The selection of the features vector is crucial, taking direct effect on the accuracy of target recognition. Considering that the airplane has smooth surface and regular geometric shape, this paper chooses the geometric shape feature to describe the target of airplane. These geometric features vector...

In this paper, a novel geometric active contour model for segmenting ultrasound image is presented. A partial differential equation is designed to minimize the dif-ference between the actual and the esti-mated intensity probability distributions of the image regions. The Rayleigh dis-tribution and maximum...

In this paper, a novel fully automatic classification method of breast tumors using ultrasound (US) image is proposed. The proposed method can be divided into two steps: “ROI generation step” and “ROI classification step”. In the ROI generation step, the proposed method fo-cuses on finding a credible...

Raindrops degrade the performance of outdoor vision system, and bring difficulties for objects detection and analysis in image sequence. In this paper, we propose an algorithm for raindrop removal using chromatic based properties in order to improve the data quality and vision effect of image sequence....

In this paper we present a new water-marking attacking algorithm based on the periodic transformation of matrix. By analyzing of the principles of adaptive watermarking embedding in DCT domain, we chose some blocks of the stegoimage to embed the watermarking based on the characteristics of human visual...

In this paper, we proposed a real-time road boundary detection method in com-plex urban road environment. The detec-tion difficulty lies in road wear, both exis-tence of marked and unmarked boundary and low-resolution vision. The idea of the algorithm is to extract the road surface firstly using improved...

An adaptive filtering algorithm based on data mining is proposed for image de-noising when an image is merged by pep-per-and-salt noise. It can adjust the rotat-ing mask size based on the noisy density in the input image so that it raises greatly the computing speed; On the other hand, the algorithm...

Speckle noise is inherent in ultrasound images, and it generally tends to reduce the resolution and contrast, thereby，to degrade the diagnostic accuracy of this modality. Speckle reduction is very im-portant and critical for ultrasound imag-ing. In this paper, we propose a novel ap-proach for speckle...

Breast cancer occurs to over 8% women during their lifetime, and is a leading cause of death among women. Sonography is superior to mammography in its ability to detect focal abnormalities in the dense breasts and has no side-effect. In this paper, we proposed a novel automatic segmentation algorithm...

Hough transform (HT) is a well estab-lished method for curve detection and recognition due to its robustness and in-sensitiveness to noise, and its parallel processing capability. However, HT is quite time-consuming. In this paper, an eliminating particle swarm optimization (EPSO) algorithm is studied...

A neutrosophic set (Ns), a part of neutro-sophy theory, studies the origin, nature, and scope of neutralities, as well as their interactions with different ideational spectra. The neutrosophic set is a power-ful general formal framework that has been recently proposed. However, the neutrosophic set needs...

A neutrosophic set (NS), a part of neu-trosphy theory, studies the origin, na-ture, and scope of neutralities, as well as their interactions with different idea-tional spectra. The neutrosophic set is a general formal framework that has been recently proposed. However, the neutrosophic set needs to be...

Keyword spotting based on large vocabulary continuous speech recognition (LVCSR) is the main researching direction of keyword spotting field. Lattice as the middle result of LVCSR, is often used in this system. But because of its big size, the performance is not efficient as we expect to be. In this...

Image segment is an important step in image processing, pattern recognition and computer vision. Numerous algorithms have been proposed to in this field for last twenty years. However, a generalized segmentation method, especial for noisy image, are not studied greatly. A neutrosophic set (NS), a part...

We introduce Brownian motion into the nonlinear diffusion process for image denoising in this paper. Brownian motion in our work stands for the variation of gray value of a pixel in the form of “random walking” which analogs the irregular and unceasing movement of a small particle. A reflection wall...

An invariant feature extraction method is proposed for banknote classification. The movement of banknote is complex in the channel of financial instruments. The scale is various. The rotation and translation are also to occur. The method of feature extraction is insensitive to the variety of scale, rotation...

We present an algorithm based on chamfer matching for classification and location of thermal imagery in electric substation. We first refine the chamfer algorithm, then we present a new object class classification and location algorithm based on chamfer distance, also we analyze the object class recognition...

A new 3D head-shoulder model based particle filter is presented for finding human head in static images. Edge cues are used as the likelihood function of the proposed particle filter. The positions of head as well as its direction are evaluated simultaneously. At each time step, the proposed algorithm...

