Web环境下基于移动多Agent技术的CBIR系统

采用移动多Agent技术,提出了一种灵活的基于内容的Web图像检索系统模型。系统将传统的Web图像检索功能封装于不同的Agent中。各Agent自主运行并相互协调,共同完成分布式Web图像检索。由于图像搜索策略封装于移动Agent中,可在数据源本地实现快速的图像匹配,减少了网络信息交换;网络管理Agent消除了异构网络带来的通信障碍。实验表明该图像检索系统具有良好的自治性、伸缩性和适应性以及灵活的在线扩展能力。     

基于内容的图象检索及其相关技术的研究

基于内容和图象检索技术，即从大量的静或活动视频图象库中检索包含目标物体的图象，在高度信息化的今天，已成为内容图象库中图象信息组织和管理不可缺少的技术术。     

Image retrieval based on non-uniform bins of color histogram and dual tree complex wavelet transform

Multimedia Tools and Applications - Traditional Content-Based Image Retrieval (CBIR) systems were developed for retrieving similar kinds of images from a whole image database based on the given...     

Parallel Local Histogram Comparison Hardware Architecture for Content-Based Image Retrieval

The explosive growth of the World Wide Web has made a vast amount of information available especially the multimedia data such as images and graphics. New generation search engines with the technology of Content-Based Image Retrieval (CBIR) is a response to the need. In this paper, a new technique based on composite local colour histograms suitable for CBIR is described. The proposed approach is accurate even in very large image databases. Furthermore, a novel parallel hardware structure has been designed and implemented on a chip-set of FPGAs, in order to increase the operation speed. Its typical maximum clock frequency is 35 MHz and it can perform over 50 comparisons of 640×480-pixel images per second.     

图象内容检索中的相似性度量和分层索引

基于内容的图象检索是图象理解应用于多媒体领域的产物,是下一代智能多媒体数据库的关键技术。本文针对基于内容的静态图象检索,提出了一种度量图象间相似程度的方法,同时还给出了一个通过分层聚类构造二叉树式分层索引数据结构的算法。     

基于内容的图象检索系统的设计与实现

依据当前对图象查询的要求,本文设计了一套完整的基于内容的图象信息检索系统,该系统较以往的各种系统,功能更加全面。对基于内容的图象信息检索算法作了研究．重点阐述了对颜色、边缘、纹理等全局特征的提取与匹配算法。实验结果表明,该系统能有效、快速地检索大规模的图象数据库,具有一定的应用价值。     

Further results on dissimilarity spaces for hyperspectral images RF-CBIR

Content-Based Image Retrieval (CBIR) systems are powerful search tools in image databases that have been little applied to hyperspectral images. Relevance feedback (RF) is an iterative process that uses machine learning techniques and user’s feedback to improve the CBIR systems performance. We pursued to expand previous research in hyperspectral CBIR systems built on dissimilarity functions defined either on spectral and spatial features extracted by spectral unmixing techniques, or on dictionaries extracted by dictionary-based compressors. These dissimilarity functions were not suitable for direct application in common machine learning techniques. We propose to use a RF general approach based on dissimilarity spaces which is more appropriate for the application of machine learning algorithms to the hyperspectral RF-CBIR. We validate the proposed RF method for hyperspectral CBIR systems over a real hyperspectral dataset.     

基于概念级语义的图像描述与识别

由于计算机自动提取的图像视觉特征与人所理解的图像内容存在巨大的差异,传统的低层的视觉特征(如颜色、纹理、形状等)CBIR(Content-Based Image Retrieval)系统的检索结果往往不尽如人意.近年来,根据概念级语义(如男孩、高兴、浪漫等)的CBIR引起了研究者的重视.本文对CBIR领域的大量文献进行了深入的分析,从工程角度综述了图像概念级语义的描述模型、概念级语义特征提取和概念级语义图像检索问题的研究进展,并阐述了作者的一些观点.     

结合改进CNN和双线性模型的CBIR方法

针对现有基于内容的图像检索（Content-Based Image Retrieval,CBIR）方法中图像特征维度较大等问题,提出一种结合改进卷积神经网络（Convolutional Neural Network,CNN）和双线性模型的CBIR方法。采用一种低维度池化方法代替传统CNN中的池化过程,以此降低图像特征映射的维度。基于双线性模型的思想,使用两个特征提取器进行特征提取,并在每个图像位置上对两个特征进行内积,以形成最终的图像描述符。通过计算图像间的曼哈顿距离度量来评估相似性,获得相关图像及其排序。实验结果表明,该方法能够准确检索出相关图像,并具有较低的检索时间和内存消耗。     

综合颜色和纹理特征的图像检索算法

基于内容的图像检索是当前多媒体信息检索的热点之一。基于内容的图像检索技术是根据对图像内容(特征)的描述和提取,在图像库中找到具有指定内容(特征)的图像。本文对图像颜色特征和纹理特征的提取、相似性度量等基于内容的图像检索的关键技术进行了分析和研究,并在此基础上,提出了一个基于颜色特征和纹理特征的图像检索算法并验证了其有效性。该算法采用HSV颜色空间的直方图作为颜色特征向量,采用灰度共生矩阵的四个纹理特征:能量、熵、惯性矩和相关性构成纹理特征向量,采用欧氏距离进行相似性度量。实验结果表明,该算法实现的系统具有良好的图像检索功能。     

State of the art content based image retrieval techniques using deep learning: a survey

In the recent years the rapid growth of multimedia content makes the image retrieval a challenging research task. Content Based Image Retrieval (CBIR) is a technique which uses features of image to search user required image from large image dataset according to the user’s request in the form of query image. Effective feature representation and similarity measures are very crucial to the retrieval performance of CBIR. The key challenge has been attributed to the well known semantic gap issue. The machine learning has been actively investigated as possible solution to bridge the semantic gap. The recent success of deep learning inspires as a hope for bridging the semantic gap in CBIR. In this paper, we investigate deep learning approach used for CBIR tasks under varied settings from our empirical studies; we find some encouraging conclusions and insights for future research.

