Computer Vision - ECCV ’96

The European Conference on Computer Vision (ECCV) has established itself as a major event in this exciting and very active field of research and development. These refereed two-volume proceedings include the 123 papers accepted for presentation at the 4th ECCV, held in Cambridge, UK, in April 1996; these papers were selected from a total of 328 submissions and together give a well-balanced reflection of the state of the art in computer vision.
The papers in volume I are grouped in sections on structure from motion; recognition; geometry and stereo; texture and features; tracking; grouping and segmentation; stereo; and recognition, matching, and segmentation.

Self-calibration from image triplets.- Parallax geometry of pairs of points for 3D scene analysis.- Euclidean 3D reconstruction from image sequences with variable focal lengths.- Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection.- Rapid object indexing and recognition using enhanced geometric hashing.- Recognition of geons by parametric deformable contour models.- Automatic extraction of generic house roofs from high resolution aerial imagery.- Three dimensional object modeling via minimal surfaces.- Class based reconstruction techniques using singular apparent contours.- Reliable surface reconstruction from multiple range images.- Shape from appearance: A statistical approach to surface shape estimation.- Volumic segmentation using hierarchical representation and triangulated surface.- Oriented projective geometry for computer vision.- Fast computation of the fundamental matrix for an active stereo vision system.- On binocularly viewed occlusion junctions.- Understanding the shape properties of trihedral polyhedra.- Nonlinear scale-space from n-dimensional sieves.- Hierarchical curve reconstruction. Part I: Bifurcation analysis and recovery of smooth curves.- Texture feature coding method for classification of liver sonography.- Local appropriate scale in morphological scale-space.- Scale-space with casual time direction.- Tracing crease curves by solving a system of differential equations.- Flows under min/max curvature flow and mean curvature: Applications in image processing.- Decomposition of the Hough transform: Curve detection with efficient error propagation.- Image retrieval using scale-space matching.- Optimal surface smoothing as filter design.- Segmentation in dynamic image sequences by isolation of coherent wave profiles.- Texture segmentation using local energy in wavelet scale space.- Tracking medical 3D data with a deformable parametric model.- EigenTracking: Robust matching and tracking of articulated objects using a view-based representation.- Contour tracking by stochastic propagation of conditional density.- Learning dynamics of complex motions from image sequences.- Quantitative analysis of grouping processes.- Geometric saliency of curve correspondences and grouping of symmetric contours.- Computing contour closure.- Visual organization of illusory surfaces.- Uncalibrated relief reconstruction and model alignment from binocular disparities.- Dense depth map reconstruction: A minimization and regularization approach which preserves discontinuities.- Stereo without search.- Informative views and sequential recognition.- Unsupervised texture segmentation using selectionist relaxation.- Robust affine structure matching for 3D object recognition.- Automatic face recognition: What representation?.- Genetic search for structural matching.- Automatic selection of reference views for image-based scene representations.- Object recognition using subspace methods.- Detecting, localizing and grouping repeatedscene elements from an image.- Image recognition with occlusions.- Silhouette-based object recognition with occlusion through curvature scale space.- A focused target segmentation paradigm.- Generalized image matching: Statistical learning of physically-based deformations.- Reasoning about occlusions during hypothesis verification.- Object recognition using multidimensional receptive field histograms.- Normalization by optimization.- Extracting curvilinear structures: A differential geometric approach.- Affine / photometric invariants for planar intensity patterns.- Image synthesis from a single example image.- Complexity of indexing: Efficient and learnable large database indexing.- Spatiotemporal representations for visual navigation.- Decoupling the 3D motion space by fixation.- Automatic singularity test for motion analysis by an information criterion.- Shape ambiguities in structure from motion.