Illumination Invariant Recognition of Three-Dimensional Texture in Color Images

In this paper, illumination-affine invariant methods are presented 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 tests: the first is used with textures of outdoor scenes while the second is performed on the well-known CURET texture database. Both tests show high recognition efficiency of the proposed recognition methods.     

An approximation-based approach to computing image moment invariants

A fast method for computing Hu’s image moment invariants is described. The invariants are found by approximation using generalized moments computed in a sliding window by a parallel recursive algorithm. The proposed method is shown to be computationally more efficient than direct computation. Vladislav V. Sergeev. Born 1951. Graduated from the Kuibyshev Aviation Institute (now, the Samara State Aerospace University) in 1974. Received doctoral degree (Dr. Sc. (Eng.)) in 1993. Head of Laboratory of Mathematical Methods of Image Processing, Image Processing Systems Institute, Russian Academy of Sciences. Scientific interests: digital signal processing, image analysis, pattern recognition, and geoinformatics. Author of more than 150 publications, including about 40 papers in journals, and a co-author of 2 monographs. Chair of the Volga-region Branch of the Russian Federation Association for Pattern Recognition and Image Analysis. Corresponding Member of the Russian Ecological Academy and the Russian Academy of Engineering, member of SPIE (The International Society for Optical Engineering), a winner of the Samara District Award for Science and Engineering. Ol’ga A. Titova. Born 1980. Graduated from the Samara State Aerospace University (SSAU) in 2002. Currently post-graduate student at the Chair of Geoinformatics, SSAU. Scientific interests: image analysis, pattern recognition, fast algorithms of digital image processing, and geoinformatics. Author of nine publications including three papers in journals. Member of the Russian Federation Association for Pattern Recognition and Image Analysis.     

Comparative analysis of function approximation methods applied to image processing

Application of nonlinear methods of multivariate regression approximation (neural networks, functions linear in fitting parameters, and hierarchical approximation) is considered to problems of image filtering based on a priori information in the form of matched pairs of images (“ideal” and “degraded”). The methods are compared with regard to their efficiency. Vasilii N. Kopenkov. Born 1978. Graduated from the Samara State Aerospace University (SSAU) in 2001. Assistant Professor at the Chair of Geoinformatics, SSAU, and a Junior Researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing and pattern recognition. Author of four papers. Member of the Russian Federation Association for Pattern Recognition and Image Analysis. Andrei V. Chernov. Born 1975. Graduated from the Samara State Aerospace University (SSAU) in 1998. Received candidate’s degree (Cand. Sc. (Eng.)) in 2004. Assistant Professor at the Chair of Geoinformatics, SSAU, and a Researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing, pattern recognition, and geoinformation systems. Author of more than 50 publications, including 11 papers in journals, and a co-author of a monograph. Member of the Russian Federation Association for Pattern Recognition and Image Analysis. Vladislav V. Sergeev. Born 1951. Graduated from the Kuibyshev Aviation Institute (now, the Samara State Aerospace University). Received doctoral degree (Dr. Sc. (Eng.)) in 1993. Head of Laboratory of Mathematical Methods of Image Processing, Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: digital signal processing, image analysis, pattern recognition, and geoinformatics. Author of more than 150 publications, including about 40 papers in journals, and a co-author of 2 monographs. Chair of the Volga-region Branch of the Russian Federation Association for Pattern Recognition and Image Analysis. Corresponding Member of the Russian Ecological Academy and the Russian Academy of Engineering, member of SPIE (The International Society for Optical Engineering), a winner of the Samara District Award for Science and Engineering.     

