Image enhancement techniques on Indian license plate localized image for improved character segmentation

In Intelligent Transportation System, License plate recognition system is one of the most important parts and the license plate localization is the key part of it. It affects the latter phase of the character segmentation and recognition directly. During License Plate Localization phase image enhancement technique is applied to solve the problems such as noise, low contrast, shadow etc in the LP image. Image enhancement techniques are also needed to improve skew correction and segmentation. Here a new approach of edge enhancement for enhancing license plates to improve SNR in detection of License Plate after improving the contrast by using Contrast Limited Adaptive Histogram Equalization is introduced. Presence of nonuniform illumination and shadow in LP image hampers LP localization accuracy which is addressed by the MACOA Image Pre-processing algorithm. This technique improves the contrast by using two thresholds, one Adaptive threshold and other Otsu threshold. Adaptive thresholding technique is used for non uniform noised or half shadowed images, while Otsu threshold is used to attenuate uniformly distributed noise.