Search

Various basic image enhancement techniques of License Plate Recognition are discussed and simulated with MATLAB. Through a lot of experiments, an improved image enhancement method is proposed by combining gray-level transformation and median filtering. The method can efficiently avoid interfere and enhance the contrast of image and obtain satisfying effects.

In the paper, degradation and restoration model is introduced. Image restoration method using inverse filtering and using wiener filtering are studied and implemented. A new method of image restoration is proposed by combining histogram equalization and median filtering. Comparing three methods by MATLAB simulation, the results show that the new method can effectively restore degradation image with comparatively high restoration efficiency.

Multi-object tracking has been a challenging topic in computer vision. A Simple and efficient moving multi-object tracking algorithm is proposed. A new tracking method combined with trajectory prediction and a sub-block matching is used to handle the objects occlusion. The experimental results show that the proposed algorithm has good performance.

Based on the principle of the image enhancement, various image enhancement methods are introduced, analyzed and studied. Because image enhancement is closely related to the property of the interested target, the habit of observers and the specific processing goal, the image enhancement is only aimed at the given process goal, too. According to different images, these image enhancement methods are simulated by the MATLAB tools. Through comparing the test results, the results show that different methods will give different effects. Without a common image enhancement method is suitable for various occasions.

A real-time predicting trace algorithm is proposed using the process of target tracking, the target’s position in the next frame is estimated by the iterative fitting. Making the predict position as the center, the target is searched within a certain window and the target tracking is accomplished. The target’s trajectory is obtained by fitting the target’s positions using curve. The experiments show that the algorithm reduces the matching complexity, improves the tracking speed and tracking precision.

Image fusion algorithm is very important in image fusion process. Image fusion algorithm based on pyramid decomposition was reviewed in this paper. Pyramid decomposition algorithm mainly includes Contrast pyramid, Gradient Pyramid, Laplacian Pyramid and Ratio Pyramid. The fusion algorithms based on pyramid decomposition were respectively applied in multi-focus images, advantage and disadvantage were summarized and application was given. Fusion results were given by MATLAB simulation. Objective evaluation index including of mean, standard deviation, entropy and average gradient was calculated in this paper. Image fusion algorithm should be selected according to the information extracted and the aim of fusion.

Occlusion is a difficult problem to be solved in the process of target tracking. In order to solve the problem of occlusion, a new tracking method combined with trajectory prediction and multi-block matching is presented and studied,and a mathematical model of trajectory prediction of moving target is established in polar coordinates and verified through some experiments. The experimental results show that the new tracking method can be better to trace and forecast the moving target under occlusion.

Contrast pyramid algorithm is put forward in this paper. The human visual system is sensitive to contrast information of image, so contrast pyramid algorithm would outstanding the contrast of image. The algorithm consists of creation process of Gauss Pyramid, the process of creating contrast Pyramid and reconstruction process of clear image. Simulation by MATLAB was completed in multi-focus image, multi-modality image and color image. Objective evaluation index such as mean, standard deviation, entropy and average gradient was calculated Simulation results and index show that the contrast pyramid algorithm has advantage of projecting the contrast of image, especially in color image fusion.

Pixel level image fusion algorithm is one of the basic algorithms in image fusion, which is mainly divided into time domain and frequency domain algorithm. The weighted average algorithm and PCA (principal component analysis) are popular algorithms in time domain. Pyramid algorithm and wavelet algorithm are usually used to fuse two or multiple images in frequency domain. In this paper, pixel level image fusion algorithm was summarized, including of operation, characteristics and application etc. MATLAB simulation shows that effect of frequency domain algorithm is better than time domain algorithm. Evaluation criteria mainly refer to entropy, cross entropy, the mean and standard deviation etc. Evaluation standard is the reference of fusion effects, different evaluation criteria could be selected according to different fused image and different fusion purpose.

Threshold technique is one of the important techniques in image segmentation. Various thresholding segmentation techniques such as histogram, grayscale expectations, Otsu, maximum entropy and iterative are studied and compared by using Matlab 7.0. Experimental results show that the iterative method can perform well and get a better result than the other thresholding segmentation methods.

