Color recognition method

Abstract

The invention discloses a color identifying method which includes the following steps: characteristic zones of an object to be identified in an image are defined; colors of pixel points in the characteristic zones are identified; the colors of the pixel points are calculated to acquire characteristic vectors of zone color identification and then colors of characteristic zones used for representing the color of the object to be identified are identified. The adoption of the invention can reduce calculated amount and accelerate calculation speed and enhance identification accuracy.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for identifying the color of an object to be identified in an image. Background technique [0002] In some cases, we need to process a specific target in the captured image to obtain various features including the category of the specific target, its position, shape, size, and even color in the image, etc. Furthermore, various acquired features are used in different usage environments. [0003] Taking the vehicle monitoring that is widely implemented now as an example, in places such as public security checkpoints and expressway toll stations, vehicles on traffic roads can be monitored through the erected intelligent traffic monitoring system, for example, real-time capture by cameras to obtain high-definition Vehicle static images, using relevant recognition technology to obtain accurate vehicle-related information (such as license plate number, model ...

AI Technical Summary

Problems solved by technology

[0006] However, the above-mentioned identification method applied to the color of the vehicle body uses an algorithm based on dynamic images. Compared with the algorithm based on static images, the calculation amount required by the dynamic algorithm is relatively large, and the accuracy of the obtained identification results is relatively poor; in addition, The above color recognition method is to recognize the color of all pixels in the entire vehicle video image after the background is removed, which not only has a large amount of calculation, but also has low reliability due to the introduction of areas in the vehicle image that cannot represent the color of the vehicle body, such as car windows. Poor, low recognition accuracy

In order to improve the reliability, it is necessary to additionally use the D-S evidence theory method based on artificial statistical experience to eliminate the interference caused by the color of the wheels, lights, windows, etc., which will easily affect the versatility of the recognition system and increase the accuracy of the system. the complexity of

Images