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.
Author(s): Jun-ichiro Hayashi, Kunihito Kato, Toshio Endoh (auth.), Roland Chin, Ting-Chuen Pong (eds.)
Series: Lecture Notes in Computer Science 1352
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 1997
Language: English
Pages: 763
Tags: Computer Graphics; Image Processing and Computer Vision; Pattern Recognition; Artificial Intelligence (incl. Robotics); Visualization
On typical implementations of Hough transform for improving its performances....Pages 1-8
Hierarchical segmentation and representation with dynamic link architecture neural network....Pages 9-16
Perceptually consistent segmentation of texture using multiple channel filter....Pages 17-24
Optimal edge detection under difficult imaging conditions....Pages 25-32
Restoring image quality through structure preserving de-noising....Pages 33-40
Feature saliency from noise variations in invariants....Pages 41-48
Multiscale image representation and edge detection....Pages 49-56
Rotation invariant texture features from Gabor filters....Pages 57-64
Euclidean invariants of linear scale-spaces....Pages 65-72
Segmenting objects at multiple scales: A robust approach....Pages 73-80
Multi-grid edge models for magnifying digital images....Pages 81-88
Scale and rotation invariant recognition method using higher-order local autocorrelation features of log-polar image....Pages 89-96
Script and language identification from document images....Pages 97-104
Document categorization for document image understanding....Pages 105-112
Recognition of various bar-graph structures based on layout model....Pages 113-120
Word-class bigram statistics language model for a hand-written chinese character recognizer....Pages 121-128
Log classification by single X-ray scans using texture features from growth rings....Pages 129-136
Precise and fast form identification method by using adaptive base lines for matching....Pages 137-144
Combinatorial coarse classification method for OLCCR....Pages 145-152
Detecting characters in grey-scale scene images....Pages 153-160
Conic based image transfer for 2-D Objects: A linear algorithm....Pages 161-168
Minimal conditions on intrinsic parameters for Euclidean reconstruction....Pages 169-176
Surface based hypothesis verification in intensity images using geometric and appearance data....Pages 177-184
Next best viewpoint (NBV) planning for active object modeling based on a learning-by-showing approach....Pages 185-192
Object recognition by matching symbolic edge graphs....Pages 193-200
Interpretation of complex scenes using Bayesian networks....Pages 201-208
Recognition of urban scene using silhouette of buildings and city map database....Pages 209-216
A cooperative inference mechanism for extracting road information automatically....Pages 217-224
Model-based active object recognition using MRF matching and sensor planning....Pages 225-232
Improved image classification using morphing....Pages 233-240
Reconstruction of non-manifold objects from two orthographic views....Pages 241-248
3D object recognition using segment-based stereo vision....Pages 249-256
The state of color vision research....Pages 257-257
Color vision and color media processing research in Asia....Pages 258-258
Recent advances in detection and description of buildings from multiple aerial images....Pages 259-266
Visual surveillance of human activity....Pages 267-274
Bayesian paradigm for recognition of objects — Innovative applications....Pages 275-282
Toward motion picture grammars....Pages 283-290
Hierarchical texture segmentation....Pages 291-298
Range image segmentation: Adaptive grouping of edges into regions....Pages 299-306
Optimising the complete image feature extraction chain....Pages 307-314
A unified framework for salient curves, regions, and junctions inference....Pages 315-322
Learning multiscale image models of 2D object classes....Pages 323-331
3D model centered framework for CV and VR....Pages 332-339
Image-based geometrically-correct photorealistic scene/object modeling (IBPhM): A review....Pages 340-349
Measuring object surface shape and reflectance properties....Pages 350-359
Robust image composition algorithms for augmented reality....Pages 360-367
Context-based recognition of manipulative hand gestures for human computer interaction....Pages 368-375
An algorithm for recursive structure and motion recovery under affine projection....Pages 376-383
Relative affine depth: Structure from motion by an uncalibrated camera....Pages 384-391
The eigenspace method for rigid motion recovery from less than eight point correspondences....Pages 392-399
3D shape and motion analysis from image blur and smear: A unified approach....Pages 400-407
3D line's extraction from 2D Spatio-Temporal Image created by sine slit....Pages 408-415
Toward non-intrusive motion capture....Pages 416-423
Appearance based visual learning and object recognition with illumination invariance....Pages 424-431
Evidence-based scene interpretation considering subjective certainty of recognition....Pages 432-439
Robust hypothesis verification for model based object recognition using Gaussian error model....Pages 440-447
Shape modeling from multiple view images using GAs....Pages 448-454
3-D reconstruction of multipart self-occluding objects....Pages 455-462
On analysis of cloth drape range data....Pages 463-470
VR models from epipolar images: An approach to minimize errors in synthesized images....Pages 471-478
Shape and pose parameter estimation of 3D multi-part objects....Pages 479-486
Generating 3D models of objects using multiple visual cues in image sequences....Pages 487-494
Strategical tracking of polyhedral objects by reactive change of projection pattern - Reactive Range Finder -....Pages 495-502
Autonomous vision-guided robot manipulation control....Pages 503-510
A new adaptive approach on rapid obstacle detection in range image....Pages 511-518
Recognition of shape models for general roads....Pages 519-526
Visual detection of obstacles assuming a locally planar ground....Pages 527-534
Potential-based modeling of 2D regions using non-uniform source distributions....Pages 535-542
A linear algorithm for motion from three weak perspective images using Euler angles....Pages 543-550
On Learning spatio-temporal relational structures in two different domains....Pages 551-558
An efficient iterative pose estimation algorithm....Pages 559-566
A new multistage approach to motion and structure estimation by gradually enforcing geometric constraints....Pages 567-574
Tracking a person with pre-recorded image database and a pan, tilt, and zoom camera....Pages 575-582
Recovery of motion and structure from optical flow under perspective projection by solving linear simultaneous equations....Pages 583-590
Vector coherence mapping: A parallelizable approach to image flow computation....Pages 591-598
Robust motion segmentation using rank ordering estimators....Pages 599-606
Optical flow in the scale space....Pages 607-614
Motion detection in temporal clutter....Pages 615-622
A novel fast three-step search algorithm for block-matching motion estimation....Pages 623-630
Moving vehicle detection and tracking in image sequences....Pages 631-638
Gesture recognition from image motion based on subspace method and HMM....Pages 639-646
Identifying faces under varying pose using a single example view....Pages 647-654
Multiple camera based human motion estimation....Pages 655-662
An autonomous facial caricaturing based on a model of visual illusion — Experimental modeling of visual illusion —....Pages 663-670
3D estimation of facial muscle parameter from the 2D marker movement using neural network....Pages 671-678
Appearance-based face recognition under large head rotations in depth....Pages 679-686
Skin-color modeling and adaptation....Pages 687-694
Human information retrieval by face extraction and recognition on TV news images using subspace method....Pages 695-702
Converting facial expressions using recognition-based analysis of image Sequences....Pages 703-710
Muscle-based feature models for analyzing facial expressions....Pages 711-718
A morphological method for moving object segmentation and posture recognition....Pages 719-725
Detection of glasses in facial images....Pages 726-733
Non-monotonic continuous dynamic programming for spotting recognition of hesitated gestures from time-varying images....Pages 734-741
Face recognition using a face-only database: A new approach....Pages 742-749