The block-division based segmentation algorithm is raised in this paper, which overcomes the shortcomings of the whole and single threshold method. Each block is processed with two-value segmentation algorithm, and finally, all blocks are combined for image recovery. In order to evaluate the performance of block-division based segmentation algorithms, some experiments are carried out by using Matlab 7.0. Experimental results show that block-division based segmentation algorithms can perform well and get a better result than the other threshold segmentation algorithms.

Threshold-based segmentation algorithms are introduced and simulated. In order to evaluate the performance of various threshold segmentation algorithms, the quantitative experimental criterions are introduced and applied. And through large experiments by using MATLAB, threshold segmentation algorithms are evaluate with uniformity measure (UM), shape measure (SM) and gray-level contrast (GC). The effect of image segmentation is described by using the average value of three experimental criterions (UM, SM and GC).

An improved correlation matching algorithm is proposed in order to overcome some shortcomings of detecting the position of object accurately. A tracking algorithm with normalized cross correlation is introduced. In order to enhance the match speed, we have adopted pyramid search algorithm. The experimental results show that the algorithm has characteristics including automatic recognition of the object; permitting tracking and prediction when the object become shaded; the algorithm makes adaptive decision of varied object during the process of tracking.

Feature extraction was a critical stage of image retrieval. For the characterization of the contents of an image could be directly affected by feature extraction. The single feature of images could not fully express images content information, make that the precision of Content-Based Image Retrieval (CBIR) be limited. To overcome the short points, texture information was used in the CBIR. The image color feature and texture feature were comprehensive extracted. And an image retrieval system was developed under MATLAB platform. The new method was simulated and verified by MATLAB.

Content-Based Image Retrieval (CBIR) system existed a gap between high-level concepts and low-level features. As an effective solution, the Relevance Feedback (RF) technique has been used on many CBIR systems to improve the retrieval precision. In order to further improve convergence speed and retrieval accuracy, a novel relevance feedback method was proposed. According to feedback from user, image feature was weighted and adjusted in the novel method.

Image fusion method based on image multi-scale decomposition is a kind of fusion method of multi-scale, multi-resolution image fusion. Its fusion process realize in different scales and different spatial resolution and different decomposition layer. Fusion effects based on multi-scale decomposition algorithm can obviously improve compared to the simple fusion methods. Among the fusion algorithm based on multi-scale to pixel-level image fusion, Pyramid decomposition and wavelet decomposition are widely used, the original image is decomposed to convert the original image domain to transform domain, and then, fusion process realized in transform domain according to certain rules of image fusion. Basic principle of fusion process was introduced in detail in this paper, and pixel level fusion algorithm at present was summed up. Simulation results on fusion are presented to illustrate the proposed fusion scheme. In practice, fusion algorithm was selected according to imaging characteristics being retained.

Image fusion method based on the non multi-scale take the original image as object of study, using various fusion rule of image fusion to fuse images, but not decomposition or transform to original images. So, it can also be called simple multi sensor image fusion methods. Its advantages are low computational complexity and simple principle. Image fusion method based on the non multi-scale is currently the most widely used image fusion methods. The basic principle of fuse method is directly to select large gray, small gray and weighted average among pixel on the source image, to fuse into a new image. Simple pixel level image fusion method mainly includes the pixel gray value being average or weighted average, pixel gray value being selected large and pixel gray value being selected small, etc. Basic principle of fusion process was introduced in detail in this paper, and pixel level fusion algorithm at present was summed up. Simulation results on fusion are presented to illustrate the proposed fusion scheme. In practice, fusion algorithm was selected according to imaging characteristics being retained.

Image fusion algorithm based on principal component analysis (PCA) was proposed in this paper. The algorithm make use of the characteristics that the principal component decomposition can retain the main information of the original data, it get covariance matrix, eigenvalue and eigenvector of covariance matrix from the source image. Then we can get the weighted coefficient and fused image with the help of eigenvalue and eigenvector. Simulation result shows that the better image quality is obtained in the proposed algorithm.