A Medical Image Segmentation Method Based on SOM and Wavelet Transforms

Image segmentation plays a crucial role in many medical imaging applications and is an important but inherently difficult problem. This paper discusses the method that classifies unsupervised image using a Kohonen self-organizing map neural network. This method has two problems： training time of the network is too long and the classified result and quantity are much easily influenced by the noise of image. Two-dimensional Discrete Wavelet Transforms （DWT） decompose MRI image into the small size and denoise approximation images. Kohonen self-organizing map neural network is trained with approximation image, then trained neural network classify pixels of original image. Training time of the network is markedly decreased and the classified quality influenced by the noise of image is markedly reduced. The technique presented here has shown a very encouraging level of performance for the problem of segmentation in MRI image of the head.     

A Line Extraction Algorithm for Hand Drawings

This paper presents an algorithm for extracting lines from hand drawings.It starts from contour pixel tracing,fits them into contour segments,and then extracts skeleton lines from the contour segments.The algorithm finds all contours in one scan of the input matrix without detecting and marking multiple pixels.In line extraction,the method Elastic Contour Segment Tracing is proposed which extracts lines by referring to the contour segments at both sides,overcoming noise and passing through blotted areas by fitting and extrapolation. Experiments on free hand mechanical drawings,sketches,letter/numerals,as well as Chinese characters are carried out and satisfactory results are achieved.     

An Adaptive Image Watermarking Algorithm Based on HMM in Wavelet Domain

An adaptive image watermarking algorithm based on HMM in wavelet domain is pro- posed.The algorithm is abstracted as follows:1)the vector HMM model is employed to describe the statistical characteristic of image wavelet coefficients and the resulting HMM based detector achieves significant improvements in performance compared to the conventional correlation detector; 2)adaptive watermark embedding based on HVS analysis;3)a novel embedding strategy which is optimized for the HMM tree structure is adopted;4)the strategy of dynamical threshold is applied in watermark detection.High robust results are achieved against Stirmark attacks,such as JPEG compression,adding noise,median cut and filter.     

An Improved Attention Parameter Setting Algorithm Based on Award Learning Mechanism

The setting of attention parameters plays a role in the performance of synergetic neural network based on PFAP model. This paper first analyzes the attention parameter setting algorithm based on award-penalty learning mechanism. Then, it presents an impro     

A Note on Polynomials Based Image Registration

It is shown that the polynomials based image registration, which is widely used in remote sensing field, does not have a sound mathematical basis. In fact, there seems no theoretical basis for the polynomials based transform to outperform the affine transformation, a much simpler one, in image registration. If the transformation functions are polynomials of order n, the corresponding scene is shown to be in general the intersection of two curved surfaces of order n 1, in other words, a space curve. In some special cases, the scene is approaching to a plane. To our knowledge, such results did not appear in the literature previously.     

A Fractal Compression Algorithm Based on Collage Distance Estimating and Compensating

A new fractal image compression scheme based on collage distance is explained, which can provide of the scheme two different compression codes containing their own unique collage distance sets and different types of similar transforms. The analysis and applications of the scheme indicate that it can be adopted as a suitable alternative for balancing between the distortion measure and compression ratio occurring in ordinary fractal compression method.     

Digital Image Watermarking Based on Discrete Wavelet Transform

This paper aims at digital watermark which is a new popular research topic recently,presents some methods to embed digital watermark based on modifying frequency coefficients in discrete wavelet transform(DWT) domian,Fist,the,the present progress of digital watermark is briefly introduced;after that,starting from Pitas‘s method and discarding his pseudo random number method,the authors use a digital image scrambling technology as preprocessing for digital watermarking ,Then the authors discuss how to embed a 1-bit digital image as watermark in frequency domain.Finally another digital watermarking method is given in which3-D DWT is used to transform a given digtial image .Based on the experimental results ,it is shown that the proposed methods are robust to a large extent.     

Diagnosis and Localization of Pipeline Leak Based on Fuzzy Decision-making Method

A leak detection plays a key role in the overall integrity monitoring for a oil pipeline system.A fuzzy decision-making approach to pipeline leak localization is proposed in this paper. The two main methods,pressure gradient localization and negative pressure wave localization,are combined with fuzzy logical decision-making method to form a novel fault diagnosis scheme.The combination scheme can improve the precision of localization.An application example,14km long oil pipeline leak detection and localization,is illustrated.This method is compared with others through practical experiments and its validity is confirmed by the results.     

Deductive Fault Simulation Algorithm Based on Fault Collapsing

The true value simulation is necessary in the critical path tracing fault simulation algorithm.The critical and non-critical inputs can be known after the number of controlling and non-controlling inputs and the criticality of output of every gate are determined.Single output region(SOR)is defined for non-critical lines,so many other non-critical lines can be obtained before fault simulation.The deductive fault simulation algorithm is used to compute the fault list for every possible critical line from bottom to top,which can greatly decrease the length of fault list and simulation time.The cross-sectios is defined to reduce the storage space.The experimental results are given at the end of the paper.     

Multicast Routing Optimization Algorithm with Bandwidth and Delay Constraints Based on GA

Most of the multimedia applications require strict QoS guarantee during the communication between a single source and multiple destinations. This gives rise to the need for an efficient QoS multicast routing strategy. Determination of such QoS-based optimal multicast routes basically leads to a multi-objective optimization problem, which is computationally intractable in polynomial time due to the uncertainty of resources in networks. This paper proposes a new multicast routing optimization algorithm based on Genetic Algorithms, which find the low-cost multicasting tree with bandwidth and delay constraints. The simulation results show that the proposed algorithm is able to find a better solution, fast convergence speed and high reliability. It can meet the real-time requirement in multimedia communication networks. The scalability and the performance of the algorithm with increasing number of network nodes are also quite encouraged.     

Emotional Feature Extraction Method Based on the Concentration of Phoneme Influence for Human–Robot Interaction

Depending on the emotion of speech, the meaning of the speech or the intention of the speaker differs. Therefore, speech emotion recognition, as well as automatic speech recognition is necessary to communicate precisely between humans and robots for human–robot interaction. In this paper, a novel feature extraction method is proposed for speech emotion recognition using separation of phoneme class. In feature extraction, the signal variation caused by different sentences usually overrides the emotion variation and it lowers the performance of emotion recognition. However, as the proposed method extracts features from speech in parts that correspond to limited ranges of the center of gravity of the spectrum (CoG) and formant frequencies, the effects of phoneme variation on features are reduced. Corresponding to the range of CoG, the obstruent sounds are discriminated from sonorant sounds. Moreover, the sonorant sounds are categorized into four classes by the resonance characteristics revealed by formant frequency. The result shows that the proposed method using 30 different speakers' corpora improves emotion recognition accuracy compared with other methods by 99% significance level. Furthermore, the proposed method was applied to extract several features including prosodic and phonetic features, and was implemented on 'Mung' robots as an emotion recognizer of users.     

Topography Image Segmentation Based on Improved Chan-Vese Model简

Aiming to solve the inefficient segmentation in traditional C-V model for complex topography image and time-consuming process caused by the level set function solving with partial differential, an improved Chan-Vese model is presented in this paper. With the good per）brmances of maintaining topological properties of the traditional level set method and avoiding the numerical so- lution of partial differential, the same segmentation results could be easily obtained. Thus, a stable foundation tbr rapid segmenta- tion-based on image reconstruction identification is established.