Quality of a shape matching technique is correlated to the quality of contour point correspondences obtained. Improving correspondences hence can be useful for better shape matching. In this paper we present a framework that can find salient points correspondences along the contour.The results demonstrate...

Focusing on the problem of low computa-tion efficiency in the process of tracking human 3D motion, the fast tracking algo-rithm for 3D arm motion based on Joint-Chain Motion Model (JCMM) is pro-posed based on the Particle Filter. In our algorithm, via the Joint-Chain Motion Model (JCMM) is defined, the...

This paper proposes a real time driver fatigue monitoring method. Haar algorithm is used to locate the face and detect the eye, histogram-based automatic threshold algorithm is used to extract the eye contour,finally we use the moving average of eyelid distance to decide whether driver is fatigue or...

The main purpose of this paper is to present a new wood defect recognition method. Moreover, the results of our proposed method presented here were good or considerably better than the results obtained by the other two methods. The experimental results show our proposed method has better robust to the...

This paper presents several algorithms that create a classification system based on SVM classifiers grouped in a tree structure. Analysis of similarity between classes allows to reduce of number of used SVM in comparison to DAGSVM method without major reduction of an accuracy. Practical tests of map...

In this paper, we propose a fully automatic segmentation algorithm of masses on breast ultrasound images by using region growing technique. First, a seed point is selected automatically from the mass region based on both textural features and spatial features. Then, from the selected seed point, a region...

This paper presents an adaptive speckle reduction method through diffused growing region filtering based on image segmentation. The main idea is to smooth the speckle regions adaptively and preserve the edge and tissue structure. The criterion of speckle region is defined from a similarity value obtained...

In this paper, we propose a novel background subtraction algorithm, which takes both texture and motion information into account. Texture information is represented by local binary pattern (LBP), which is tolerant of illumination changes and is computational simplicity. Assuming that there is significant...

Face detection plays a very important role in pattern recognition and the precision of face detection directly affects the following results. This paper proposes a fast and precise method of face detection in complex background based on skin color model. Firstly, we extract skin color regions of the...

For research on the proper law of audio-visual speech and biometrics technology, and evaluation of algorithms and sys-tems, we construct a multi-language and multi-view database HIT-AVDB-II with a corpus of various common and special sentences include Chinese and English poems, tongue twister, digits,...

Fuzzy Logic was intruded by Lotfi A. Zadeh in 1965. It is for solving uncertainty and ambiguity problems. Fuzzy logic is a multivalued logic defined in . However, there are a lot of paradoxes, as proposition, can not be described in Fuzzy Logic. In this paper, we will define an extended fuzzy logic and...

Arithmetic coding is an indispensable part of high performance data compression, which theoretically could encode data close to Shannon entropy. In arithmetic coding, probability estimation is an important step, because it determines coding efficiency directly. The paper discusses the probability estimation...

Rain, which is randomly distributed and falls at high speed, behaves complex in video and makes the work of rain detection hard. The improved histogram model is proposed for detection and removal of rain in video. The properties of this model, which are suitable for both stationary and dynamic scenes,...

This paper presents a system - Photo Traveler - for exploring large photo col-lections of a scene with a visceral 3D sense. Based on 3d-reconstruction, Photo Traveler managed to rearrange those pho-tos in 3D scene, enabling the user to ex-plore photos as if looking through the real cameras, and move...

A novel multi-regions based particle filters that effectively deals with occlusion problem in people tracking has been proposed in this paper. After locating multiple key regions, the algorithm uses several nearly independent particle filters (NIPF) to track each region which will be influenced by the...

Evaluation of Risk Area by Myocardial Contrast Echocardiography with a New Computer-aided Method

This paper describes an adaptive frequency domain filtering method to enhance the scale and hour lines as well as the data trace prior to their segmentation and extraction.

The Digital Database for Breast Ultrasound Image (DDBUI) is a database of digitized screen sonography with associated ground truth and some other information. The DDBUI project is a collaborative effort involving the Harbin Institute of Technology and the Second Affiliated Hospital of Harbin Medical...

To investigate the effect of using a novel segment algorithm on radiologists’ sensitivity and specificity for discriminating malignant masses from benign masses using breast ultrasound (BUS) imaging. 510 conventional BUS images acquired from 109 masses were processed by the novel segment algorithm. Five...

