Guoan Yang

Contourlet filter design based on chebyshev best uniform approximation

The contourlet transform can deal effectively with images which have directional information such as contour and texture. In contrast to wavelets for which there exists many good filters, the contourlet filter design for image processing applications is still an ongoing work. Therefore, this paper presents an approach for designing the contourlet filter based on the Chebyshev best uniform approximation for achieving an efficient image denoising applications using hidden Markov tree models in the contourlet domain. Here, we design both the optimal 9/7 wavelet filter banks with rational coefficients and new pkva 12 filter. In this paper, the Laplacian pyramid followed by the direction filter banks decomposition in the contourlet transform using the two filter banks above and the image denoising applications in the contourlet hidden Markov tree model are implemented, respectively. The experimental results show that the denoising performance of the test image Zelda in terms of peak signal-to-noise ratio is improved by 0.33 dB than using CDF 9/7 filter banks with irrational coefficients on the JPEG2000 standard and standard pkva 12 filter, and visual effects are as good as compared with the research results of Duncan D.-Y. Po and Minh N. Do.

Extensible JPEG2000 image compression systems

The purpose of this paper is to presents an approach to extend the functionality and the application fields of the JPEG2000 image coding systems by choosing various wavelet kernels such as CDF 9/7, LT 5/3, BT 7/5a, BT 7/5b, standard 7/5, Antonini 7/5, LS 9/7 etc. This paper gives a general procedure for extending the JPEG2000 coding system by using 7/5 wavelet which includes 7/5 wavelet lifting scheme, quantization algorithm, EBCOT coding and their optimization design. Experimental results show that the compression performances of the extensible image coding system for various image properties, and various needs and requirements of the image compression are always excellent by choosing appropriate wavelet kernel. The image compression performances of the 7/5 wavelet kernel in extended JPEG2000 coding system very close to CDF9/7 wavelet kernel, and 7/5 wavelet filter have rational coefficients, so that reduces computational complexity and are suitable for implementation via VLSI than CDF 9/7 wavelet kernel

A novel optimization design approach for Contourlet directional filter banks

A Contourlet transform, an expansion of a wavelet transform, is a double filter bank structure composed of Laplacian Pyramid and directional filter banks. Several wavelet filters of preferable performance have been developed for wavelet transforms, e.g. CDF (Cohen, Daubechies and Feauveau) 9/7 filter. However, there is still only a limited number of wavelet filters applicable for Contourlet transforms. Therefore, it has become an urgent issue to find effective contourlet filters and design methods in the field of multiscale geometric analysis. In order to design a new directional filter bank for Contourlet transforms, this paper uses parametric modeling to obtain a novel PKVA (See-May Phoong, Chai W. Kim, P. P. Vaidyanathan, and Rashid Ansari) filter, by first implementing Chebyshev best uniform approximation, and then reaching the optimal solution by means of Parks-McClellan algorithm. Using Brodatz standard texture image database for test images, and using image denoising treated with hidden Markov tree (HMT) models in the Contourlet domain, the optimal PKVA filter was obtained on the basis of the peak signal to noise ratio (PSNR) maximum criterion with human visual properties considered. Experiment results show that the image denoising performance of our filter is better than that of Po and Do’s. The PSNR obtained from the experiment is 1.011449 higher than that of Po and Do’s in average. Therefore, Contourlet transforms using the proposed PKVA filter as DFB can ensure that the local error in images is of a uniform minimum value, and that good overall visual effect can be achieved.

Multi-Layer Perceptron including glial pulse and switching between learning and non-learning

A glia is a nervous cell which is existing in a brain. This cell changes a Ca2+ concentration. This ion affects a neuron membrane potential and it is propagated to the neighboring glia. Moreover, the Ca2; directly affects the human memory by increasing of a D-serine. From these functions, we propose a Multi-Layer Perceptron (MLP) including glial pulse and switching between a learning and non-learning. In this method, the neurons in the hidden-layer received the pulse from connected glias. The pulse is generated depending on the neuron outputs and it is propagated to the neighboring glias and neurons. Moreover, the neurons are separated to some groups. Each group periodically switches a learning term and a non-learning term. Each group starts the learning term having a small lag each other. We consider that a performance of the MLP improves by two different methods influencing each other. By two simulations, we confirm that the MLP obtains the high solving ability by using our methods.

