Fractal dimension (fd) is a feature which is widely used to characterize medical images. Previously, researchers have shown that fd separates important classes of images and is orthogonal to other texture measures. Ex...
详细信息
Fractal dimension (fd) is a feature which is widely used to characterize medical images. Previously, researchers have shown that fd separates important classes of images and is orthogonal to other texture measures. Existing methods of estimating fd, however, are unable to distinguish many images with similar characteristics, limiting the effectiveness of fd as a feature. This paper analyzes the limitation of box-counting (BC) and fractional Brownian motion (fBm) methods of estimating fd. Estimation by BC is ineffective when applied to data-limited images. Estimation by fBm uses a restrictive model which is not applicable to Iterated Function Systems or to noisy images. The authors present a new method of estimating fd which is applicable to data-limited medical images. In the authors' method, Fractal Interpolation Functions (FIFs) are used to generate self-affine models of graphical representations of image data. The fd of each FIF is analytically evaluated, and measures of confidence and self-affinity are computed. The new method is demonstrated in a test study of red blood cells.
Recognition of voiced speech phonemes is addressed in this paper using features extracted from the bispectrum of the speech signal. Voiced speech is modeled as a superposition of coupled harmonics, located at frequenc...
详细信息
Recognition of voiced speech phonemes is addressed in this paper using features extracted from the bispectrum of the speech signal. Voiced speech is modeled as a superposition of coupled harmonics, located at frequencies that are multiples of the pitch and modulated by the vocal tract. For this type of signal, nonzero bispectral values are shown to be guaranteed by the estimation procedure employed. The vocal tract frequency response is reconstructed from the bispectrum on a set of frequency points that are multiples of the pitch. An AR model is next fitted on this transfer function. The AR coefficients are used as the feature vector for the subsequent classification step. Any finite dimension vector classifier can be employed at this point. Experiments using the LVQ neural classifier give satisfactory classification scores on real speech data, extracted from the DARPA/TIMIT speech corpus.
Computing the trajectories generated by an arbitrary system or process is extremely important for its analysis, especially for control and stability investigations. This paper analyses the fundamental matrix sequence ...
Computing the trajectories generated by an arbitrary system or process is extremely important for its analysis, especially for control and stability investigations. This paper analyses the fundamental matrix sequence (a discrete counterpart of the transition matrix in the continous case) for a linear unit memory repetitive process. The main result refers to the representation of the repetitive process in terms of the general singular Kurek model.
作者:
Oda, MAkamatsu, SFukamachi, HATR Human Information Processing Laboratories
Kyoto Japan 619-02 Shigeru Akamatsu received his B.E.
M.E. and Dr. of Eng. degrees in Mathematical Enginwring and Instrumentation Physics in 1975 1977 and 1994 respectively from the University of Tokyo Japan. In 1977 he joined the Electrical Communications Laboratories Nippon Telegraph and Telephone Public Corporation Yokosuka Japan. From 1977 through 1985 he was engaged in the research and development of optical character recognition systems for handwritten Chmese characters. During the academic year 1985-86 he was a Visiting Researcher at the University of California Irvine California U.S.A. Until 1992 he was a Senior Research Engineer Supervisor at W Human Interface Laboratories and conducted research on human image recognition with a special interest in face recognition. Since 1992 he has been with ATR Human Information Processing Research Laboratories Kyoto Japan where he is currently Head of Department 2. His research interests include computational and cognitive studies on high-level vision with a special interest in facial information processing by man and computer. He is a member of the Institute of Electronics Information and Communication Engineers of Japan the Information Processing Society of JapanACMand the IEEE Computer Society.Hidm Fukamachi received his B.E. degree in Image Technology from the Tokyo Institute of Polytechnics in 1990. He joined NTT Software Corp. in 1990
where he was engaged in the development of image processing software. Since 1993 he has been with ATR Human Information Processing Research Laboratories.
Some facial images are not necessarily clear images in the human brain. However, it can be easily judged whether a face matches the image in our mind;this is true even when the drawing or the expression of the target ...
详细信息
Some facial images are not necessarily clear images in the human brain. However, it can be easily judged whether a face matches the image in our mind;this is true even when the drawing or the expression of the target image is difficult to comprehend. This is because even if the image cannot be imagined like a picture, it does exist. The authors have proposed a system with which a retriever can retrieve an ambiguous target image from an image database. The system's retrieval efficiency and ease-of-retrieval were clarified by experiments using line drawn facial images. In this paper, the system is extended to photographs of faces. The most difficult problem in treating photographs is determining the retrieval key. One consideration is to add the subjective impressions or features of physical figures as keywords for each image data. Regardless of the method, however, significant manpower is necessary. The K-L expansion technique is used here, which has been verified as effective for face identification, and expect to need only a small amount of manpower. This paper investigates whether the technique can also be useful in ambiguous image retrieval.