A Rejection Model Based on Multi-Layer Perceptrons for Mandarin Digit Recognition

High performance Mandarin digit recognition(MDR)is much more difficult to achieve than its English counterpart,especially on inexpensive hardware implementation.In this paper,a new ,Multi-Layer Perceptrons(MLP)based postprocessor,an a posteriori probability estimator is presented and used for the rejection model of the speaker independent Mandarin digit recognition system based on hidden Markov model(HMM).Poor utterances,which are recognized by HMMs but have low a posteriori probability,will be rejected.After rejecting about 4.9% of the tested utteraces,the MLP rejection model can boost the digit recognition accuracy from 97.1%to 99.6%,The performance is better than those rejection models based on linear discrimiantion,likelihood ratio or anti-digit.     

Wiener estimation method in estimating of spectral reflectance from RGB images

Color is one of the most important features in digital images. The representation of color in digital form with a three-component image (RGB) is not very accurate, hence the use of a multiple-component spectral image is justified. At the moment, acquiring a spectral image is not as easy and as fast as acquiring a conventional three-component image. One answer to this problem is to use a regular digital RGB camera and estimate its RGB image into a spectral image by the Wiener estimation method, which is based on the use of a priori knowledge. In this paper, the Wiener estimation method is used to estimate the spectra of icons. The experimental results of the spectral estimation are presented. The text was submitted by the authors in English. Pekka Tapani Stigell. Year of birth 1976. Year of graduation and name of institution: Last year undergraduate student in the Department of Computer Science in the University of Joensuu, Finland. Affiliation: InFotoics Center, Department of Computer Science, University of Joensuu. Position: Trainee. Area of research: Color research. Number of publications: 1. Membership to scientific societies: Pattern Recognition Society of Finland, member-society of IAPR (International Association for Pattern Recognition). Prizes for achievements in research or applications: The best young scientist award in PRIA-7-2004 (shared with two other scientists). Kimiyoshi Miyata. Year of birth: 1966. Year of graduation and name of institution: 2000. Graduate School of Science and Technology, Chiba University, Japan. Year of graduation: 1990, BE degree (Chiba University), 1992, ME degree (Chiba University), 2000, Ph.D degree (Chiba University). Affiliation: Museum Science Division, Research Department, National Museum of Japanese History. Position: Assistant Professor. Area of research: Improvement of image quality, color management, application of imaging science and technology to museum activities. Number of publications: 11. Membership to scientific societies: Society of Photographic Science and Technology of Japan, Optical Society of Japan, Institute of Image Electronics Engineers of Japan, Society for Imaging Science and Technology. Prizes for achievements in research or applications: Progressing Award from Society of Photographic Science and Technology of Japan in 2000, Itek Award from Society for Imaging Science and Technology in 2000. Markku Hauta-Kasari. Year of birth: 1970. Graduation and name of the institution: University of Technology, Lappeenranta, Finland. Year of graduation: 1999, Ph.D. degree (University of Technology, Lappeenranta). Affiliation: InFotonics Center, Department of Computer Science, University of Joensuu. Position: Director. Area of research: Color research, neural computation, pattern recognition, optical pattern recognition, computer vision, image processing. Number of publications: Articles in refereed international scientific journals: 5, Articles in refereed international scientific conferences: 9, Other Scientific Publications: 40. Membership to academies: Chairman of the Pattern Recognition Society of Finland May 2003. Membership to scientific societies: Pattern Recognition Society of Finland, member-society of IAPR (International Association for Pattern Recognition), Finnish Information Processing Association, Finnish Union of University Researchers and Teachers, Optical Society of Japan, Optical Society of America. Prizes for achievements in research or applications: The best Ph.D.-thesis award in the field of pattern recognition in 1998–1999 in Finland. Award was issued by the Pattern Recognition Society of Finland on April 25, 2000.     

