Computer Vision - ACCV'98: Third Asian Conference on Computer Vision, Hong Kong, China, January 8 - 10, 1998, ProceedingsRoland Chin, Ting-Chuen Pong 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. |
Contents
Research Issues in Biometrics | 2 |
Automatic OnLine Signature Verification | 10 |
Integrating Faces and Fingerprints for Personal Identification | 16 |
Automated Fingerprint Pattern Classification Error Analysis | 24 |
A HighDimensional Indexing Scheme for Scalable FingerprintBased Identification | 32 |
Sign of Surface Curvature from Shading Images Using Neural Network | 40 |
A Study of the Constraints Imposed by Isophotes | 48 |
Determination of Sign of Gaussian Curvature of Surface Having General Reflectance Property | 56 |
Object Recognition and Orientation via Zernike Moments | 386 |
A Study of Zernike Moment Computing | 394 |
Query Expansion by Raw Image Features and Text Annotations in Image Retrieval | 402 |
An Image Database for the Fashion Textile and Clothing Industry in Hong Kong | 410 |
Auto Cameraman Via Collaborative Sensing Agents | 418 |
Dynamic Adaptive Data Structures for Semantic Analysis and Synthesis of Video Information | 426 |
Recognition of Simple Curved Surfaces from 3D Surface Data | 434 |
A Recursive FittingandSplitting Algorithm for 3D Object Modeling Based on Superquadrics | 442 |
Estimating Depth Through the Fusion of Photometric Stereo Images | 64 |
Using Shadows to Reconstruct | 72 |
Estimation of Reflection Parameters from a Color Image | 80 |
A Natural Norm for Color Processing | 88 |
A Color Normalization Algorithm for Image Indexing | 96 |
Adaptive Colorlinage Embeddings for Database Navigation | 104 |
A Large Capacity Steganography Using Color BMP Images | 112 |
Dynamic Calibration of an Active Vision System to Compute the Ground Plane Transformation | 120 |
Identification of 3D Reference Structures for VideoBased Localization | 128 |
Directing Robots with Visual Primitives for Navigation and Micromanipulation | 136 |
Combining Camera and Laser Radar for ALV Navigation | 144 |
Stereo VisionBased Obstacle Detection for Partially Sighted People | 152 |
Evaluation and Application of Recognition Confidence in OCR | 160 |
A New Nonlinear Shape Normalization Method for Offline Handwritten Chinese Character Recognition | 168 |
A Novel Triangulation Procedure for Thinning Cursive Text | 176 |
Digital Geometric Methods in Image Analysis and Compression | 184 |
Detection and Enhancement of Small Masses via Precision Multiscale Analysis | 192 |
A Method of Industrial Parts Surface Inspection Based on an Optics Model | 200 |
Illumination Color from the Blurred InterReflection of a Reference Nose | 208 |
Shape Recovery from One Image under Multiple Light Sources | 216 |
Spherical and Cylindrical Light Source Models for Shape Recovery | 224 |
Polyhedral Shape Recovery Based on Interreflections | 232 |
Improved Supervised Color Constancy for Color Inspection | 240 |
Unsupervised Filtering of Munsell Spectra | 248 |
Foveated Vision for Scene Exploration | 256 |
Evolutionary Methods Applied to Binocular Disparity Estimation | 264 |
Robust Epipolar Geometry Using Genetic Algorithm | 272 |
A Solution for Motion Stereo Correspondence | 280 |
Acquisition of ThreeDimensional Information Using Omnidirectional Stereo Vision | 288 |
Error Analysis in Stereo Vision | 296 |
A Machine Learning Approach | 305 |
Precise Matching by Robust Estimation of Deformation and Local Coherence | 313 |
Active Viewpoint Control for Shape from Occluding Contours | 321 |
A New Comparison Scheme for Size Functions With an Application to Monogram Recognition | 329 |
Towards Qualitative Shape Data Management | 338 |
Robust Matching and Hierarchical Recognition of 2D Shapes Using Chain of Circles | 346 |
Finding the Center of Rotational Symmetry from Noisy Forms | 354 |
Recognition in WaveletCompressed Imagery | 362 |
Fast Image Template and Dictionary Matching Algorithms | 370 |
Recognition of Planar Shapes Using Algebraic Invariants from Higher Degree Implicit Polynomials | 378 |
Learning and Recognizing 3D Objects by Using Partial Planar Curve Matching Method | 450 |
