位置：成果数据库 > 期刊 > 期刊详情页
基于局部颜色-空间特征的图像语义概念检测
  • ISSN号：1006-8961
  • 期刊名称：《中国图象图形学报》
  • 时间：0
  • 分类：TP301.6[自动化与计算机技术—计算机系统结构;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]上海交通大学电子工程系图像通信与信息处理研究所,上海200240, [2]上海市数字媒体处理与传输重点实验室,上海200240
  • 相关基金：国家自然科学基金项目（60502034,60625103）;国家863计划项目（1006AA01Z124）
作者： 刘洁敏[1,2], 姚豫[1,2], 张瑞[1,2], 杨小康[1,2]
关键词： 语义图像检索, 概念检测, 图像局部特征, 颜色-空间信息, semantic image retrieval, concept detection, image local feature, color-spatial feature
中文摘要：

针对基于语义的图像检索系统，提出了一种基于局部颜色-空间特征的图像语义概念检测方法。各种基于颜色、纹理和形状的全局特征都存在着众多信息冗余项和干扰项，而该文提出的局部颜色-空间特征则是利用语义概念层的先验知识进行特征降维后提取出的特征，它能更好地描述图像的语义内容，且具有容易提取、计算复杂度低的优点。实验结果表明，基于局部颜色-空间特征的概念检测方法优于基于全局特征的概念检测方法，将其用于图像检索后的检索精度比采用基于全局颜色特征的方法提高了36．4％。

英文摘要：

In this paper, a novel approach to semantic concept detection based on local color-spatial feature is proposed. There is much noise and redundant information in many global features of color, texture and shape. This local color-spatial feature contains more semantic contents of image than other global features by using prior knowledge of semantic concept level to reduce feature dimensions. Experiment results are reported and presented to demonstrate the effectiveness and efficiency of the proposed approach. Average precision of image retrieval by using the semantic concept detection method based on local color-spatial feature is 36.4% higher than the method based on global color feature.

同期刊论文项目
信息理论与信息系统
期刊论文 48 会议论文 48 获奖 1 专利 7
人眼视觉特性计算模型及其在数字图像通信中应用的研究
期刊论文 27 会议论文 19 专利 5
同项目期刊论文
基于语义概念的视频检索系统的设计与实现
一种基于 SIFT 算子的人脸识别算法
一种基于视觉注意模型的图像分类方法
基于局部特征的图像语义概念检测
基于视觉注意模型和 HMM 的足球视频语义分析
CamShift Guided Particle Filter for Visual Tracking
Unified deblocking for discrete cosine transfer compressed image
Transform domain transcoding from MPEG-2 to H.264 with interpolation drift-error compensation
Rate control for H.264 with two-step quantization parameter determination but single-pass encoding
Adaptive video-blocking artifact removal in discrete Hadamard transform domain
Perceptually-adaptive in-band preprocessing for 3-D wavelet video coding (vol 45, pg 030504, 2006)
Image quality metric with an integrated bottom-up and top-down HVS approach
用于H. 264 的Turbo 码非均等译码保护策略
H-infinity-optimal model for VBR video traffic prediction
Moving cast shadows detection using ratio edge
基于可伸缩视频编码 Hierarchical B 结构的恒定质量控制
基于卡尔曼滤波的 H.264 头信息量估计及其在帧级码率控制中的应用
自适应时域差错掩盖方法
基于动态规划的自适应关键帧提取算法
一种基于SIFT算子的人脸识别方法
基于视觉注意模型和HMM的足球视频语义分析
基于语义概念的视频检索系统的设计与实现
一种基于视觉注意模型的图像分类方法
高频段下新MIMO时域均衡算法仿真研究
C频段空地链路无线信道大尺度衰落模型
一种参数自适应的LDPC译码算法
Single Frequency Network System Coverage and Trial Testing of High Speed Railway Television System
一种快速高效的无线信道实现方法
A Ranging Method for OFDMA Uplink System
基于达芬奇平台的智能视频监控算法设计
Channel estimation joint DOAs and time delay correlation in TD-SCDMA mobile radio systems
A Novel Interference Cancellation Approach for Interleaved OFDMA Uplink System
Transmitter Identification With Watermark Signal in DVB-H Signal Frequency Network
An Improved Simulator for the Correlation-Based MIMO Channel in Multiple Cluster Scattering Environm
Directional Lapped Transforms for Image Coding
Optimal training design and placement for MIMO orthogonal frequency division multiplexing channel es
An implementation of the Decision Feedback Equalizer based on Delay-Matched structure
Group-of-pictures-based unequal error protection for scalable video coding extension of H.264/AVC
Low Complexity Channel Estimation Method for TDS-OFDM Based Chinese DTTB System
Iterative Approach for Multiuser Carrier Frequency Offset Estimation in Interleaved OFDMA Uplink
Intra-Predictive Transforms for Block-Based Image Coding
Distortion-Minimized Video Slicing for Unequal Loss Protection
Efficient quadtree based block-shift filtering for deblocking and deringing
Adaptive fractional window increment of TCP in multihop ad hoc networks
Robust Video Region-of-Interest Coding Based on Leaky Prediction
Multilevel framework to detect and handle vehicle occlusion
Frequency Domain Feed-forward Filter Combined DFE Structure in Single Carrier Systems over Time-vary
On Channel Estimation Method Using Time Domain Sequences in OFDM Systems
No-reference noticeable blockiness estimation in images
Efficient deblocking with coefficient regularization, shape-adaptive filtering, and quantization con
Improve throughput of TCP-Vegas in multihop ad hoc networks
A novel spatial and temporal correlation integrated based, motion-compensated interpolation for fram
Configurable multi-rate decoder architecture for QC-LDPC codes based broadband broadcasting system
Efficient image deblocking based on postfiltering in shifted windows
Unified deblocking for discrete cosine transfer compressed images
A Novel Channel Estimation Method Using Virtual Pilots in MIMO OFDM Systems
GOP-level transmission distortion modeling for mobile streaming video
Psycho-acoustic model in the wavelet domain
基于可伸缩视频编码Hierarchical-B结构的恒定质量控制
H.264兼容的全景视频编码方法
基于动态规划的自适应关键帧提取算法
基于MeanShift的抗遮挡运动目标跟踪算法
视频稳像技术综述
Optimal Training Design and Placement for MIMO Orthogonal Frequency Division Multiplexing Channel Estimation
一种基于SIFT算子的人脸识别方法
基于视觉注意模型和HMM的足球视频语义分析
期刊信息
  • 《数码影像》
  • 主管单位:
  • 主办单位:中国图象图形学学会 中科院遥感所 北京应用物理与计算数学研究所
  • 主编：
  • 地址：北京市海淀区花园路6号
  • 邮编：100088
  • 邮箱：
  • 电话：010-86211360 62378784
  • 国际标准刊号：ISSN：1006-8961
  • 国内统一刊号：ISSN：11-3758/TB
  • 邮发代号:
  • 获奖情况:
  • 国内外数据库收录:
  • 被引量:0