Fast correlation method with the use of a wide selection of template in problems of image analysis

The problem of searching for and recognizing fragments of images that correspond to one of a wide variety of template is considered. The method of the fast correlation of a wide selection of trinary template, which successfully resolves this problem, is suggested. The use of this method in two problems of image analysis is shown, namely, the search for position of eyes in documental photographs of faces and the recognition of computer-readable lines in scanned images of documents. Nikolai Ivanovich Glumov. Born in 1962. In 1985, he graduated the Kuibyshev Aviation Institute (now, the Samara State Aerospace University). In 1994, he defended the Candidate of Science (Engineering) Dissertation. Currently, he is working as the Senior Researcher at the Image Processing Systems Institute, Russian Academy of Sciences. His circle of scientific interests involves the image processing and pattern recognition, image compression, and simulation of the systems of formation of digital images. Glumov has more than 90 publications involving more than 30 articles and one monograph (in partnership). He is a member of the Russian Association of Pattern Recognition and Image Processing. Evgenii Valer’evich Myasnikov. Born in 1981. In 2004, he graduated the Samara State Aerospace University and entered the Post-Graduate Education of SGAU. In 2007, Myasnikov defended the Candidate of Science (Engineering) Dissertation. Currently, is working as the Probationer Researcher at the Image Processing Systems Institute, Russian Academy of Sciences and simultaneously as the Assistant of the Department of Geoinformatics at SCAU. The circle of scientific interests involves the creation of software complexes, image processing and pattern recognition, and search for images in databases. Myasnikov has 23 publications, including six articles. He is the member of the Russian Association of Pattern Recognition and Image Processing. Vasilii Nikolaevich Kopenkov. Born in 1978. In 2001, he graduated the Samara State Aerospace University (SGAU). Currently, he is working as the assistant of the Department of Geoinformatics at the SGAU and Junior Researcher at the Image Processing Systems Institute, Russian Academy of Sciences. The circle of scientific interests involves the processing of images of the distanced probing of the Earth, pattern recognition, and geoinformatic systems. Kopenkov has 17 publications, including seven articles. He is the member of the Russian Association of Pattern Recognition and Image Processing. Marina Aleksandrovna Chicheva. Born in 1964. In 1987, she graduated the Kuibyshev Aviation Institute (now, the Samara State Aerospace University). In 1998, she defended the Candidate of Science (Engineering) Dissertation. She currently works as the Senior Researcher at the Image Processing Systems Institute, Russian Academy of Sciences. Her scientific interests include image processing and compression, rapid algorithms of discrete transformations, and pattern recognition. Chicheva has more than 18 articles, including one monograph (in partnership). She is the member of the Russian Association of Pattern Recognition and Image Processing.     

An interlingua-based Chinese-English MT system

Chinese-English machine translation is a significant and challenging problem in information processing.The paper presents an interlingua-based Chinese-English natural language translation system(ICENT).It introduces the realization mechanism of Chinses language analysis,which contains syntactic parsing and semantic analyzing and gives the design of interlingua in details .Experimental results and system evaluation are given .The sesult is satisfying.     

Fast computation of exact Zernike moments using cascaded digital filters

Zernike moments have been extensively used and have received much research attention in a number of fields: object recognition, image reconstruction, image segmentation, edge detection and biomedical imaging. However, computation of these moments is time consuming. Thus, we present a fast computation technique to calculate exact Zernike moments by using cascaded digital filters. The novelty of the method proposed in this paper lies in the computation of exact geometric moments directly from digital filter outputs, without the need to first compute geometric moments. The mathematical relationship between digital filter outputs and exact geometric moments is derived and then they are used in the formulation of exact Zernike moments. A comparison of the speed of performance of the proposed algorithm with other state-of-the-art alternatives shows that the proposed algorithm betters current computation time and uses less memory.     

Singularity Analysis of Geometric Constraint Systems

Singularity analysis in an important subject of the geometric constraint satisfaction problem.In this paper,three kinds of singularities are described and corresponding identifcation methods are presented for both under0constrained systems and over-constrained systems,Another special but common singularity for under-constrained geometric systems,pseudo-singularity,is analyzed.Pseudo-singularity is caused by a variety of constraint mathching of under-constrained systems and can be removed by improving constraint distribution.To avoid pseudo-singularity and decide redundant constraints adaptively,a differentiaiton algorithm is proposed in the paper.Its corrctness and effciency have been validated through its practical applications in a 2D/3D geometric constraint solver CBA.     

