位置：成果数据库 > 期刊 > 期刊详情页
基于双树复数小波变换的图像清晰度判定
  • ISSN号：1006-2467
  • 期刊名称：《上海交通大学学报》
  • 时间：0
  • 分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]上海交通大学图像处理与模式识别研究所,上海200240
  • 相关基金：国家自然科学基金资助项目（60675023）;国家重点基础研究发展规划（973）项目（51323020203-2）
作者： 郭敬明[1], 杨杰[1], 李鸿升[1], 黎明[1]
关键词： 图像清晰度, 双树复数小波, 细分, image foeus, dual-tree complex wavelet, decomposition
中文摘要：

提出了一种新的图像清晰度评价方法.该方法基于双树复数小波变换，定义高频带与低频带2-范数的比值作为图像清晰度的判定准则.实验结果表明，所提出的方法优于传统的图像清晰度准则，区分效果好，评价结果更为准确、可靠.

英文摘要：

A new measure of image focus was proposed. Based on DTCWT（dual-tree complex wavelet transform） ,a ratio of high-pass band and low-pass band norms is defined as a measure of image focus. The experiments show that the proposed measure of image focus is better than the existing measure of image focus, and has more exact and reliable results.

同期刊论文项目
复杂场景下稳健视觉跟踪算法研究
期刊论文 60 会议论文 7 专利 3
同项目期刊论文
基于粒子滤波的红外目标跟踪
Multi-information incorporation approach to kernel-based infrared target model construction with app
A face detection and recognition system in color image series
Locality preserving projections plus affinity propagation: A fast method for face recognition
Local Coordinates Alignment (LCA): A novel manifold learning approach
Infrared small target detection using PPCA
Multimodal biometrics using geometry preserving projections
基于主成份分析的仿射不变特征图像匹配方法
Segmenting foreground from similarly colored background
Self-detection of optical contamination or occlusion in vehicle vision systems
Foreground segmentation based on selective foreground model
Accurate extraction of infrared target based on graph cut
Small target detection using two-dimensional least mean square (TDLMS) filter based on neighborhood
核Fukunaga-Koontz变换检测红外小目标
复杂背景下圆形红外目标跟踪系统
基于正则化Adaboost的红外目标识别
融合关注度和空间投影的核跟踪算法
Performance evaluation of foreground modeling in moving foreground segmentation
Improved algorithm for multiple infrared targets tracking
Multi-feature based Ensemble Classification and Regression Tree (ECART) for target tracking in infra
Face recognition using message passing based clustering method
Detecting infrared small target by using TDLMS filter based on neighborhood analysis
一种改进的红外多目标跟踪算法
Foreground segmentation based on tracking
A novel algorithm to segment foreground from a similarly colored background
Target tracking in infrared imagery using a novel particle filter
Patch Alignment for Dimensionality Reduction
General moving objects recognition method based on graph embedding dimension reduction algorithm
Moving object detection based on shape prediction
The analysis of the color similarity problem in moving object detection
Target tracking based on a hybrid tracker with two hierarchical appearance models
Maximum variance projections for face recognition
Infrared small target detection with kernel Fukunaga-Koontz transform
Automatically detect and track infrared small targets with kernel Fukunaga-Koontz transform and Kalm
Automatic extraction of infrared small target based on support vector regression and adaptive region
Feature selection based on rough sets and particle swarm optimization
Subspace evolution analysis for face representation and recognition
Linear local tangent space alignment and application to face recognition
基于红外背景复杂程度描述的小目标检测算法
基于正则化观测矢量的H无穷粒子滤波红外目标跟踪方法
Point target detection of infrared images with eigentargets
Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measur
Integrating affinity propagation clustering method with linear discriminant analysis for face recogn
基于SIFT的图像配准方法
基于Hǒlder指数和ICA的海域SAR图点目标检测
基于AIF的三角形网格切割方法
自动多投影仪非线性几何校正与图像边缘融合方法
局部坐标排列
一种简化的医学图像中轴提取算法
基于编辑距离的轨迹相似性度量
基于支持向量机的彩色序列图像复原模型更新算法
Support Vector Regression Based Color Image Restoration in YUV Color Space
ICA Based Speckle Filtering for Using Adaptive Target Extraction in SAR Images Space Separation
Unsupervised Color-texture Image Segmentation
基于支持向量机的湍流退化图像加速复原算法
核Fukunaga—Koontz变换检测红外小目标
期刊信息
  • 《上海交通大学学报》
  • 中国科技核心期刊
  • 主管单位:中华人民共和国教育部
  • 主办单位:上海交通大学
  • 主编：郑杭
  • 地址：上海市华山路1954号15F
  • 邮编：200030
  • 邮箱：shjt@chinajournal.net.cn
  • 电话：021-62933373 62932534
  • 国际标准刊号：ISSN：1006-2467
  • 国内统一刊号：ISSN：31-1466/U
  • 邮发代号:4-256
  • 获奖情况:
  • 1996年全国优秀科技期刊奖,1992年、1996年、1999年国家教育部系统优秀科技期刊奖,2002年“百种重点期刊奖”,2003年百种中国杰出学术期刊,2004年教育部全国高校优秀科技期刊一等奖,2004年“百种重点期刊奖”
  • 国内外数据库收录:
  • 美国化学文摘（网络版）,美国数学评论（网络版）,德国数学文摘,荷兰文摘与引文数据库,美国工程索引,美国剑桥科学文摘,英国科学文摘数据库,日本日本科学技术振兴机构数据库,中国中国科技核心期刊,中国北大核心期刊（2004版）,中国北大核心期刊（2008版）,中国北大核心期刊（2011版）,中国北大核心期刊（2014版）,中国北大核心期刊（2000版）
  • 被引量:30903