Application of Top Hat Transform technique on Indian license plate image localization

Abstract

Automatic License Plate Recognition (ALPR)is used in Intelligent Transportation systems wherein they are deployed for automatic ticketing of vehicles at car parking area, tracking vehicles during traffic signal violations and related applications. Out of the three major modules of ALPR systems, namely 1. localization of license plate from vehicle image, 2. segmentation of the characters images from the localized license plate and 3.Recognition of segmented characters images as license plate number, localization of potential license plate from the vehicle images is the most challenging task due to the huge variations in size, shape, color, texture and spatial orientations of license plate regions in such images. LP Localization fails often due to the presence of complex background and non-uniform illumination of license plate due to varying lighting conditions. In this paper, we propose a smart, simple and efficient algorithm for Indian license Plate Localization using Top Hat Transformation, which suppresses the background of image and remove the non uniform illumination. The algorithm is tested with live ALPR field images, confirming the robustness of the proposed method against adverse imaging condition.

Quantitative Assessment of Eye Phenotypes for Functional Genetic Studies UsingDrosophila melanogaster

“…As the quality of the final output extracted from the image depends on the size of the SE, we tested different combination of SE sizes to optimize the pixel intensity of the circular shaped ommatidia ( Figure S1 ). We performed a top-hat transformation to extract light objects from a dark background ( Arulmozhi et al 2012 ). As a result, the background is suppressed as pixel values are subtracted from the input frame, reducing its intensity and enhancing the eye region in the process.…”

“…The images obtained from SEM were processed differently, as a low contrast between the foreground (eye) and the background limited the application of top hat transformation to suppress the background ( Arulmozhi et al 2012 ). In addition, the SEM images capture the details in the area surrounding the eye, thereby significantly increasing the background noise, and thus hindering the accurate detection of the ommatidial cluster.…”

“…In a bright-field image, the contrast is between the reflection spot at the center of the ommatidium and the rest of the ommatidium, while, in a SEM image, this contrast is between a darker center and lighter boundary of the ommatidium. Then, by applying top hat transformation to the enhanced image, the ommatidia were highlighted from the background ( Arulmozhi et al 2012 ). However, noises such as light reflection on the boundary between neighboring ommatidia are also extracted.…”

A smart camera for the surveillance of vehicles in intelligent transportation systems

“…Strengthening of edges is achieved by combining selected binarization methods with techniques including greying, normalizing, histogram equalization, etc., as reported in [41]. Other preprocessing objectives, such as noise removal and general image enhancement, are achieved by applying wavelet-based filters [55] and the top-hat transform [5], respectively.…”