A Non-Collision Hash Trie-Tree Based Fast IP Classification Algorithm

With the developemnt of network applications,routers must support such functions as firewalls,provision of QoS,traffic billing,etc.All these functions need the classification of IP packets,according to how different the packetes are processd subsequently,which is determined.In this article,a novle IP classification algorithm is proposed based on the Grid of Tries algorithm.The new algorithm not only eliminates original limitations in th case of multiple fields but also shows better performance in regard to both and space.It has better overall performance than many other algorithms.     

Method for the automatic georeferencing and calibration of cartographic images

The paper considers one of the stages of creating and reneqing digital maps, i.e., georeferencing and calibrating cartographic representations (scanned topographic drawings). It is proposed to use the standards accepted in Russia for paper maps to search for intersections in the coordinate lines using known physical coordinates. An algorithmic system and software consisting of the following stages have been developed: search for interior and exterior margins of the topographic drawing, search for intersections of coordinate lines, verification of detected control points, and geometric transformation. The use of this method allows one to exclude hand labor by operators, which saves 10–20 min per map board. Ol’ga Aleksandrova Titova. Born in 1980. Graduated from Samara State Aerospace University (SGAU) in 2003. Received Candidate’s degree in 2006 in technical sciences. An assistant at the Geoinformatics Department of SGAU and a trainee observer at the Image Processing Systems Institute of Russian Academy of Science. Scientific interests include digital signal and image processing, including remotesensing data, geoinformation systems, and image recognition. She is the author of 19 scientific publications, including four articles, and a Member of the Russian Association for Pattern Recognition and Image Analysis. Andrei Vladimirovich Chernov. Born in 1975. Graduated from Samara State Aerospace University (SGAU) in 1998. Received Candidate’s degree in 2004 in technical sciences. Associate Professor at the Department of Geoinformatics, Samara State Aerospace University. Scientific interests include processing remote sensing data and image recognition. He is the author of more than 50 scientific publications, including 24 articles and one monograph (as a coauthor), as well as a member of the Russian Association for Pattern Recognition and Image Analysis.     

Software environment for simulating algorithms for image analysis and processing

We consider the purpose, functionality, configuration, and structure of a software environment designed for simulation and investigation of methods, algorithms, and information technology for digital images analysis and processing. Mikhail V. Gashnikov. Born 1975. Graduated from the Samara State Airspace University (SSAU) in 1998. Received candidate’s degree in Technology in 2004. He is now an assistant professor at the chair of earth information of the SSAU. Scientific interests: image processing, compression, statistical coding. Author of more than 30 publications, including 12 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis. Evgenii V. Myasnikov. Born 1981. Graduated from the Samara State Airspace University in 2004. He is now a post-graduate student at the Chair of Earth Information of the Samara State Airspace University. Scientific interests: development of software systems, image processing, image retrieval in databases. Author of 6 publications, including one paper. Member of the Russian Association for Pattern Recognition and Image Analysis. Andrei V. Chernov. Born 1975. Graduated from the Samara State Airspace University (SSAU) in 1998. Received candidate’s degree in Technology in 2004. He is now an assistant professor at the Chair of Earth Information of the SSAU and a research fellow at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing, pattern recognition, geoinformation systems. Author of more than 50 publications, including 11 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis. Nikolai I. Glumov. Born 1962. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1985. Received candidate’s degree in Technology in 1994. He is now a senior researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing and pattern recognition, compression of images, simulation of systems of digital image formation. Author of more than 50 publications, including 21 papers and one monographs (in coauthorsip). Member of the Russian Association for Pattern Recognition and Image Analysis. Vladislav V. Sergeev. Born 1951. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1974. Received doctoral degree in Technology in 1993. Head of the Laboratory of Mathematical Methods for Image Processing at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: digital signal processing, image analysis, pattern recognition, earth information. Author of more than 150 publications, including approximately 40 papers and two monographs (in coauthorship). President of the Povolzh’e Branch of the Russian Association for Pattern Recognition and Image Analysis. Corresponding member of the Russian Ecological Academy and of the Russian Academy of Engineering Sciences. Member of the International Society for Optical Engineering. A laureate of the Samara Provincial Government prize in science and engineering. Marina A. Chicheva. Born 1964. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1987. Received candidate’s degree in Technology in 1998. She is now a senior researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image recognition, compression, fast algorithms for discrete transformations. Author of more than 40 publications, including 15 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis.     

