位置：立项数据库 > 立项详情页
光学影像处理与模式识别
  • 项目名称：光学影像处理与模式识别
  • 项目类别：国家杰出青年科学基金
  • 批准号：61125106
  • 申请代码：F010401
  • 项目来源：国家自然科学基金
  • 研究期限：2012-01-01-2015-12-31
  • 项目负责人：李学龙
  • 负责人职称：研究员
  • 依托单位：中国科学院西安光学精密机械研究所
  • 批准年度：2011
中文摘要：

申请人是国际上较早研究视觉信息张量分析的学者之一。针对张量鉴别分析提出的收敛学习框架为该方向的研究和应用提供了理论基础。所提出的张量分类器有效克服过学习难题。系列算法可显著改善图像的质量及系统的模式识别能力。取得的成果已在国家空间探测和遥感光学图像处理系统中得到应用，对特定观测图像处理起到重要作用。发表SCI论文100余篇，含IEEE汇刊46篇，4篇为IEEE Top 100下载。2次获IEEE汇刊和会议的最佳论文和提名，3篇Thomson Reuters Science Watch 热点论文，7篇入选Science Watch相关领域的国际36篇最重要文献。近5年内，SCI他引825次，Google Scholar引用2,000余次。H指数为25，Erd?s 数为3。担任4种IEEE汇刊编委和IEEE-SMC-CC技委会主席，是BCS, IAPR, IEE和SPIE的Fellow。

中文主题词： 图像处理；图像质量提高；多分辨分析；场景解析；模式识别
英文摘要：

Image Processing；Image Quality Improvement；Multiresolution Analysis；Scene Parsing；Pattern Recognition

英文主题词： Image Processing；Image Quality Improvement；Multiresolution Analysis；Scene Parsing；Pattern Recognition
结论摘要：

随着光学成像技术的飞速发展和普及，光学影像分析和识别方法越来越受到学者们的关注。为了满足新型光学成像系统的高智能性、高分辨性和高可靠性等的需求，本项目以智能化光学影像分析和学习为核心，研究和发展基于人工智能的光学影像分析和识别技术，开发基于采样和信息融合的光学多分辨率成像系统。具体地，本项目主要研究图像质量提高、视觉显著性表示、遥感图像分析和解析、遥感图像分类和检索等四个课题。这四个课题也是光学影像分析和模式识别系统的核心任务。经过四年的努力，我和合作者在图像质量提高和评价方面、显著性特征表示、遥感图像分析和解析、图像分类和检索等方面提出了一些比较有效的算法。例如，我们提出了一种基于最大后验分布的场景解析算法。该算法通过低秩表示来学习类条件概率，进而用马尔科夫随机场来学习像素类别的先验上下文分布，并通过这两个分布计算后验分布，从而最终的场景解析结果。在标准数据集上的实验结果显示，我们的算法比同类算法表现出了较好的解析效果。本项目所取得的成果对于进一步研究光学影像分析和模式识别问题可能会具有一定的科学意义，并且也可能会在新型光学影像分析和识别系统的设计方面具有一定的参考价值.

