Seriously degraded license plate image information recovery method

Abstract

The invention relates to a seriously degraded license plate image information recovery method. According to the method, a convolutional neural network is used to learn priori knowledge required by seriously degraded license plate information extraction; training and fine adjustment of the convolutional neural network are carried out by adopting the simulated license plate image and the real license plate image, and the character output probability of each license plate character position is obtained by adopting a SoftMax output form, so that a decision basis is provided for license plate information extraction, and unified processing of character segmentation and recognition is achieved. According to the method and the process, extraction of seriously degraded license plate information iseffectively realized, and extraction of all low-resolution license plate information is facilitated. The method can help the public security department to obtain meaningful evidences and clues, and has the maximum application value.

Description

technical field [0001] The invention belongs to the application field of image processing technology, in particular to a method for recovering severely degraded license plate image information. Background technique [0002] Public surveillance cameras used to monitor public areas and traffic are ubiquitous. Due to bandwidth and storage limitations, most of these video surveillance systems consist of relatively low-resolution cameras. Additionally, to expand the area covered by surveillance, these surveillance cameras are often configured to maximize the field of view, further limiting the effective resolution of objects in the video. As a result, videos captured by public surveillance cameras are often of such low resolution that important identifying details are obscured. Even advanced denoising and general super-resolution techniques cannot extract useful information from such low-quality images such as a license plate with a width of about 20 pixels. But useful informa...

AI Technical Summary

Problems solved by technology

With the recent success of Convolutional Neural Networks (CNN), various overall image recognition methods have emerged. For example, Goodfellow et al. proposed a CNN architecture capable of recognizing arbitrary combinations of numbers of bounded length for extracting from images. house numbers, but cannot handle highly degraded images

[0004] Extracting useful information from highly degraded license plates is a pathologically incomplete problem that requires a lot of prior knowledge to recover useful information from limited pixels

Images