Exploiting Intensity Inhomogeneity to Extract Textured Objects from Natural Scenes -- Exploiting Intensity Inhomogeneity to Extract Textured Objects from Natural Scenes -- Convolutional Virtual Electric Field External Force for Active Contours -- An Effective Segmentation for Noise-Based Image Verification Using Gamma Mixture Models -- Refined Exponential Filter with Applications to Image Restoration and Interpolation -- Color Correction and Compression for Multi-view Video Using H.264 Features -- A Subjective Method for Image Segmentation Evaluation -- Real-Time Object Detection with Adaptive Background Model and Margined Sign Correlation -- A 7-Round Parallel Hardware-Saving Accelerator for Gaussian and DoG Pyramid Construction Part of SIFT -- Weighted Map for Reflectance and Shading Separation Using a Single Image -- Polygonal Light Source Estimation -- Face Relighting Based on Multi-spectral Quotient Image and Illumination Tensorfaces -- Perception-Based Lighting Adjustment of Image Sequences -- Ultrasound Speckle Reduction via Super Resolution and Nonlinear Diffusion -- Background Estimation Based on Device Pixel Structures for Silhouette Extraction -- Local Spatial Co-occurrence for Background Subtraction via Adaptive Binned Kernel Estimation -- Gable Roof Description by Self-Avoiding Polygon -- Tracking Endocardial Boundary and Motion via Graph Cut Distribution Matching and Multiple Model Filtering -- Object Detection with Multiple Motion Models -- An Improved Template Matching Method for Object Detection -- Poster Session 3: Machine Learning, Recognition, Biometrics and Surveillance -- Unfolding a Face: From Singular to Manifold -- Fingerspelling Recognition through Classification of Letter-to-Letter Transitions -- Human Action Recognition Using Non-separable Oriented 3D Dual-Tree Complex Wavelets -- Gender from Body: A Biologically-Inspired Approach with Manifold Learning -- Fingerprint Orientation Field Estimation: Model of Primary Ridge for Global Structure and Model of Secondary Ridge for Correction -- Gait Recognition Using Procrustes Shape Analysis and Shape Context -- Person De-identification in Videos -- A Variant of the Trace Quotient Formulation for Dimensionality Reduction -- Adaptive-Scale Robust Estimator Using Distribution Model Fitting -- A Scalable Algorithm for Learning a Mahalanobis Distance Metric -- Lorentzian Discriminant Projection and Its Applications -- Learning Bundle Manifold by Double Neighborhood Graphs -- Training Support Vector Machines on Large Sets of Image Data -- Learning Logic Rules for Scene Interpretation Based on Markov Logic Networks -- Efficient Classification of Images with Taxonomies -- Adapting SVM Image Classifiers to Changes in Imaging Conditions Using Incremental SVM: An Application to Car Detection -- Incrementally Discovering Object Classes Using Similarity Propagation and Graph Clustering -- Image Classification Using Probability Higher-Order Local Auto-Correlations -- Disparity Estimation in a Layered Image for Reflection Stereo -- Model-Based 3D Object Localization Using Occluding Contours -- A Probabilistic Model for Correspondence Problems Using Random Walks with Restart -- Highly-Automatic MI Based Multiple 2D/3D Image Registration Using Self-initialized Geodesic Feature Correspondences -- Better Correspondence by Registration -- Image Content Based Curve Matching Using HMCD Descriptor -- Skeleton Graph Matching Based on Critical Points Using Path Similarity -- A Statistical-Structural Constraint Model for Cartoon Face Wrinkle Representation and Generation -- Spatially Varying Regularization of Image Sequences Super-Resolution -- Image Search Result Summarization with Informative Priors -- Interactive Super-Resolution through Neighbor Embedding -- Scalable Image Retrieval Based on Feature Forest -- Super-Resolution of Multiple Moving 3D Objects with Pixel-Based Registration -- Human Action Recognition Using Pyramid Vocabulary Tree -- Auto-scaled Incremental Tensor Subspace Learning for Region Based Rate Control Application -- Visual Focus of Attention Recognition in the Ambient Kitchen -- Polymorphous Facial Trait Code -- Face Recognition by Estimating Facial Distinctive Information Distribution -- Robust 3D Face Recognition Based on Rejection and Adaptive Region Selection -- Face Recognition via AAM and Multi-features Fusion on Riemannian Manifolds -- Gender Recognition via Locality Preserving Tensor Analysis on Face Images -- A Chromosome Image Recognition Method Based on Subregions -- Co-occurrence Random Forests for Object Localization and Classification -- Solving Multilabel MRFs Using Incremental ?-Expansion on the GPUs -- Non-rigid Shape Matching Using Geometry and Photometry -- Beyond Pairwise Shape Similarity Analysis -- Globally Optimal Spatio-temporal Reconstruction from Cluttered Videos.

It givesus greatpleasureto presentthe proceedings of the 9th Asian Conference on Computer Vision (ACCV 2009), held in Xi'an, China, in September 2009. This was the ?rst ACCV conference to take place in mainland China. We received a total of 670 full submissions, which is a new record in the ACCV series. Overall, 35 papers were selected for oral presentation and 131 as posters, yielding acceptance rates of 5.2% for oral, 19.6% for poster, and 24.8% in total. In the paper reviewing, we continued the tradition of previous ACCVsbyconductingtheprocessinadouble-blindmanner.Eachofthe33Area Chairs received a pool of about 20 papers and nominated a number of potential reviewers for each paper. Then, Program Committee Chairs allocated at least three reviewers to each paper, taking into consideration any con?icts of interest and the balance of loads. Once the reviews were ?nished, the Area Chairs made summaryreportsforthepapersintheirpools,basedonthereviewers'comments and on their own assessments of the papers.