Statistical characteristics in HSI color model and position histogram based vehicle license plate detection

Abstract

Visual perception takes an important role in the implementation of intelligent robot and transportation systems. Such perception is to detect and recognize various objects in the real environment. Detecting license plate (LP) is a crucial and inevitable component of the vehicle license plate recognition (VLPR) system. In this proposed algorithm, initially, HSI color model is adopted to select automatically statistical threshold value for detecting candidate regions. According to different colored LP, these candidate regions may include LP regions; geometrical properties of LP are then used for classification. The proposed method is able to deal with candidate regions under independent orientation and scale of the plate. Finally, the decomposition of candidate regions contains predetermined LP alphanumeric character by using position histogram to verify and detect vehicle license plate (VLP) region. In experiment more than 150 images were used, and they were taken from the variety of conditions such as complex scenes, illumination changing, distances and varied weather etc. Under these conditions, success of LP detection has reached more than 94%.

Segmentation of images by color features: A survey

“…But also, the color recognition is more precise because the chromaticity is well characterized. The HSV and HSI spaces are known because the color representation emulates the human perception of colors [30,49,69,150] , because humans recognize color mainly by the chromaticity, then by the intensity. The L * a * b * and L * u * v * spaces are similar, to some extent, to the HSV and HSI spaces, the difference lies, essentially, on the chromaticity characterization; but the drawback with all these spaces is the non-removable singularities.…”

“…RGB [8,22,30,51,68,72,94,106,108,119,136,142,146,157,165,170] HSV [30,67,69,100,105,118,137,150,189] HSI [30,67,69,100,105,118,137,150,189] L * a * b * [22,30,66,81,94,139,185] L * u * v * [30,125,155,160,165,191,193] YUV [23,26,27,80,…”

A Wavelet Neural Networks License Recognition Algorithm and Its Application

“…Where, I is the license, w is the width of the image, h is the height, and (i, j) is the pixel position in the image. The dynamic threshold is computed using (4).…”

“…A bior3.7 wavelet was applied to transform the vehicle image. From Table III, we can see the value scope of threshold coefficients a m in (4). Parameters k=60 and l=20 are introduced to scan the image, since the size of license candidate is more than that of the rectangle of 60×20.…”

“…Among these algorithms, the relatively matured are listed as follows: structural pattern recognition uses the rich structural information of characters to extract textural feature as recognition norm [1][2][3]. Statistical pattern recognition extracts a group of statistical features of the license characters, then classifies it by decision functions according to some rules [4][5]. Combination-based algorithms generally integrate advantages of both statistical and structural recognition algorithms, and enable themselves to process various and even more complicated patterns [6][7].…”