A novel approach of binarization for gray images is presented in this paper. The proposed algorithm uses the normalized graph cut(Ncut) as the measure for spectral clustering, and the weighted matrix used in evaluating the graph cuts is based on the gray levels of an image, rather than the image pixels...

In this paper, a novel feature-level Multiple HMMs classifier for lipreading is presented. Firstly, it subdivides mouth images into four non-overlapping subblocks. Then AdaBoost is used to adaptively select optimal Gabor kernels from four subblocks convolved with different Gabor kernel functions and...

This paper presents a regional structures identification model by using remote sensing images, and the method of automatic extracting feature information from remotesensing images, and recognizing regional structures through spatial correlative analysis with gravitation, magnetic information.

In this paper, a correlative structure model based on regional gravity information is generated using back-propagation neural network. The gravity bouguer anomalies of samples are analyzed. The result has been used to process the 1:1,000,000 gravity horizontal derivation maps of the mining areas in the...

Neutrosophic logic is introduced in 1995 as a generalization of fuzzy logic. It includes a new component as neutralities. In this paper, we propose a novel neutronsophic set for SVM inputs and combine it with the reformulated SVM which treats samples differently according to the weighting function. The...

In this paper, the classifiers for land/water and natural land/artificial land combined the texture measures with spectral analysis for remote sensing images have been built. The specific recognition has been designed in order to take advantages of both analyses. Moreover, coastal line development analysis,...

In software testing organizations, an effective knowledge management of testing process is the key to improve the quality of software testing. Knowledge management has different features in software testing. In this paper, a knowledge management model was proposed towards software testing process, which...

A new approach is proposed in our paper to solve the topology mismatch problem in P2P network called Quasi-Chord. Quasi-Chord is in the light of the ideology of Chord. Our model utilizes global network position (GNP) system to coordinate the host on the physical layer and uses the Cantor space filling...

How to effectively distribute service replicas to its n nodes is of much importance in distributed and parallel systems. In many cases, the service replicas are randomly placed, and some service replicas have no relation to any nodes in which they are. So these service replicas are very difficultly accessed,...

This paper describes experiments and the results of Chinese-English cross-lingual subcategorization lexicon acquisition based on a weakly supervised SVM method. Previous similar researches are mostly focused on statistical filtering, and there is no supervised training for the generation of hypotheses....

This paper presents a novel parallel image matching algorithm based on the local entropy difference vector (LEDV). Spatial information is introduced into the definition of image entropy and a thresholding operation is employed to limit the contribution of a mismatching block to the matching result. The...

Unceasingly developed and deeply exploited along with the software system, the variety of middlewares becomes more and more, they mutually affect each other in the complex way. These middlewares, because of the complex of the origin, are not extremely credible. So, before using these middlewares, we...

In view of low precision of the reconstructed image of Electrical Capacitance Tomography (ECT) at present, a new image reconstruction method based on RBF neural network for Electrical Capacitance Tomography is proposed. Adaptive genetic algorithm is used to optimize the centers and widths of hidden layer...

Recent studies in financial economics suggest that good technical analysis may have a merit in data series prediction. Linear Genetic Programming (LGP) is a genetic programming variant that evolves sequences of instructions from an imperative programming language. This paper presents a LGP approach to...

instant message tool’s provider. In order to recognize the influence factors of user loyalty and the influence mechanism, an empirical investigation of 379 subjects is conducted. Based on the structural equation model analysis, service quality and satisfaction are confirmed to have positive influence...

Management in our country faces strong challenges at the turn of the century. By analyzing the hotspots disturbed in Chinese management field, a new idea is proposed in this paper. This idea showed that it is necessary to build a management theory to accommodate the requirements of times dynamically....

UCT (Upper Confidence Bound Apply to Tree) is a new algorithm applies to huge branches mini-max game tree search which gains a great success on a Go program called MoGo. This paper proposes an imperfect information multi-player Military Chess system basing on UCT algorithm which also adopts Monte- Carlo...

Masqueraders invade into users’system and impersonate the real users to do whatever they want. Unfortunately, firewalls or misuse-based intrusion detection systems are generally ineffective in detecting masquerades. In this paper an abnormal detection method based on one class SVM are presented to detect...