Vehicle logo recognition method and system based on feature enhancement

Abstract

The invention discloses a vehicle logo recognition method and system based on feature enhancement, and belongs to the technical field of image recognition, and the method comprises the steps: carryingout the preprocessing of a vehicle logo image, obtaining a processed image, and extracting the overall features and self-symmetric similarity features of the processed image; processing the processedimage to obtain a saliency map, obtaining local saliency blocks according to the saliency map, and extracting the local saliency blocks to obtain local saliency block features; fusing the features toobtain final features; and recognizing the final features to obtain a vehicle logo recognition result. According to the system, a preprocessing unit and a feature fusion unit are connected with a feature extraction unit, and the feature fusion unit is connected with an identification unit. The method aims to overcome the defect that in the prior art, the vehicle logo recognition accuracy is low,the vehicle logo recognition accuracy can be improved, efficient vehicle logo recognition can be further achieved under the condition that the number of training samples is small, and a better vehiclelogo recognition effect is achieved.

Description

technical field [0001] The present invention relates to the field of image recognition, more specifically, to a method and system for vehicle logo recognition based on feature enhancement. Background technique [0002] In the intelligent transportation system, the information identification of the vehicle is an important part, and the identification of the vehicle logo plays an important role. The vehicle logo is a distinctive sign of the vehicle, which is highly representative and not easy to be damaged or tampered with. It can well represent vehicle information and play an important supporting role in traffic monitoring systems, vehicle tracking, and vehicle identification. In the prior art, the recognition of vehicle logos is mostly based on the improvement of some classic algorithms, which often do not have a good recognition effect on actual road images. This is because in the traffic system, the images of passing vehicles captured by the road monitoring system are oft...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this scheme is that there are certain restrictions on the car logo image when calculating the template matching coefficient in this scheme. When the position of the car logo in the image is shifted or the proportion is small, the matching result will be greatly affected. Impact

However, the disadvantage of this scheme is that this scheme only considers the random point pair information in the foreground and background skeleton, and ignores the overall features. When the skeleton area in the car logo image is affected by local lighting or shadows, the recognition effect is not stable.

Images