with the characteristic value of said determined sample pictures; returning, by the server, said found pictures to the client. The present application enables the user to search pictures of similar shapes according to the shape types, thereby satisfying the user's search demands.

## Claims

### Claim 1

A method for picture search, comprising:
classifying a plurality of pictures in a picture database according to a plurality of keywords associated with the respective ones of the plurality of pictures and according to a plurality of picture shape types;
determining a first plurality of sample pictures among the classified plurality of pictures that correspond to respective ones of the plurality of picture shape types;
receiving a picture search request from a user;
identifying a first set of found pictures in the picture database, the first set of found pictures corresponding to a keyword in the search request;
presenting a second plurality of sample pictures that correspond to the plurality of picture shape types to the user, the second plurality of sample pictures being selected from the set of found pictures;
receiving a determined sample picture that corresponds to a user selection of one of the second plurality of sample pictures; and
identifying a second set of found pictures, the second set of found pictures being selected from the first set of found pictures and having a set of corresponding characteristic values that satisfy a predetermined criterion.

### Claim 2 (depends on 1)

The method of claim 1, wherein classifying a plurality of pictures in a picture database according to a plurality of keywords associated with the respective ones of the plurality of pictures and according to a plurality of picture shape types includes extracting from the picture database a certain number of pictures with a same keyword.

### Claim 3 (depends on 1)

The method of claim 1, wherein the second plurality of sample pictures are presented to the user in a sorted order.

### Claim 4 (depends on 1)

The method of claim 1, wherein classifying the plurality of pictures according to a plurality of picture shape types includes comparing a plurality of characteristic values of the plurality of pictures.

### Claim 5 (depends on 4)

The method of claim 4, wherein comparing a plurality of characteristic values of the plurality of pictures includes grouping pictures whose differences of characteristic values are within a predetermined distance as pictures of identical or similar shape types.

### Claim 6 (depends on 1)

The method of claim 1, wherein presenting the second plurality of sample pictures that correspond to a plurality of shape types to the user includes identifying, in the picture database, pictures whose distance from a characteristic value vector of the determined sample picture is below a predetermined threshold.

### Claim 7 (depends on 1)

The method of claim 1, wherein the second plurality of sample pictures that correspond to a plurality of shape types are presented according to an order of number of user selections.

### Claim 8 (depends on 1)

The method of claim 1, wherein the second set of found pictures have identical or similar shape type to the determined sample picture.

### Claim 9

A system for implementing picture search, comprising:
one or more processors configured to:
classify a plurality of pictures in a picture database according to a plurality of keywords associated with the respective ones of the plurality of pictures and according to a plurality of picture shape types;
determine a first plurality of sample pictures among the classified plurality of pictures that correspond to respective ones of the plurality of picture shape types;
receive a picture search request from a user;
identify a first set of found pictures in the picture database, the first set of found pictures corresponding to a keyword in the search request;
present a second plurality of sample pictures that correspond to the plurality of picture shape types to the user, the second plurality of sample pictures being selected from the set of found pictures;
receive a determined sample picture that corresponds to a user selection of one of the second plurality of sample pictures; and
identify a second set of found pictures, the second set of found pictures being selected from the first set of found pictures and having a set of corresponding characteristic values that satisfy a predetermined criterion; and
one or more memories coupled to the one or more processors, configured to provide the one or more processors with instructions.

### Claim 10 (depends on 9)

The system of claim 9, wherein classifying a plurality of pictures in a picture database according to a plurality of keywords associated with the respective ones of the plurality of pictures and according to a plurality of picture shape types includes extracting from the picture database a certain number of pictures with a same keyword.

### Claim 11 (depends on 9)

The system of claim 9, wherein the second plurality of sample pictures are presented in a sorted order.

### Claim 12 (depends on 9)

The system of claim 9, wherein classifying the plurality of pictures according to a to plurality of picture shape types includes comparing a plurality of characteristic values of the plurality of pictures.

### Claim 13 (depends on 12)

The system of claim 12, wherein comparing a plurality of characteristic values of the plurality of pictures includes grouping pictures whose differences of characteristic values are within a predetermined distance as pictures of identical or similar shape types.

### Claim 14 (depends on 9)

The system of claim 9, wherein presenting the second plurality of sample pictures that correspond to a plurality of shape types to the user includes identifying, in the picture database, pictures whose distance from a characteristic value vector of the determined sample picture is below a predetermined threshold.

### Claim 15 (depends on 9)

The system of claim 9, wherein the second plurality of sample pictures that correspond to a plurality of shape types are presented according to an order of number of user selections.

### Claim 16 (depends on 9)

The system of claim 9, wherein the second set of found pictures have identical or similar shape type to the determined sample picture.
