High definition licence plate detection algorithm

Abstract

This paper describes a background noise elimination technique introduced for License Plate (LP) detection algorithms specifically designed for High Definition (HD) images to deal with the surplus data they contain. The images are firstly enhanced using a robust method, followed by the application of morphological operators and histogram percentile autonomous thresholding for removing background noises keeping the resulting image grey. Finally, greyscale edge detection based segmentation is applied to extract the candidate regions of interest. Experiments on thousands of images show an improvement not only in LP detection in HD images, but also in edges processing time, which compensates for the additional time due to background noise elimination. The proposed algorithm is also tested on Standard Definition (SD) images where higher LP detection success is observed on SD images with complex background scenes

Automatic number plate recognition system on an ARM-DSP and FPGA heterogeneous SoC platforms

“…The overall system operates at 14 frames per second and with over 95% recognition success using a large (70K plus) UK and European database of LP images. The ANPR algorithms developed are advanced work based on earlier research work using fixed point DSPs published by the authors in [2], [3] and [4].…”

Accuracy of automatic number plate recognition (ANPR) and real world UK number plate problems

“…However, the outcome of this aspect of work will not be published nor put into the public domain. This is a pioneering work; a literature review [3][4][5][6] conducted by the authors revealed that there is no other published real-world research. These papers assume ideal experimental conditions.…”

HD number plate localization and character segmentation on the Zynq heterogeneous SoC

“…These advantages come with the drop back of having an increasingly larger number of pixels to process, which leads to more processing time. Thus, HD images processing poses a challenge to meeting real-time processing requirements of ANPR systems [1]. This challenge holds especially for the NPL stage, as it is the most timeconsuming stage of the system [2].…”