Object Recognition Method and Apparatus

A method, comprising:

• obtaining, by a device, a to-be-recognized image and one or more body regions of the to-be-recognized image, wherein the one or more body regions comprise a to-be-recognized object;
• determining, by the device, a saliency score of each body region of the one or more body regions, wherein the respective saliency score of each respective body region represents a saliency degree of an object in the respective body region;
• and
• when a saliency score of a body region A is greater than or equal to a categorization threshold, determining, by the device, a feature vector of an object in the body region A based on a feature of the object in the body region A, and determining a category of the object in the body region A based on the feature vector of the object in the body region A and a category feature vector in a feature library, wherein the body region A is comprised in one of the one or more body regions, and the category feature vector represents a common feature of objects of a same category or a feature of one category of objects.

A method, comprising:

• receiving a feature library update request sent by a first terminal, wherein the feature library update request carries N categories of samples and a category of each category of samples of the N categories of samples, and each category of samples in the N categories of samples includes one sample;
• updating a feature library based on the N categories of samples and the category of each category of samples of the N categories of samples;
• receiving an object recognition request sent by a second terminal, wherein the object recognition request comprises a to-be-recognized image block, and wherein the first terminal and the second terminal are a same terminal or different terminals;
• determining a category of an object in the to-be-recognized image block based on a feature of the object in the to-be-recognized image block;
• and
• sending a recognition response message to the second terminal, wherein the recognition response message carries a category of the object in the to-be-recognized image block, and the category of the object in the to-be-recognized image block is a category of the categories of the N categories of samples.

A server, comprising:

• a non-transitory memory, configured to store a computer program;
• and
• a processor, configured to invoke the computer program stored in the non-transitory memory and run the computer program to perform operations comprising:
• receiving a feature library update request sent by a first terminal, wherein the feature library update request carries N categories of samples and a category of each category of samples of the N categories of samples, and each category of samples of the N categories of samples includes a sample;
• updating a feature library based on the N categories of samples and the category of each category of samples of the N categories of samples;
• receiving an object recognition request sent by a second terminal, wherein the object recognition request comprises a to-be-recognized image block, and the first terminal and the second terminal are a same terminal or different terminals;
• determining a category of an object in the to-be-recognized image block based on a feature of the object in the to-be-recognized image block;
• and
• sending a recognition response message to the second terminal, wherein the recognition response message carries a category of the object in the to-be-recognized image block, and the category of the object in the to-be-recognized image block is a category of the categories of the N categories of samples.