Contour Matching Technique for 3D Object Recognition Using Kalman Filter | 458 |
Kalman Filter Based Matching Technique for 3D Object Recognition | 466 |
A Generating Method for 3dimensional Knitting Cloth Shapes | 474 |
A Fast Mesh Deformation Method to Build Spherical Representation Models of 3D Objects | 482 |
SemiAutomatic 3D Object Digitizing System Using Range Images | 490 |
Image Guided Surgical Systems | 498 |
Technical Evaluation of Biometric Systems | 499 |
Face Recognition from Sequences Using Models of Identity | 507 |
Enhancing Human Face Detection Using Motion and Active Contours | 515 |
Learning Identity and Behaviour with Neural Networks | 523 |
Open Sesame Speech Password or Key to Secure Your Door? | 531 |
A Unified Framework for ImageDerived Invariants | 542 |
Stereo Correspondences in Scale Space | 550 |
Fast Stereo Matching in Compressed Video | 558 |
Robust Total Least Squares Based Optic Flow Computation | 566 |
Image Processing via the Beltrami Operator | 574 |
Efficient Contour Extraction in Color Images | 582 |
Color Edge Detection Using Orthogonal Polynomials | 588 |
Fast and Robust Segmentation of Natural Color Scenes | 596 |
Segmentation and Tracking Using Colour Mixture Models | 605 |
Object Tracking Using Adaptive Colour Mixture Models | 613 |
A Learning Approach to Fixating on 3D Targets with Active Cameras | 621 |
Automatic Detection and Tracking of Human Heads Using an Active Stereo Vision System | 630 |
Front Propagation and LevelSet Approach for Geodesic Active Stereovision | 638 |
A Bayes NetsBased PredictionVerification Scheme for Active Visual Reconstruction | 646 |
Actively Building Models with VIRTUE | 654 |
Using RBF Networks to Map GWT Ridge Images to Pose | 662 |
3D Pose Estimation and Model Refinement of an Articulated Object from a Monocular Image Sequence | 670 |
Face Synthesis with Arbitrary Pose and Expression from Several Images | 678 |
Live Facial Expression Generation Based on Mixed Reality | 686 |
RealTime Tracking of Human Hands from a Sign Language Image Sequence | 696 |
The ModelBased Dynamic Hand Posture Identification Using Genetic Algorithm | 704 |
Parallel Implementation of Fractal Image Compression Using Multiple Digital Signal Processors | 712 |
Comparison of Mean Field Annealing and Multiresolution Analysis in Missing Data Estimation | 720 |
Segmentation of MRF Based Image Using Hierarchical Genetic Algorithm | 728 |
Motion Compensated Color Video Classification Using Markov Random Fields | 736 |
EdgePreserving Smoothing by Convex Minimization | 744 |
Author Index | 753 |
Other editions - View all
Computer Vision, ACCV'98: Third Asian Conference on Computer Vision, Hong ... Roland T. Chin No preview available - 1998 |
Common terms and phrases
algorithm analysis angle application approach biometric blob camera classification coefficients color constancy color image components Computer Vision considered constraint contour coordinate corresponding curvature curve database defined deformation detection disparity distance distribution edge edge detection epipolar geometry equation error estimation extracted feature density Figure filters fingerprint frame function Gaussian Gaussian curvature genetic algorithm geometric global histogram IEEE IEEE Trans illumination Image Processing image sequences input image invariant Kalman filter light source linear matching matrix measure mesh method motion neural network noise obtained optic flow optical paper parameters pattern class Pattern Recognition performance pixels pose problem Proc proposed query reconstruction region representation robot robust rotation sample scale scale-space scene segmentation sensor shape shown in Fig shows solution space speaker recognition stereo superquadric surface surface normal target technique texture threshold tracking transformation vector verification visual wavelet Zernike moments
Popular passages
Page v - Last but not least, we would like to express our gratitude to all of the organizations who have supported our efforts to bring the conference to fruition.