A new texture operator, gray-level entropy matrix (GLEM), was developed, and nine new textural features were extracted from this matrix. These textural features were applied to light microscopy images of nuclei taken ...
详细信息
作者:
Aoki, YIijima, TMemberJapan Advanced Institute of Science and Technology
Hokuriku Ishikawa Japan 923 Yasubim Aoki:graduated from the University of Kanazawa Faculty of Engineering
Department of Electrical Engineering and Information Science in 1992 and received his Master's degree in 1994 from the Japan Advanced Institute of Science and Technology Hokuriku Department of Information Science where he is currently in the doctoral program engaged in research on pattern recognition. Honorary MemberTaizo lijima:graduatedwith a B.E. degree from the Tokyo Institute of Technology in 1948 and received his Ph.D. degree later. He joined the Electro-Technical Laboratories in 1948 and
since then has been involved in research on electromagnetic theory and pattern recognition theory image processing voice recognition and research and development of OCR. After serving as the head of Iijima Special Research Laboratories he became Professor at the Tokyo Institute of Technology in 1986. He because Professor Emeritus of that institute in 1986. He became Professor at Tokyo Engineering University and Professor Emeritus there in 1991. In 1991 he became Professor at the Japan Advanced Institute of Science and Technology and was appointed Vice President of the institute in 1992. He served successively as editor examiner secretary of general affairs inspector counsel committee-head of pattern recognition and specialized studies head of Tokyo chapter and vice president of this institute. In 1991 he became Honorary Member. He received the Paper Award from the Institute four times and the Literary Works Award once. He received the Achievement Award and the Distinguished Service Award in 1976 and 1989 respectively. He received the Purple Ribbon Medal from the Emperor in 1989.
Theoretical studies on Iijima's ''Theory of Pattern Recognition,'' which is known as a method of multiple similarity, have shown clearly that there are situations when it is difficult to determine ...
详细信息
Theoretical studies on Iijima's ''Theory of Pattern Recognition,'' which is known as a method of multiple similarity, have shown clearly that there are situations when it is difficult to determine the viewpoint and visual field, important parameters to introduce topological aspects into the pattern space, observing a figure itself. To cope with this problem, this paper proposes transforming the observed image from a figure f(r) to a second-order differential image rho(r), called ''figure source.'' The aim is to reconstruct the theory in such a way as to enable the application of similarity evaluation methods as in the conventional case, without compromising the current theory, and all the necessary proofs are given. In this paper, the figure source equation as well as rules representing its properties are developed, and several related physical quantities are redefined.
Control of a computer workstation via face position and facial gesturing would be an important advance for people with hand or body disabilities as well as for all users. Steps toward realization of such a system are ...
详细信息
Control of a computer workstation via face position and facial gesturing would be an important advance for people with hand or body disabilities as well as for all users. Steps toward realization of such a system are reported here. A computer system has been developed to track the eyes and the nose of a subject and to compute the direction of the face. Face direction and movement is then used to control the cursor. Test results show that the resulting system is usable, although several improvements are needed.
The need for more accurate results and larger problem sizes pushes the users in certain fields towards using supercomputing power. Besides problems with initial program development, another problem arises with debuggi...
详细信息
The need for more accurate results and larger problem sizes pushes the users in certain fields towards using supercomputing power. Besides problems with initial program development, another problem arises with debugging this kind of program. Debugging parallel programs is one of the hard tasks that users have to deal with when using parallel architectures. Where memory hot spots and bus contention are problems with shared memory architectures, nondeterminism arising from race conditions and the lack of a global clock are severe problems in using distributed memory architectures. We will discuss a new approach for detecting and/or studying concurrent events in distributed memory machines if race conditions occur in a certain program run. Through event graph manipulation the user can investigate whether wrong results may appear through different ordering of events.
The paper presents a general non-rigid body representation for physically-based modeling of dynamic behaviour of heterogeneous objects and its application in a development of a new heterogeneous morphing technique to ...
详细信息
HM-Card is a novel hypermedia authoring and presentation system for the development and use of a diverse range of hypermedia applications on PCs/MS-Windows. It is the first tool to implement the HM data model, a recen...
详细信息
HM-Card is a novel hypermedia authoring and presentation system for the development and use of a diverse range of hypermedia applications on PCs/MS-Windows. It is the first tool to implement the HM data model, a recent approach to provide a sound theoretical basis for the sophisticated structuring and navigating of hypermedia databases. However, in this paper we only cover the HM data model as the underlying theoretical foundation for the actual authoring system HM-Card. HM-Card offers an extensive set of functional and structural authoring elements, such as animations, question/answer dialogs, transparent import of external documents, and execution of other MS-Windows applications. The user-interface of HM-Card is intended to support rapid prototyping and authoring of complex hypermedia applications. Finished HM-Card applications can be run as stand-alone systems, used in MS-Windows' OLE (Object Linking and Embedding concept) clients, as well as be integrated as modules into large-scale distributed hypermedia systems.
暂无评论