An architectural model for intelligent network management

Traditional network management approach involves the management of each vendor‘s equipment and networkd segment in isolation through its own proprietary element management system.It is necessary to set up a new network management architecture that calls for operation consolidation across vendor and technology boundaries.In this paper,an architerctural model for Intelligent Network Management(INM)is presented.The INM system includes a manager system,which controls all subsystems and coordinates different management tasks;an expert system,which is responsible for handling particularly difficult problems,and intelligent agents,which bring the management closer to applications and user requirements by spreading intellignet agents through network segments or domain.In the expert system model proposed,especially an intellignet fault management system is given.The architectural model is to build the INM system to meet the need of managing modern network systems.     

Automatic Segmentation of News Items Based on Video and Audio Features

The automatic segmentation of news items is a key for implementing the automatic cataloging system of news video.This paper presents an approach which manages audio and video feature infomation to automatically segment news items.The integration of audio and visual analyses can overcome the weakness of the approach using only image analysis techniques.It makes the approach more adaptable to various situations of news items.The proposed approach detects silence segments in accompanying audio,and integrates them with shot segmentation results,as ewll as anchor shot detection results,to determine the boundaries among news items,Expeimental results show that the integration of audio and video features is an effective approach to solving the problem of automatic segmentation of news items.     

Preparing a common raster coverage for a territory based on hierarchical compressed presentation of orthoimages

Technology for the quick viewing of georeferenced images has been developed. Principles of the organization and structure of hierarchical HGI format, which is intended to store compressed images with controlled maximal error, are presented. Additionally, a basic method of HGI format compression is described. The advantages of using the HGI format for covering a territory with orthoimages are described. Mikhail Valer’evich Gashnikov. Born in 1975. Graduated from Samara State Aerospace University (SGAU) in 1998. Received Candidate’s degree in 2002 in technical sciences. Associate Professor at the Department of Geoinformatics, Samara State Aerospace University. Scientific interests include image processing, compression of images, and statistical coding. He is the author of 50 scientific publications, including 21 articles and one monograph (as a coauthor). He is a member of the Russian Association for Pattern Recognition and Image Analysis. Nikolai Ivanovich Glumov. Born in 1962. Graduated from Kuibyshev State Aeronautical Institute (currently Samara State Aerospace University) in 1985. Received his Candidate’s degree in 1994 in technical sciences and currently works as a Senior Research Associate at the Image Processing Systems Institute of the Russian Academy of Science. Scientific interests include processing remote sensing data and image recognition, image compression, the formation of modeling systems of digital images. He is the author of more than 90 scientific publications, including 30 articles and one monograph (as a coauthor). He is a member of the Russian Association for Pattern Recognition and Image Analysis. Andrei Vladimirovich Chernov. Born in 1975. Graduated from Samara State Aerospace University in 1998. Received Candidate’s degree in 2004 in technical sciences and currently works as an Associate Professor at the Department of Geoinformatics, Samara State Aerospace University. Scientific interests include processing remote sensing data and image recognition. He is the author of more then 50 scientific publications, including 24 articles and one monograph (as a co-author). He is a member of the Russian Association for Pattern Recognition and Image Analysis.