Object recognition method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides an object recognition method and device, electronic equipment and a computer readable storage medium; wherein the method comprises the steps: receiving a business request transmitted by a client, wherein the business request comprises the type identification of a requested object recognition function and the corresponding parameter information; determining a target object identification server corresponding to the at least two object identification algorithms based on the service request; sending the parameter information to a target object identification server to enable the target object identification server to output a corresponding first object identification result; and performing duplicate removal processing on each first object identification result to obtaina second object identification result, and sending the second object identification result to the client. According to the scheme, the application platform only needs to send the service request oncefor requesting the object recognition function and receive the processed recognition result once, the implementation process of the object recognition function is simple, the result is visual, and meanwhile, the expansion cost of the object recognition function is low.

Description

technical field [0001] The present application relates to the technical field of face recognition, and in particular, the present application relates to an object recognition method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] With the development of face recognition technology, more and more face recognition technologies are applied to various monitoring application platform systems. In the more common application scenarios at present, the application platform is connected with the face recognition algorithms of multiple algorithm manufacturers, and users send business requests for various face recognition functions to the target face recognition servers corresponding to each algorithm manufacturer through the application platform. Therefore, the face recognition algorithms of corresponding algorithm manufacturers are called to realize the requested face recognition function. [0003] However, in the above application s...

AI Technical Summary

Problems solved by technology

[0003] However, in the above application scenarios, since the application platform is directly connected to the face recognition algorithms of each algorithm manufacturer, the application platform needs to carry out secondary development according to the algorithm capabilities and scheduling methods of the face recognition algorithms of each algorithm manufacturer. When docking the face recognition algorithm, it is necessary to stop the operation of the application platform for secondary development, and the application platform requests the face recognition function, and it needs to send service requests to the servers of multiple algorithm manufacturers at the same time, and receive multiple service requests at the same time. Algorithm manufacturers’ servers feed back the recognition results separately. Therefore, the cost of face recognition function expansion in the prior art solutions is high, and the application platform triggers the algorithms of each algorithm manufacturer and receives the recognition results independently of each other, making face recognition The implementation process is cumbersome

Images