Introduction: With the promotion and application of digital imaging technology in the medical domain, the amount of medical images has grown rapidly. However, the commonly used compression methods cannot acquire satisfying results. Methods: In this paper, according to the existed and stated experiments and conclusions, the lifting step approach is used for wavelet decomposition. The physical and anatomic structure of human vision is combined and the contrast sensitivity function (CSF) is introduced as the main research issue in human vision system (HVS), and then the main designing points of HVS model are presented. On the basis of multi-resolution analyses of wavelet transform, the paper applies HVS including the CSF characteristics to the inner correlation-removed transform and quantization in image and proposes a new HVS-based medical image compression model. Results: The experiments are done on the medical images including computed tomography (CT) and magnetic resonance imaging (MRI). At the same bit rate, the performance of SPIHT, with respect to the PSNR metric, is significantly higher than that of our algorithm. But the visual quality of the SPIHT-compressed image is roughly the same as that of the image compressed with our approach. Our algorithm obtains the same visual quality at lower bit rates and the coding/decoding time is less than that of SPIHT. Conclusions: The results show that under common objective conditions, our compression algorithm can achieve better subjective visual quality, and performs better than that of SPIHT in the aspects of compression ratios and coding/decoding time.

Systems with a single sensor (radar or infrared image sensor) have their limitations in target recognition and tracking. A system with multi-sensors can fuse data from different sensors to overcome the limitations in the system with a single sensor, it can make use of the complement and redundancy of data from different sensors to improve the precision of target recognition and tracking and the robustness and reliability. In our system for target recognition and tracking, radar and infrared image sensors are used. As a radar sensor in our system can provide with the information of the distance and direction of the target (not the image of the target), data fusion is implemented only at characteristic level and at decision level. For data fusion at characteristic level, characteristics of a target obtained from radar can be used in the IR Image-based subsystem to improve the ability of object recognition, and vice versa. The process of target recognition based on IR image analysis is composed of image enhancement, image segmentation and recognition of segmented objects. For image enhancement, median-filter, histogram equalization, wavelet transformation and canny-operator are used. A median-filter is used for the elimination of punctate noises in an IR image. The grayness of a pixel in an IR image is determined by the grayness of its neighbors. Histogram equalization is used for the improvement of the contrast of an IR image. Multi-scale pyramidal wavelet transformation is used to delete unexpected edges and improve the continuity of edges in an IR image. Canny operator based on Gauss-function is used for edge detection, an IR image is transformed into a binary image based on the adaptive threshold. According to area (number of pixels) of segmented objects, the recognition of segmented objects is divided into two classes: recognition of dot targets and area targets. Rule-based reasoning is used to deal with the recognition of dot targets; a classifier based on neural network is used to deal with the recognition of area targets. The models for target recognition are extracted by data mining. The rules for the recognition of dot targets are extracted by decision trees. A neural network for the recognition of area targets is constructed by multi-layer preceptron and trained by training examples. The following characteristics of target are used as inputs of the neural classifier: •distance of the target obtained from the radar-based subsystem. •area of the target in the IR image, the variation of areas of the target in the consecutive two IR images. •the mean grayness of pixels of the target. •the variation of centers of the target in the consecutive two IR images. •the topological shape of the target (seven moment invariants Ψ1,Ψ2,...,Ψ7, the number of forks in the frame extracted.) •the direction of the target motion predicated by radar and the relation of angles among the axes of the missile, Radar and IR image sensor. After data fusion at characteristic level, a true target is recognized by the radar-based subsystem and the IR image-based subsystem. Based on these two decisions, data fusion at decision level is to make a final decision of target tracking. a factor "decision certainty" is introduced to realize data fusion at decision level, which represents the relative certainty of decisions of target tracking.

Fast computation of Zernike moments from normalized geometric moments has been developed in this work. The computation is multiplications free and only additions are needed to generate Zernike moments. Geometric moments have been generated using Hatamian's filter up to high orders by a very simple and straightforward computation scheme. Other kinds of moments (i.e., Legendre, pseudo Zernike. etc.) can be computed using the same algorithm after giving the proper transformations that state their relation to geometric moments. Proper normalizations to geometric moments are necessary so that it can be used in the efficient computation of Zernike moments. To ensure fair comparisons, recursive algorithms are used to generate Zernike polynomials and any other coefficients. Computational complexity model and the test programs show that the speed up factor of the proposed algorithm is superior with respect to other fast and/or direct computations. To our knowledge, it is the first time that Zernike moments can be computed in real time rates which encourages the use of Zernike moments features in different image retrieval systems that supports huge database such as XM experimental model stated for MPEG-7 experimental core. It is concluded that choosing direct computation would be impractical.

Automatic identification of landmarks in cephalometry is very important and useful for orthognathic surgery. In this paper, a computerized automatic cephalometric analysis system (CACAS) based on image processing is presented. For original X-ray image, median filtering and histogram equalization is used to improve image quality. The edge of a X-ray image is detected by wavelet transform and Canny filter. Seventeen landmarks in cephalometry are successfully identified by knowledge-based edge tracing and changeable template. Seventy three measurements based on distances, angles, ratios among landmarks are computed automatically. The reliability of landmarks and the validity of measurements are compared between automatic and manual operation. The values of measurements by CACAS are preciser and more reliable, the mean error for linear measurements is less than 0.9mm; the mean error for angular measurements is less than 1.2dg. The rate of validity is over 80% even if the image quality is poor. For an image with high signal to noise ratio, the rate of validity of landmarking and measurements by the CACAS system is over 90%.

In this paper, we present illumination-affine invariant methods based on affine moment normalization techniques, Zernike moments, and multiband correlation functions. The methods are suitable for the illumination invariant recognition of 3D color texture. Complex valued moments (i.e., Zernike moments) and affine moment normalization are used in the derivation of illumination affine invariants where the real valued affine moment invariants fail to provide affine invariants that are independent of illumination changes. Three different moment normalization methods have been used, two of which are based on affine moment normalization technique and the third is based on reducing the affine transformation to a Euclidian transform. It is shown that for a change of illumination and orientation, the affinely normalized Zernike moment matrices are related by a linear transform. Experimental results are obtained in two directions; the first is used with textures of outdoor scenes while the second test is performed on the well-known CUReT texture database. Both tests show high recognition efficiency of the proposed recognition methods.