     

基于内容的图像检索介绍

基于内容特征的图象检索(CBIR)是目前国内外研究的一个热点。本文简要介绍了基于内容的图像检索技术的发展过程及主要原理,重点论述了基于内容的图像检索常用关键技术——图像视觉特征的描述和提取。     

Learning a Maximum Margin Subspace for Image Retrieval

One of the fundamental problems in Content-Based Image Retrieval (CBIR) has been the gap between low-level visual features and high-level semantic concepts. To narrow down this gap, relevance feedback is introduced into image retrieval. With the user-provided information, a classifier can be learned to distinguish between positive and negative examples. However, in real-world applications, the number of user feedbacks is usually too small compared to the dimensionality of the image space. In order to cope with the high dimensionality, we propose a novel semisupervised method for dimensionality reduction called Maximum Margin Projection (MMP). MMP aims at maximizing the margin between positive and negative examples at each local neighborhood. Different from traditional dimensionality reduction algorithms such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), which effectively see only the global euclidean structure, MMP is designed for discovering the local manifold structure. Therefore, MMP is likely to be more suitable for image retrieval, where nearest neighbor search is usually involved. After projecting the images into a lower dimensional subspace, the relevant images get closer to the query image; thus, the retrieval performance can be enhanced. The experimental results on Corel image database demonstrate the effectiveness of our proposed algorithm.     

基于内容的遥感图像变化信息检索概念模型设计

在海量遥感数据背景下,传统的基于关键字/元数据数据服务模式,无法满足不同应用领域用户对多样化遥感变化信息数据的获取需求。将基于内容的图像检索技术应用到遥感图像变化信息数据获取中,提出了一种全新的基于内容的遥感图像变化信息检索概念模型。通过深入分析当前基于内容的图像检索的先进理论方法,构建基于内容的遥感图像变化信息检索模型框架,并对变化信息数据管理模型构建、多维特征提取和智能反馈模型创建等关键问题进行研究和算法实现,以中低分辨率遥感图像变化信息数据获取为例来进行模型验证与分析,建立原型系统。该方法作为一种新的遥感图像变化信息获取与服务方式,能有效利用遥感图像中底层特征,更准确地刻画了不同用户的遥感图像变化信息检索需求。同时,对影像的预处理要求较低,不受变化检测产品生产种类限制,具有较好普适性和自动化性,提高了遥感信息服务水平和效率。     

Design of Content-based Remote Sensing Image Change Information Retrieval and Relevance Feedback Model

With the rapid development of satellite remote sensing technology, processing the variety of remotely sensed data has increasingly been complex and difficult. It is also hard to efficiently and intelligently retrieve change information what users need from a massive database of images. In the context of mass remote sensing data, the existing knowledge based on a priori knowledge + the keyword / metadata remote sensing data service model can not meet above-mentioned challenge. Firstly，it is not guaranteed to obtain the totally change information data in the database, as we can not get the all prior knowledge. Second, the keyword / metadata can not accurately describe the different application areas of the user's actual retrieval needs. To deal with this, the Content-Based Image Retrieval (CBIR) is successfully applied on the change detection in this paper. And, Content-Based Remote Sensing Image Change Information Retrieval and Relevance Feedback model is introduced. Firstly, we learn the CBIR theory fully and exclusively. Then, the model structure and framework is built. And, some critical issues, such as data management, multi-features selection and relevance feedback, are considered. Thirdly, an experimental prototype system is set up to demonstrate the validity and practicability of this model. As a new remote sensing image change detection information acquisition mode, the new model can reduce the demands of image pre-processing, overcome synonyms spectrum, seasonal changes and other factors in the change detection, and meet different kinds of needs. Meanwhile, the new model has important implications for improving remote sensing image management skill and autonomic capabilities of information retrieval filed.     

Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval

Self-Organising Maps (SOMs) can be used in implementing a powerful relevance feedback mechanism for Content-Based Image Retrieval (CBIR). This paper introduces the PicSOM CBIR system, and describes the use of SOMs as a relevance feedback technique in it. The technique is based on the SOM’s inherent property of topology-preserving mapping from a high-dimensional feature space to a two-dimensional grid of artificial neurons. On this grid similar images are mapped in nearby locations. As image similarity must, in unannotated databases, be based on low-level visual features, the similarity of images is dependent on the feature extraction scheme used. Therefore, in PicSOM there exists a separate tree-structured SOM for each different feature type. The incorporation of the relevance feedback and the combination of the outputs from the SOMs are performed as two successive processing steps. The proposed relevance feedback technique is described, analysed qualitatively, and visualised in the paper. Also, its performance is compared with a reference method.     

基于内容的图像检索技术综述

随着计算机网络以及多媒体技术的飞速发展,基于文本的传统图像搜索已经不能满足高效准确的要求,所以基于内容的图像检索(Content-Based Image Retrieval,简称CBIR)技术越来越受到用户们的重视。本文对CBIR技术的主要原理与方法进行了分析并对以后的发展趋势进行了展望。