A Novel 9/7 Wavelet Filter banks For Texture Image Coding

This paper proposes a novel 9/7 wavelet filter bank for texture image coding applications based on lifting a 5/3 filter to a 7/5 filter, and then to a 9/7 filter. Moreover, a one-dimensional optimization problem for the above 9/7 filter family is carried out according to the perfect reconstruction (PR) condition of wavelet transforms and wavelet properties. Finally, the optimal control parameter of the 9/7 filter family for image coding applications is determined by statistical analysis of compressibility tests applied on all the images in the Brodatz standard texture image database. Thus, a new 9/7 filter with only rational coefficients is determined. Compared to the design method of Cohen, Daubechies, and Feauveau, the design approach proposed in this paper is simpler and easier to implement. The experimental results show that the overall coding performances of the new 9/7 filter are superior to those of the CDF 9/7 filter banks in the JPEG2000 standard, with a maximum increase of 0.185315 dB at compression ratio 32:1. Therefore, this new 9/7 filter bank can be applied in image coding for texture images as the transform coding kernel.

Improvement of learning performance of multi-layer perceptron by two different pulse glial networks

A glia is the most number of nervous cells in a brain. The glia is investigated in a medical field, because the glia correlates to neuron works and composes a human cerebration. We consider that the glia function can be applied to an artificial neural network. In this study, we propose the Multi-Layer Perceptron (MLP) with the two different pulse glial networks. The proposed MLP has the glial network which is inspired from biological functions of the glia. One neuron is connected with two glias. Two glias generate the pulse depending on the output neurons. One glia connects the neuron for increasing the output of neuron. On the other hand, the glia connects the neuron for decreasing the output of neuron. Both glias composes the glial networks. These effects are propagated into the networks. The glial effects become complexity and affects the MLP learning performance. By the computer simulation, we confirm that the learning performance of the proposed MLP is better than the conventional MLP.

A novel image fusion algorithm using an NSCT and a PCNN with digital filtering

ABSTRACT Image fusion is an important task in both image processing and computer vision research that use multisensor processing and multiscale analysis. This paper proposed a novel image fusion algorithm using a nonsubsampled contourlet transform (NSCT) and a pulse-coupled neural network (PCNN) with digital filtering. First, we decomposed two original images into a low-frequency and a series of high-frequency subband coefficients based on the NSCT and repeated that step for the next low-frequency subband. Second, each low-frequency subband coefficient in different levels in the frequency domain for both images was duplicated, and then these low-frequency subband coefficients of different levels from two different images were processed through a Laplacian filter and an average filter. The Laplacian filter can improve the performance of both edge and texture representation; the average filter can implement image smoothing for creating a superior reconstruction of an image via the low-frequency subband coefficients of the frequency domain in image processing. Moreover, the coupling coefficients from different images were fused by using the PCNN. Finally, reconstructed a fused image based on low- and high-frequency subband coefficients in different scales and directions using the inverse NSCT. Experimental results show that the proposed algorithm is superior to state-of-the-art conventional image fusion algorithms.

Principle component analysis based hyperspectral image fusion in imaging spectropolarimeter

Image fusion is of great importance in object detection. A PCA based image fusion method was proposed. A pixel-level average method and a wavelet-based methods have been implemented for a comparison study. Different performance metrics without reference image are implemented to evaluate the performance of image fusion algorithms. It has been concluded that image fusion using PCA based method showed better performance.

Wavelet transform based defringing in interference imaging spectrometer

The constructive and destructive fringe-like pattern (FP) introduced by the fringing effects is a universal phenomenon emerging in the imaging system using the back-illuminated CCD. Generally, the flat fielding or modeling based methods were applied to suppressing the FP and featured as time-consuming, duplicated, and hardware-based. In this paper, a method based on the wavelet transform was proposed for the interferogram processing in interference imaging spectrometer. An artificial interferogram construction method was developed and utilized to evaluate the quality of the reconstructed interferogram. The performance of defringing was significantly determined by the wavelet decomposition. Through numerical simulation, 4 wavelets were selected out of 50 typical wavelets; the decomposition levels with better performance were determined. The feasibility of the defringing and performance evaluation methods were verified by the simulation and practical experiments. It provides us with a software-based, time-saving, without prior knowledge, automatic approach for defringing.