Iraqi License Plate Localization by Morphology operation and Connected Component Labeling

Abstract

Morphological image processing is a collection of non-linear operations related to the shape or morphology of features in an image. Morphological techniques probe an image with a small shape or template called a structuring element. The structuring element is positioned at all possible locations in the image and it is compared with the corresponding neighborhood of pixels. Some operations test whether the element "fits" within the neighborhood, while others test whether it "hits" or intersects the neighborhood. A set of pixels in which each pixel is connected to all other pixels is called a connected component. A component labeling algorithm finds all connected components in an image and assigns a unique label to all points in the same component. In this paper, the Morphology and CCL are used to find the Iraqi license plate location which represents the main operation in any LPR system. Most of the conclusions reached by the researcher showed that the process of identifying the car plate location is a complex process and requires a set of steps that are applied to the original image and through which to improve that image. The input images are colored images with the size of 800X600. The number of samples used in this paper are 31 vehicle with complex background , different weather and under various illumination conditions and distance .The number of samples that have been successfully detect its plate are 28 sample and the number of samples that did not detect its plate are 3.