Earticle

This paper presents a multi-band wavelet image content authentication scheme for satellite images by incorporating the principal component analysis (PCA). The proposed scheme achieves higher perceptual transparency and stronger robustness. Specifically, the developed watermarking scheme can successfully resist common signal processing such as JPEG compression and geometric distortions such as cropping. In addition, the proposed scheme can be parameterized, thus resulting in more security. That is, an attacker may not be able to extract the embedded watermark if the attacker does not know the parameter. In an order to meet these requirements, the host image is transformed to YIQ to decrease the correlation between different bands, Then Multi-band Wavelet transform (M-WT) is applied to each channel separately obtaining one approximate sub band and fifteen detail sub bands. PCA is then applied to the coefficients corresponding to the same spatial location in all detail sub bands. The last principle component band represents an excellent domain for inserting the water mark since it represents lowest correlated features in high frequency area of host image. One of the most important aspects of satellite images is spectral signature, the behavior of different features in different spectral bands, the results of proposed algorithm shows that the spectral stamp for different features doesn't tainted after inserting the watermark..

Image registration is a vital problem in medical imaging. It has many potential applications in clinical diagnosis (Diagnosis of cardiac, retinal, pelvic, renal, abdomen, liver, tissue etc disorders). It is a process of aligning two images into a common coordinate system thus aligning them in order to monitor subtle changes between the two. Registration algorithms compute transformations to set correspondence between the two images the purpose of this paper is to provide a comprehensive review of the existing literature available on Image registration methods. We believe that it will be a useful document for researchers longing to implement alternative Image registration methods for specific applications.

Medical Image segmentation deals with segmentation of tumor in CT and MR images for improved quality in medical diagnosis. Geometric Vector Flow (GVF) enhances the concave object extraction capability. However, it suffers from high computational requirement and sensitiveness to noise. This paper intends to combine watershed algorithm with GVF snake model to reduce the computational complexity, to improve the insensitiveness to noise, and capture range. Specifically, the image will be segmented firstly through watershed algorithm and then the edges produced will be the initial contour of GVF model. This enhances the tumor boundaries and tuning the regulating parameters of the GVF snake mode by coupling the smoothness of the edge map obtained due to watershed algorithm. The proposed method is compared with recent hybrid segmentation algorithm based on watershed and balloon snake. Superiority of the proposed work is observed in terms of capture range, concave object extraction capability, sensitivity to noise, computational complexity, and segmentation accuracy.

In this paper the edge-directed error diffused digital halftoning in noisy media is analyzed. It is known that there occurs error in transmitting data through a communication channel due to addition of noise, generally additive white Gaussian noise (AWGN). The proposed work employs Steerable stochastic error diffusion (SSED) approach, a hybrid scheme that utilizes the advantages of Steerable filter for edge detection purpose and five neighbor stochastic error diffusion (FNSED) approach for error diffusion purpose. Analysis of different methods of edgedetection and error diffusion in the presence of zero mean AWGN with different values of variance has also been made. The results show that the proposed scheme produces halftones of better quality in the presence of even large value of noise variance compared to other approaches of edge detection and error diffusion.

In this paper we present an adaptive multilevel total variational (TV) method for image denoising which utilizes TV partial differential equation (PDE) models and exploits the multiresolution properties of wavelets. The adaptive multilevel TV method provides fast adaptive wavelet-based solvers for the TV model. Our approach employs a wavelet collocation method applied to the TV model using two-dimensional anisotropic tensor product of Daubechies wavelets. The algorithm inherently combines the denoising property of wavelet compression algorithms with that of the TV model, and produces results superior to each method when implemented alone. It exploits the edge preservation property of the TV model to reduce the oscillations that may be generated around the edges in wavelet compression. In contrast with previous work combining TV denoising with wavelet compression, the method presented in this paper treats the numerical solution in a novel way which decreases the computational cost associated with the solution of the TV model. We present a detailed description of our method and results which indicate that a combination of wavelet based denoising techniques with the TV model produces superior results, for a fraction of the computational cost.

Classification of iris templates based on their texture patterns is one of the most effective methods in iris recognition systems. This paper proposes a novel algorithm for automatic iris classification based on fractal dimensions of Haar wavelet transforms is presented. Fractal dimensions obtained from multiple scale features are used to characterize the textures completely. Haar wavelet is applied in order to extract the multiple scale features at different resolutions from the iris image. Fractal dimensions are estimated from these patterns and a classifier is used to recognize the given image from a data base. Performance comparison was made among different classifiers.

Ultrasound imaging is a widely used and safe medical diagnostic technique, due to its noninvasive nature, low cost and capability of forming real time imaging. However the usefulness of ultrasound imaging is degraded by the presence of signal dependant noise known as speckle. The speckle pattern depends on the structure of the image tissue and various imaging parameters. There are two main purposes for speckle reduction in medical ultrasound imaging (1) to improve the human interpretation of ultrasound images (2) despeckling is the preprocessing step for many ultrasound image processing tasks such as segmentation and registration. A number of methods have been proposed for speckle reduction in ultrasound imaging. While incorporating speckle reduction techniques as an aid for visual diagnosis, it has to keep in mind that certain speckle contains diagnostic information and should be retained. The objective of this paper is to give an overview about types of speckle reduction techniques in ultrasound imaging

In this paper, we propose a novel video retrieval system using Generalized Eigenvalue Decomposition (GED). The system contains two major subsystems: database creation and database searching. In both subsystems, we propose new methods for shot-feature extraction, feature dimension transformation and feature similarity measuring base on GED. Experimental results confirm the effectiveness of our proposed system.

The selection of “proper similarity measure” of color histograms is an essential consideration for the success of many methods. The Histogram Quadratic Distance Measure (HQDM) is a metric distance. Till today, this method is supposed to be the better choice, But it holds a disadvantage that it can compute the cross similarity between all elements of histograms. Therefore, computationally it is more expensive. This paper proposes a method that is known as Integrated Histogram Bin Matching (IHBM) which is also a metric method, and overcomes the disadvantages of the HQDM. The proposed IHBM first matches the closest Histogram Bin Pair according to the distance matrix determined from color histograms, which satisfies the Monge condition. After matching histogram bins, the similarity measure is computed as a weighed sum of the similarity between histogram bin pairs, with weights determined by the matching scheme. The proposed IHBM is experimented on 1000 color images and results are compared with the existing methods.

The resolution of multy variable complex problems such as the multy speaker speech recognition and independently of context, requires the application of neural structures. One tool which proves to be powerful in the classification field, is the kohonen map called SOM. This map is characterized by the representation of static data. Thus, we ought to enrich the intelligibility and the performance of this model in order to reach what biology imposes by handling a kind of logical pile "memory" with the introduction of temporal context which realise feedbacks that integrate respectively the leaky integrators concept for the TKM. The recurrent leaky integrators idea for the recurrent SOM ‘RSOM’ in an improvement of the TKM. More recently, the principle of self refer for the recursive SOM. In other case, we are introducing the possibility to obtain hybridization with GA in an attempt to reach the natural evolution of the human thought as regards to recognition.

We introduce the development of animation stimuli for theory of mind (ToM) in magnetoencepalography (MEG). We will discuss apparatus for presenting animation stimuli and a technical problem like an eye movement signal generated from following triangles in the animations, and its rejection using independent component analysis (ICA). With the ToM animations and the apparatus, we conducted MEG measurements for 8 normal controls and 6 schizophrenic patients. We present a preliminary assessment result for the developed animation stimuli as a tool for ToM test, which has been obtained by scoring in the followingup interview after the MEG measurement.