License Plates Detection Using a Gaussian Windows

Abstract

In the current study, the authors propose a method for extracting license plate regions by means of a neural network trained to output the plates center of gravity. The method is shown to be effective. Since the learning pattern presentation positions are defined by random numbers, a different pattern is submitted to the neural network for learning each time, which enables it to form a neural network with high universality of coverage. The article discusses issues of the optimal learning surface for a license plate covered by the learning pattern, the effect of suppression learning of the number and headlight sections, as well as the effect of learning pattern enlargement/reduction and of concentration value conversion. Results of evaluation tests based on pictures of 595 vehicles taken at an underground parking garage demonstrated detection rates of 98.5%.

Novel License Plate Detection Method Based on Heuristic Energy

“…Recently, machine learning-based license plate detection methods using different classifiers become very popular [11][12][13][14] . …”

A Effective Online Training Algorithm by Partitioning Bounding Box for Visual Object Tracking Using Convolutional Neural Network

“…특히, 심화 학습의 제한사항이었던 데이터 부 족과 하드웨어 한계성 문제가 GPU의 발전과 빅 데이 터의 등장으로 인해 해결되며 심화 학습을 영상 객체 추적에 적용하려는 연구가 중심이되고 있다. 심화 학 습을 적용한 영상 객체 추적은 객체 형태의 변화 및 사라짐, 조도의 변화, 빠른 움직임, 복잡한 배경 등을 극복해 대상 객체의 변형에 대응되도록 모델링되어야 한다[4] .객체의 다양한 변화에 효과적으로 대처하도록 대상객체를 모델링 하는 방법이 활발하게 연구되고 있다.…”