Double-layer convolutional neural network-based license plate reconstruction method

Abstract

The invention provides a double-layer convolutional neural network-based license plate reconstruction method. The method includes the following steps that: blurring processing is performed on a clearlicense plate image on the basis of a random fuzzy kernel, so that a corresponding blurred license plate image can be generated; and blurred image blocks of a fixed size are intercepted from the blurred license plate image, and are inputted into a pre-designed de-blurring convolutional neural network, so that a de-blurred image feature layer is obtained; the same blurred license plate image blockis inputted into a pre-designed image enhancement convolutional neural network, so that an image enhancement mask set can be obtained; the de-blurred image feature layer and the image enhancement maskset are combined into a two-layer aggregation feature set, and a model is trained, so that reconstruction convolution parameters can be obtained; a blurred license plate image in an actual scene is inputted into a double-layer convolutional neural network, and is subjected to calculation with the reconstruction convolution parameters, so that a reconstructed license plate image can be obtained. With the method of the invention adopted, the quality of a blurred and degraded image can be improved; the contrast of the image can be improved; the sharpness of the image can be improved; and the edge and texture details of the image can be enhanced.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for reconstructing a license plate based on a double-layer convolutional neural network. Background technique [0002] With the development of intelligent and automatic management, people pay more and more attention to it, among which the automatic recognition of license plate is one of the important basic functions. In actual scenarios, the license plate detection and recognition system needs to face many special environments, such as rain, snow and smog. Insufficient light in these actual scenes leads to unclear and blurred license plates that need to be detected and recognized. If the camera is out of focus or shakes, the characters of the captured license plate image will be blurred. Therefore, reconstruction of blurred license plate images and recovery of real information have attracted more and more attention from technicians. [0003] There...

AI Technical Summary

Problems solved by technology

For example, the Wiener filter algorithm and the ConstraintLeast Square algorithm, although the calculation speed is very fast, the deblurring result image will be greatly disturbed by noise

Although the currently commonly used RL algorithm and Total Variation algorithm can obtain better image deblurring results, due to the need for cyclic and iterative processing, the algorithm has high computational complexity and slow calculation speed.

Existing image restoration methods will cause ringing and overexposure spots in the reconstructed image

Images