Hybrid Method for Elimination of Uneven Illumination from Camera-based Document Images

In this paper, is addressed the issues of uneven lighting and complex background of the camera-based document image using hybridization of new split and merge method. The input image is divided into four uniform size sub-images, and CLAHE enhancement technique was applied to all four sub-images to rectify noise amplification in each part of input image and then adaptive document binarization operation was used on four sub-images. Then, all four sub section images are merged to get the binarized image with elimination of noises, uneven illumination. Encouraging results are obtained by this method as compared on to other existing methods of Sauvola, Feng and Kasar found in the literature. The comparative analysis is made on collected datasets, as the standard datasets are not available.

Feature extraction for license plate location based on L0-norm smoothing

We propose a simple feature extraction algorithm for license plate location, which can reduce the occurrence of pseudo-licenses significantly. Our scheme arises from a novel L0-norm image smoothing, in which the multiple local textures in the complex backgrounds can be suppressed remarkably without changing the structures and edges of the license objects. Due to this “edgeaware” property, we then combine a feature filtering with an efficient binarized image, a simple multi-scale image analysis algorithm, to remove the potential false license plates. Finally, we extract license plates with a projection method. Experimental results show the proposed method provides a flexible and powerful way to the license plate location in complex backgrounds.

GROUPING METHOD OF IMAGE FRAGMENTS OF ADJACENT DISLOCATION ETCH PITS OF THE SEMICONDUCTOR WAFER

An increase in production volumes of gallium arsenide semiconductor devices determines the need for better control of dislocations of semiconductor wafer. The grouping method of image fragments of adjacent dislocation etch pits of the semiconductor wafer is proposed in the article. Adjacent fragments will be allocated in the pre-binarized image of wafer surface, which contains adjacent fragments of etch pits of dislocation loops after treatment by the described method. Improved methods for determining the loop line width determines the edge line width of etch pits of suspected dislocations, given the variability of their display in the binarized image. The current loop line width is compared to the reference line width of the dislocation loop. The grouping method of image fragments of adjacent dislocation etch pits of the semiconductor wafer defines recovery of loop lines branching, takes into account various options of line adjacency and determines the direction of further recovery of loop line of dislocation etch pits. A step by step description of the method is given.

Improved Binarization Method of QR Code Mobile Terminal

This optimized binarization algorithms for mobile terminals QR code. Bimodal histogram method, OTSU method and homomorphic filtering algorithm were combined to improve multi-threshold method. Experimental results showed that the method to different light image of the environment was able to get a better QR code binarized image, greatly enhancing the success rate of the QR code recognition.

The Research on Locating License Plate of Vehicle Based on Color Conversion and Projection

In the research field in automatically recognizing license plate of vehicle, to locate the license plate acts as the key issue. The paper posed the method by graying and binarizing the color image firstly, and then to project the binarized image in both horizontal and vertical directions, as well as to locate the area of license plate according to its geometrical characters maximally. The Test results proved that the method performed well in speed and precision of locating.