成果综合统计
成果类型
数量
  • 期刊论文
  • 会议论文
  • 专利
  • 获奖
  • 著作
  • 183
  • 25
  • 0
  • 20
  • 0
期刊论文
Prostate Segmentation in MR Images Using Discriminant Boundary Features
Power line detection from optica limages
Mean shift based gradient vector flow for image segmentation
Intrinsic Images Decomposition Using Optimization and User Scribbles
Biologically Inspired Features for Scene Classification in Video Surveillance
Sparse Kernel Entropy Component Analysis for Dimensionality Reduction of Biomedical Data
Secrecy Outage and Diversity Analysis of Cognitive Radio Systems
Automatic Segmentation of Breast Lesions for Interaction in Ultrasonic Computer-Aided Diagnosis
Large-Scale Aerial Image Categorization using a Multi-Task Topological Codebook
Targeting Accurate Object Extraction from An Image: A Comprehensive Study of Natural Image Matting
Joint Optimization towards Effective and Efficient Image Search
Single Image Super-Resolution With Multiscale Similarity Learning
GA-SIFT: A new scale invariant feature transform for multispectral image using geometric algebra
Action recognition by spatio-temporal oriented energies
From Heuristic Optimization to Dictionary Learning: A Review and Comprehensive Comparison of Image D
Image esthetic assessment using both hand-crafting and semantic features
Hessian Regularized Support Vector Machines for Mobile Image Annotation on the Cloud
Event-Based Media Enrichment using an Adaptive Probabilistic Hypergraph Model
Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
A Local Structural Descriptor for Image Matching via Normalized Graph Laplacian Embedding
Large-Scale Unsupervised Hashing with Shared Structure Learning
Relevance Preserving Projection and Ranking for Web Image Search Reranking
Biclustering Learning of Trading Rules
Structured-Patch Optimization for Dense Correspondence
A Fine-Grained Image Categorization System by Cellet-Encoded Spatial Pyramid Modeling
Spatio-Chromatic Context Modeling for Color Saliency Analysis
Multiple Representations-based Face Sketch-Photo Synthesis
Efficient Video Stitching Based on Fast Structure Deformation
场景图像分类技术研究综述
Evolutionary Compact Embedding for Large-scale Image Classification
Locality and Similarity Preserving Embedding for Feature Selection
Parallelized Evolutionary Learning for Detection of Biclusters
Adaptive Shape Prior Constrained Level Sets for Bladder MR Image Segmentation
Power line detection from optical images
LDFT-Based Watermarking Resilient to Local Desynchronization Attacks
Contrast Enhancement-Based Forensics in Digital Images
Spectral-Spatial Constraint Hyperspectral Image Classification
Learning Deep and Wide: A Spectral Method for Learning Deep Networks
Adaptive fusion of particle filtering and spatio-temporal motion energy for human tracking
Shrink image by feature matrix decomposition
Integrate the original face image and its mirror image for face recognition
Linear Tracking for 3-D Medical Ultrasound Imaging
Robust Hashing with Local Models for Approximate Similarity Search
Data Uncertainty in Face Recognition
Feature Learning for Image Classification via Multiobjective Genetic Programming
Actively Learning Human Gaze Shifting Paths for Semantics-Aware Photo Cropping
Hierarchical incorporation of shape and shape dynamics for flying bird detection
Object-Aware Power Line Detection Using Color and Near-Infrared Images
Learning Compact Feature Descriptor and Adaptive Matching Framework for Face Recognition
Bezier Interpolation for 3-D Freehand Ultrasound
Compact Structure Hashing via Sparse and Similarity Preserving Embedding
Truncation Error Analysis on Reconstruction of Signal from Unsymmetrical Local Average Sampling
Fusion of Multichannel Local and Global Structural Cues for Photo Aesthetics Evaluation
Scene Parsing from an MAP Perspective
Deep Image Saliency Computing via Progressive Representation Learning
Detecting Densely Distributed Graph Patterns for Fine-grained Image Categorization
A-Optimal Projection for Image Representation
Nonnegative Multiresolution Representation Based Texture Image Classification
