License plate detection method based on deep learning

Abstract

The invention discloses a license plate detection method based on deep learning, comprising the following steps: using a fast-rcnn algorithm to train an RPN convolution neural network and a fast-rcnn convolution neural network; building an image library with marks and tags as a sample set; using the trained RPN convolution neural network to process the images in the sample set to get a rough license plate area; sending a rough license plate box to the trained fast-rcnn convolution neural network for judgment; and judging whether the rough license plate area is an optimal license plate area according to the output vector of the fast-rcnn convolution neural network, and if the rough license plate area is an optimal license plate area, taking the rough license plate area as a final license plate area. According to the invention, a multi-scale and multi-proportion reference box is adopted in training of the RPN convolution neural network, so detection of license plates with unconventional scale and proportion is promoted effectively. The RPN convolution neural network and the fast-rcnn convolution neural network share convolution layer parameters, so the whole system is simpler, less amount of calculation is needed, and the rate of missed detection is lower. Moreover, the real-time requirement of the system can be satisfied.

Description

technical field [0001] The invention belongs to the technical field of computer vision recognition, and in particular relates to a license plate detection method based on deep learning. Background technique [0002] Computer vision is an important interdisciplinary subject in the fields of artificial intelligence and image processing. Early solutions to computer vision tasks mainly consisted of two steps, one was to manually design features, and the other was to build a shallow learning system. With the development of artificial intelligence, deep learning was formally proposed in 2006. Deep learning originated from multi-layer artificial neural networks, and has been successfully applied in fields such as computer vision, natural language processing, and intelligent search. Currently existing deep learning networks mainly include convolutional neural networks, deep belief networks, and stacked autoencoders. Convolutional neural network is widely used in image processing ...

AI Technical Summary

Problems solved by technology

However, this method still has a big problem. If the number of image pyramid layers is too small, the amount of calculation is small, but the missed detection rate is high. If the number of image pyramid layers is too large, the missed detection rate is low, but the calculation amount is relatively high. Large, cannot meet the real-time requirements of the system, and this method fixes the size and ratio of the sliding window, for some license plates with unconventional scales and aspect ratios, it is easy to miss detection

Images