Computer Vision, Accv'98: Third Asian Conference on Computer Vision, Hong Kong, China, January 8-10, 1998 : Proceedings

On typical implementations of Hough transform for improving its performances.- Hierarchical segmentation and representation with dynamic link architecture neural network.- Perceptually consistent segmentation of texture using multiple channel filter.- Optimal edge detection under difficult imaging conditions.- Restoring image quality through structure preserving de-noising.- Feature saliency from noise variations in invariants.- Multiscale image representation and edge detection.- Rotation invariant texture features from Gabor filters.- Euclidean invariants of linear scale-spaces.- Segmenting objects at multiple scales: A robust approach.- Multi-grid edge models for magnifying digital images.- Scale and rotation invariant recognition method using higher-order local autocorrelation features of log-polar image.- Script and language identification from document images.- Document categorization for document image understanding.- Recognition of various bar-graph structures based on layout model.- Word-class bigram statistics language model for a hand-written chinese character recognizer.- Log classification by single X-ray scans using texture features from growth rings.- Precise and fast form identification method by using adaptive base lines for matching.- Combinatorial coarse classification method for OLCCR.- Detecting characters in grey-scale scene images.- Conic based image transfer for 2-D Objects: A linear algorithm.- Minimal conditions on intrinsic parameters for Euclidean reconstruction.- Surface based hypothesis verification in intensity images using geometric and appearance data.- Next best viewpoint (NBV) planning for active object modeling based on a learning-by-showing approach.- Object recognition by matching symbolic edge graphs.- Interpretation of complex scenes using Bayesian networks.- Recognition of urban scene using silhouette of buildings and city map database.- A cooperative inference mechanism for extracting road information automatically.- Model-based active object recognition using MRF matching and sensor planning.- Improved image classification using morphing.- Reconstruction of non-manifold objects from two orthographic views.- 3D object recognition using segment-based stereo vision.- The state of color vision research.- Color vision and color media processing research in Asia.- Recent advances in detection and description of buildings from multiple aerial images.- Visual surveillance of human activity.- Bayesian paradigm for recognition of objects -On typical implementations of Hough transform for improving its performances.- Hierarchical segmentation and representation with dynamic link architecture neural network.- Perceptually consistent segmentation of texture using multiple channel filter.- Optimal edge detection under difficult imaging conditions.- Restoring image quality through structure preserving de-noising.- Feature saliency from noise variations in invariants.- Multiscale image representation and edge detection.- Rotation invariant texture features from Gabor filters.- Euclidean invariants of linear scale-spaces.- Segmenting objects at multiple scales: A robust approach.- Multi-grid edge models for magnifying digital images.- Scale and rotation invariant recognition method using higher-order local autocorrelation features of log-polar image.- Script and language identification from document images.- Document categorization for document image understanding.- Recognition of various bar-graph structures based on layout model.- Word-class bigram statistics language model for a hand-written chinese character recognizer.- Log classification by single X-ray scans using texture features from growth rings.- Precise and fast form identification method by using adaptive base lines for matching.- Combinatorial coarse classification method for OLCCR.- Detecting characters in grey-scale scene images.- Conic based image transfer for 2-D Objects: A linear algorithm.- Minimal conditions on intrinsic parameters for Euclidean reconstruction.- Surface based hypothesis verification in intensity images using geometric and appearance data.- Next best viewpoint (NBV) planning for active object modeling based on a learning-by-showing approach.- Object recognition by matching symbolic edge graphs.- Interpretation of complex scenes using Bayesian networks.- Recognition of urban scene using silhouette of buildings and city map database.- A cooperative inference mechanism for extracting road information automatically.- Model-based active object recognition using MRF matching and sensor planning.- Improved image classification using morphing.- Reconstruction of non-manifold objects from two orthographic views.- 3D object recognition using segment-based stereo vision.- The state of color vision research.- Color vision and color media processing research in Asia.- Recent advances in detection and description of buildings from multiple aerial images.- Visual surveillance of human activity.- Bayesian paradigm for recognition of objects - Innovative applications.- Toward motion picture grammars.- Hierarchical texture segmentation.- Range image segmentation: Adaptive grouping of edges into regions.- Optimising the complete image feature extraction chain.- A unified framework for salient curves, regions, and junctions inference.- Learning multiscale image models of 2D object classes.- 3D model centered framework for CV and VR.- Image-based geometrically-correct photorealistic scene/object modeling (IBPhM): A review.- Measuring object surface shape and reflectance properties.- Robust image composition algorithms for augmented reality.- Context-based recognition of manipulative hand gestures for human computer interaction.- An algorithm for recursive structure and motion recovery under affine projection.- Relative affine depth: Structure from motion by an uncalibrated camera.- The eigenspace method for rigid motion recovery from less than eight point correspondences.- 3D shape and motion analysis from image blur and smear: A unified approach.- 3D line's extraction from 2D Spatio-Temporal Image created by sine slit.- Toward non-intrusive motion capture.- Appearance based visual learning and object recognition with illumination invariance.- Evidence-based scene interpretation considering subjective certainty of recognition.- Robust hypothesis verification for model based object recognition using Gaussian error model.- Shape modeling from multiple view images using GAs.- 3-D reconstruction of multipart self-occluding objects.- On analysis of cloth drape range data.- VR models from epipolar images: An approach to minimize errors in synthesized images.- Shape and pose parameter estimation of 3D multi-part objects.- Generating 3D models of objects using multiple visual cues in image sequences.- Strategical tracking of polyhedral objects by reactive change of projection pattern - Reactive Range Finder -.- Autonomous vision-guided robot manipulation control.- A new adaptive approach on rapid obstacle detection in range image.- Recognition of shape models for general roads.- Visual detection of obstacles assuming a locally planar ground.- Potential-based modeling of 2D regions using non-uniform source distributions.- A linear algorithm for motion from three weak perspective images using Euler angles.- On Learning spatio-temporal relational structures in two different domains.- An efficient iterative pose estimation algorithm.- A new multistage approach to motion and structure estimation by gradually enforcing geometric constraints.- Tracking a person with pre-recorded image database and a pan, tilt, and zoom camera.- Recovery of motion and structure from optical flow under perspective projection by solving linear simultaneous equations.- Vector coherence mapping: A parallelizable approach to image flow computation.- Robust motion segmentation using rank ordering estimators.- Optical flow in the scale space.- Motion detection in temporal clutter.- A novel fast three-step search algorithm for block-matching motion estimation.- Moving vehicle detection and tracking in image sequences.- Gesture recognition from image motion based on subspace method and HMM.- Identifying faces under varying pose using a single example view.- Multiple camera based human motion estimation.- An autonomous facial caricaturing based on a model of visual illusion - Experimental modeling of visual illusion -.- 3D estimation of facial muscle parameter from the 2D marker movement using neural network.- Appearance-based face recognition under large head rotations in depth.- Skin-color modeling and adaptation.- Human information retrieval by face extraction and recognition on TV news images using subspace method.- Converting facial expressions using recognition-based analysis of image Sequences.- Muscle-based feature models for analyzing facial expressions.- A morphological method for moving object segmentation and posture recognition.- Detection of glasses in facial images.- Non-monotonic continuous dynamic programming for spotting recognition of hesitated gestures from time-varying images.- Face recognition using a face-only database: A new approach.