Intro; Preface; Organization; Contents -- Part I; Biological Vision Inspired Visual Method; An Evolution Perception Mechanism for Organizing and Displaying 3D Shape Collections; 1 Introduction; 2 The Overview of EPM; 3 The Details of EPM; 3.1 Population Organization; 3.2 Individual Snapshot; 3.3 Interactive Display; 4 Experimental Results and Discussion; 5 Conclusions; References; C-CNN: Cascaded Convolutional Neural Network for Small Deformable and Low Contrast Object Localization; 1 Introduction; 2 Cascaded CNN Detector; 2.1 The net-16; 2.2 The net-32; 2.3 The net-4
3 Experiments and Analysis3.1 Experiments Results; 3.2 Comparisons Results and Analysis; 4 Conclusion; References; Skeleton-Based 3D Tracking of Multiple Fish From Two Orthogonal Views; 1 Introduction; 2 The Proposed Method; 2.1 Object Detection; 2.2 Objects Tracking; 3 Experimental Results and Discussion; 3.1 Data Sets; 3.2 Parameters Setting; 3.3 Evaluation Metrics; 3.4 Results and Discussion; 4 Conclusion; References; A Retinal Adaptation Model for HDR Image Compression; 1 Introduction; 2 The Proposed Model; 2.1 Response of Photoreceptors; 2.2 Local Enhancement and Fusion
2.3 Recovering of the Color Image3 Experimental Results; 4 Conclusion; References; A Novel Orientation Algorithm for a Bio-inspired Polarized Light Compass; 1 Introduction; 2 Materials and Methods; 2.1 System Description; 2.2 Observation of Sky Polarization Angle Pattern; 2.3 Extraction of the Sky Region; 2.4 Computation of the Azimuth Angle; 3 Experimental Results; 3.1 Turntable Experiment; 3.2 Dynamic Vehicle Experiment; 4 Conclusion; References; Biomedical Image Analysis; A Brain MR Images Segmentation and Bias Correction Model Based on Students t-Mixture Model; 1 Introduction
2 Backgrounds2.1 Students t-Mixture Model (SMM); 2.2 Spatially Variant Finite Mixture Model (SVFMM); 3 Proposed Method; 4 Parameter Learning; 5 Experiment Results and Discussion; 6 Conclusion; References; Define Interior Structure for Better Liver Segmentation Based on CT Images; 1 Introduction; 2 Method; 2.1 P1: Liver Intensity Range Probability; 2.2 P2: Liver Location Probability; 2.3 P3: Hepatic Vein Neighborhood Probability; 2.4 P4: Liver Voxel Neighborhood Probability; 2.5 Final Probability; 3 Experiment and Results; 3.1 Experimental Setup and Evaluation Measures; 3.2 Results
3.3 Discussion4 Conclusion; References; Computer Vision Applications; GPU Accelerated Image Matching with Cascade Hashing; 1 Introduction; 2 Review of Cascade Hashing; 3 Cascade Hashing Matching Based on GPU; 3.1 The Disk-Memory-GPU Data Exchange Strategy; 3.2 Fast Computation of Hashing Code on GPU; 3.3 Improved Parallel Hashing Ranking; 3.4 Improved Parallel Euclidean Distance Calculation; 4 Experiments and Results; 5 Conclusions; References; Improved Single Image Dehazing with Heterogeneous Atmospheric Light Estimation; 1 Introduction; 2 Atmospheric Scattering Model
Annotation This three volume set, CCIS 771, 772, 773, constitutes the refereed proceedings of the CCF Chinese Conference on Computer Vision, CCCV 2017, held in Tianjin, China, in October 2017.The total of 174 revised full papers presented in three volumes were carefully reviewed and selected from 465 submissions. The papers are organized in the following topical sections: biological vision inspired visual method; biomedical image analysis; computer vision applications; deep neural network; face and posture analysis; image and video retrieval; image color and texture; image composition; image quality assessment and analysis; image restoration; image segmentation and classification; image-based modeling; object detection and classification; object identification; photography and video; robot vision; shape representation and matching; statistical methods and learning; video analysis and event recognition; visual salient detection.