Abstract preview: A method of rotation invariant texture classification based on a joint space-frequency model is introduced. Multiresolution filters, based on a truly analytic form of a polar 2-D gabor wavelet, are u ... more
Abstract preview: A comparison of different wavelet transform based texture features for content based search and retrieval is music. These include the conventional orthogoanl and bi-orthogonal wavelet transforms, tree ... more
Abstract preview: This paper suggests a wavelet transform based multiresolution approach as a viable solution to the problems of storage, retrieval and browsing in a large image database. We also investigate the perf ... more
T. Wiegand, M. Lightstone, T. G. Campbell and S. K. Mitra,
“A Rate-Constrained Encoding Strategy for H.263 Video Compression”,
International Symposium on Multimedia Communication and Video Coding, Brooklyn, NY, Oct. 1995.
Abstract preview: We propose a new method for indexing large image databases. The method incorporates neural network learning algorithms and pattern recognition techniques to construct an image pattern dictionary. Im ... more
D. Andresen, L. Carver, R. Dolin, C. Fischer, J. Frew, M. Goodchild, O. Ibarra, R. Kothuri, M. Larsgaard, B. Manjunath, D. Nebert, J. Simpson, T. Smith, T. Yang and Q. Zheng,
Abstract preview: The Alexandria Digital Library (ADL) is focused on providing broad access to distributed collections of spatially-indexed information. ADL has a four-component architecture involving collections, c ... more
I-S Lin and S. K..Mitra,
“Efficient 2-D FIR Filtering Algorithms Based on Overlapped Block Structure”,
38th Midwest Symposium on Circuits and Systems, Rio de Janeiro, Brazil, Aug. 1995.
Abstract preview: Image Registration is concerned with establishment of correspondence between images of the same scene. One challenging problem in this area is the registration of multispectral multisensor images. In ... more
A. D. Alexandrov, W. Y. Ma, A. El Abbadi and B. S. Manjunath,
Abstract preview: In this paper we combine image feature extraction with indexing techniques for efficient retrieval in large texture images databases. A 2D image signal is processed using a set of Gabor filters to der ... more
A. Hossen, U. Heute, O. Shentov and S. K. Mitra,
“Subband DFT - Part II: Accuracy Complexity and Applications”,
Signal Processing, vol. 42, no. 3, pp. 279-294, Feb. 1995.
Abstract preview: We propose a nonuniform frequency sampling method for 2-D FIR filter design based on the concept of the nonuniform discrete Fourier transform(NDFT). The NDFT of a 2-D sequence is defined as a sequenc ... more
Abstract preview: In the image fusion scheme presented in this paper, the wavelet transforms of the input images are appropriately combined, and the new image is obtained by taking the inverse wavelet transform of the ... more
Abstract preview: Efficient retrieval of information from image and other multimedia databases if an important and challenging problem. Among techniques developed for this purpose, query by example is the most effecti ... more
B. S. Manjunath and W. Y. Ma,
“Information Retrieval in Image Databases”,
ISMM International conference on Multimedia Systems and Applications, pp. 6-9, Honolulu, Hawaii, Aug. 1994.
Abstract preview: The 3-D multimodality brain image registration algorithm proposed in this paper is based on the matching of feature curves which are defined by the intersections of the interhemispherical fissure pla ... more
H. Li, B. S. Manjunath and S. K. Mitra,
“Optical-to-SAR image registration using the active contour approach”,
27th Asilomar Conference on Signals, Systems and Computers, pp. 568-572, Pacific Grove, CA, Nov. 1993.
Abstract preview: A model consisting of a multistage system which extracts and groups salient features in the image at different spatial scales (or frequencies) is used. In the first stage, a Gabor wavelet decomposit ... more
Abstract preview: An important goal of early vision is to transform the intensity data to a representation more suitable for further processing. Examples of such transformations include obtaining depth information fro ... more
Abstract preview: In this paper we present a contour-based multisensor image registration scheme which uses region boundaries and other strong edges as matching primitives. Chain code correlation and other shape simil ... more
B. S. Manjunath, Chandra Shekhar, R. Chellappa and C. von der Malsburg,
Abstract preview: Feature detection is a fundamental issue in many intermediate level vision problems such as stereo, motion correspondence, image registration, etc. In this paper a new approach to feature detection i ... more
B. S. Manjunath, R. Chellappa and C. von der Malsburg,
Abstract preview: Face represent one of the most common visual patterns in our environment, and humans have a remarkable ability to recognize faces. Face recognition does not fit into the traditional approaches of mod ... more
R. Chellappa, R.L. Kashyap and B.S. Manjunath,
“Model-Based Texture Segmentation and Classification”,
Handbook of Pattern Recognition and Computer Vision, C.H. Chen, L.F. Pau, and P.S.P. Wang (editors), Eds., World Scientific Publishing Company, 1992.
Abstract preview: A computational vision approach is presented for the estimation of 2-D translation, rotation, and scale from two partially overlapping images. An illuminant direction estimation method is first used ... more
B.S. Manjunath, P.B. Chou and R.S Jaffe,
“Optical Detection of Defects in Semiconductor Wafers Using Technical Artificial Neural Networks”,
Abstract preview: This paper presents a unified approach to boundary perception. The model consists of a hierarchical system which extracts and groups salient features in the image at different spatial scales. In the f ... more
B. S. Manjunath and R. Chellappa,
“Unsupervised Texture Segmentation Using Random Field Models”,
Abstract preview: This appear describes several texture segmentation algorithm based on deterministic and stochastic relaxation principles, and their implementation on parallel networks. The segmentation problem is pos ... more
Abstract preview: Several texture segmentation algorithms based on deterministic and stochastic relaxation principles, and their implementation on parallel networks are described. The segmentation process is posed as a ... more