Mutual Component Analysis for Heterogeneous Face Recognition
Joint Multilabel Classification with Community-Aware Label Graph Learning
Video Parsing via Spatiotemporally Analysis with Images
大数据系统综述
Image Classification with Densely Sampled Image Windows and Generalized Adaptive Multiple Kernel Lea
Transfer Learning for Visual Categorization: A Survey
Texture Classification and Retrieval Using Shearlets and Linear Regression
Toward Scalable Systems for Big Data Analytics: A Technology Tutorial
A Probabilistic Associative Model for Segmenting Weakly Supervised Images
Realistic Action Recognition Via Sparsely-constructed Gaussian Processes
Pylon Line Spatial Correlation Assisted Transmission Line Detection
Efficient Closed-loop Multiple-view Registration
Toward Multiscreen Social TV with Geolocation-Aware Social Sense
Semi-Supervised Multitask Learning for Scene Recognition
Robust Video Object Cosegmentation
A Variational Approach to Simultaneous Image Segmentation and Bias Correction
Robust Match Fusion Using Optimization
Learning a Probabilistic Topology Discovering Model for Scene Categorization
Graph-Based Learning for Segmentation of 3D Ultrasound Images
Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction
Local Coordinate Concept Factorization for Image Representation
Heterogeneous image transformation
Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search
Facial Skin Beautification Using Adaptive Region-Aware Masks
A Novel Visual Codebook Model Based on Fuzzy Geometry for Large-Scale Image Classification
Event analysis in social multimedia： a survey
Robust Text Detection in Natural Scenes Using Text Geometry and Visual Appearance
会议论文
A Maximum Entropy Feature Descriptor for Age Invariant Face Recognition
Image Super-Resolution Using Multi-layer Support Vector Regression
Complementary Projection Hashing
Image Super-resolution via Non-local Steering Kernel Regression Regularization
Sparse Representation for Blind Image Quality Assessment
A New Sparse Feature-based Patch for Dense Correspondence
Multi-scale Dictionary for Single Image Super-resolution
Coupled Directional Level Set for MR Image Segmentation
Compressed Hashing
Learning Hash Functions Using Sparse Reconstruction
Local Learning-Based Image Super-Resolution
A-Optimal Non-negative Projection for Image Representation
Color Fractural Structure Model for Reduced-Reference Colorful Image Quality Assessment
Matrix Completion by Truncated Nuclear Norm Regularization
Geometry Constrained Sparse Coding for Single Image Super-resolution
PUTTING IMAGES ON A MANIFOLD FOR ATLAS-BASED IMAGE SEGMENTATION
Toward a Biometric-Aware Cloud Service Engine for Multi-Screen Video Applications
Beyond Spatial Pyramids: A New Feature Extraction Framework with Dense Spatial Sampling for Image Cl
Multi-Atlas based Image Segmentation with Label Image Constraint
Learning to Detect Stereo Saliency
Hyperspectral Biological Images Compression Based on Multiway Tensor Projection
Representative and Diverse Video Summarization
Person Re-identification by Bidirectional Projection
Local Structure Divergence Index for Image Quality Assessment
Building Holistic Descriptors for Scene Recognition: A Multi-objective Genetic Programming Approach
获奖
2014 IEEE ICDM 10-Year Highest Impact Paper Award
2015 IEEE MultiMedia Best Paper Award
ACM ICIMCS 2014 Best Paper
OSA Fellow
中国青年五四奖章
中青年科技创新领军人才
国家百千万人才工程国家级人选
何梁何利基金科学与技术创新奖
2014 IEEE ICDM 10-Year Highest Impact Paper Award
2015 IEEE MultiMedia Best Paper Award
ACM ICIMCS 2014 Best Paper
OSA Fellow
IEEE Fellow
陈嘉庚青年科学奖
IEEE Fellow
陈嘉庚青年科学奖
中国青年五四奖章
中青年科技创新领军人才
国家百千万人才工程国家级人选
何梁何利基金科学与技术创新奖
相关项目
基于动态CT多期图像的早期肝癌CAD技术研究
期刊论文 17 会议论文 8 专利 1 著作 1
基于机器视觉的新疆库尔勒香梨品质无损检测方法研究
期刊论文 5 会议论文 4
基于图像处理技术的输电线路故障诊断
期刊论文 15 会议论文 3 专利 2
图像处理中最优化方法的研究
期刊论文 28 会议论文 9
基于图像识别的糖尿病视网膜病变自动诊断技术研究
期刊论文 10 会议论文 15 专利 8
基于图像处理的带钢表面缺陷自动识别技术
期刊论文 13 会议论文 1
X射线数字图像智能识别及自动检测技术基础研究
期刊论文 8 会议论文 3
视频检索关键问题研究及其在敏感信息识别中的应用
期刊论文 3 会议论文 4
关于流形学习的有效性算法与特征提取解释理论研究
期刊论文 17
李学龙的项目
快速鲁棒迁移子空间算法
期刊论文 58 会议论文 34