These two volumes constitute the refereed proceedings of the Third Asian Conference on Computer Vision, ACCV''98, held in Hong Kong, China, in January 1998. The volumes present together a total of 58 revised full papers and 112 revised posters selected from over 300 submissions. The papers are organized in topical sections on biometry, physics-based vision, color vision, robot vision and navigation, OCR and applications, low-level processing, active vision, face and hand posture recognition, segmentation and grouping, computer vision and virtual reality, motion analysis, and object recognition and modeling.

Hersteller:
Springer Verlag GmbH
juergen.hartmann@springer.com
Tiergartenstr. 17
DE 69121 Heidelberg

InhaltsangabePen computing - An overview.- Research issues in biometrics.- Automatic on-line signature verification.- Integrating faces and fingerprints for personal identification.- Automated fingerprint pattern classification error analysis.- A high-dimensional indexing scheme for scalable fingerprint-based identification.- Sign of surface curvature from shading images using neural network.- On the classification of singular points for the global shape from shading problem: A study of the constraints imposed by isophotes.- Determination of sign of gaussian curvature of surface having general reflectance property.- Estimating depth through the fusion of photometric stereo images.- Out of the dark: Using shadows to reconstruct 3D surfaces.- Estimation of reflection parameters from a color image.- A natural norm for color processing.- A color normalization algorithm for image indexing.- Adaptive color-image embeddings for database navigation.- A large capacity steganography using color BMP images.- Dynamic calibration of an active vision system to compute the ground plane transformation.- Identification of 3D reference structures for video-based localization.- Directing robots with visual primitives for navigation and micro-manipulation.- Combining camera and laser radar for ALV navigation.- Stereo vision-based obstacle detection for partially sighted people.- Evaluation and application of recognition confidence in OCR.- A new nonlinear shape normalization method for off-line handwritten Chinese character recognition.- A novel triangulation procedure for thinning cursive text.- Digital geometric methods in image analysis and compression.- Detection and enhancement of small masses via precision multiscale analysis.- A method of industrial parts surface inspection based on an optics model.- Illumination color from the blurred inter-reflection of a reference nose.- Shape recovery from one image under multiple light sources.- Spherical and cylindrical light source models for shape recovery.- Polyhedral shape recovery based on interrefiections.- Improved supervised color constancy for color inspection.- Unsupervised filtering of Munsell spectra.- Foveated vision for scene exploration.- Evolutionary methods applied to binocular disparity estimation.- Robust epipolar geometry using genetic algorithm.- New development of stereo vision: A solution for motion stereo correspondence.- Acquisition of three-dimensional information using omnidirectional stereo vision.- Error analysis in stereo vision.- Detecting targets in SAR images: A machine learning approach.- Precise matching by Robust estimation of deformation and local coherence.- Active viewpoint control for shape from occluding contours.- Point selection: A new comparison scheme for size functions (With an application to monogram recognition).- Sketch up: Towards qualitative shape data management.- Robust matching and hierarchical recognition of 2-D shapes using "Chain of Circles".- Finding the center of rotational symmetry from noisy forms.- Recognition in wavelet-compressed imagery.- Fast image template and dictionary matching algorithms.- Recognition of planar shapes using algebraic invariants from higher degree implicit polynomials.- Object recognition and orientation via Zernike moments.- A study of Zernike moment computing.- Query expansion by raw image features and text annotations in image retrieval.- Montage: An image database for the fashion, textile, and clothing industry in Hong Kong.- Auto cameraman via collaborative sensing agents.- Dynamic adaptive data structures for semantic analysis and synthesis of video information.- Recognition of simple curved surfaces from 3D surface data.- A recursive fitting-and-splitting algorithm for 3-D object modeling based on superquadrics.- Learning and recognizing 3D objects by using partial planar curve matching method.- Contour matching technique for 3D object recognition using Kalman filter.- Kalman filter based matching technique for 3D object

The ACCV''98 volumes present together a total of 58 revised full papers and 112 revised posters selected from over 300 submissions. The papers are organized in topical sections on biometry, physics-based vision, color vision, robot vision and navigation, OCR and applications, low-level processing, active vision, face and hand posture recognition, segmentation and grouping, computer vision and virtual reality, motion analysis, and object recognition and modeling.