This book constitutes the refereed proceedings of the 12th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2017, held in Beijing, China June 30 - July 1, 2017. The 26 papers presented were carefully reviewed and selected from 78 submissions. They provide a forum for sharing progresses in the areas of image processing technology; image analysis and understanding; computer vision and pattern recognition; big data mining, computer graphics and VR; as well as image technology applications

Inhalt

SAR image registration using clustering analysis and anisotropic diffusion-based SIFT.- Palmprint Recognition with Deep Convolutional Features.- sosurface Algorithm Based on Generalized Three Prism.- A Novel Classifier Using Subspace Analyse for Face Recognition.- A Variational Model based on Total Generalized Variation for Multiplicative Noise Removal.- An Improved Superpixel Method for Color Image Segmentation Based on SEEDS.- Global Perception Feedback Convolutional Neural Networks.- Single Image Defogging based on Step Estimation of Transmissivity.- The Method of Crowd Density Alarm for Video Sequence.- A novel three-dimensional asymmetric reconstruction method o plasma.- Pose Measurement of Drogue via Monocular Vision for Autonomous Aerial Refueling.- Recognition of Group Activities Based on M-DTCWT and Elliptic Mahalanobis Metrics.- U3D File Format Analyzing and 3DPDF Generating Method.- Estimating Cumulus Cloud Shape from a Single Image.- Design of a Computer-Aided-Design System for Museum Exhibition Based on Virtual Reality.- Real-time salient object detection based on fully convolutional networks.- Boosting Multi-view Convolutional Neural Networks for 3D Object Recognition via View Saliency.- Spacecraft Component Detection in Point Clouds.- Research on 3D Modeling of Geological Interface Surface.- Image Segmentation via the Continuous Max-Flow Method Based on Chan-Vese Model .- Deep-Stacked Auto Encoder for Liver Segmentation.- A Flattened Maximally Stable Extremal Region Method for Scene Text Detection.- A Combinational De-noising Algorithm for Low-Dose Computed Tomography.