综合颜色与纹理的图像检索

提出了组合颜色和纹理特征的图像检索方法,通过对颜色进行量化然后提取颜色特征,计算图像之间的颜色距离.用Gabor变换提取图像的纹理特征然后根据L2距离计算图像的纹理距离,利用颜色特征和纹理特征的加权来求检索图像和查询图像的相似度,根据相似度的大小来进行图像的检索.实验结果表明,基于组合特征的图像检索方法优于单纯的图像检索方法.     

基于跨媒体字典的图像检索

当前存在的图像检索大多是基于内容的检索,为提高检索的准确率,通过整合文本及视觉信息,提出一种自动将文本查询转化为可视化表示的方法,实现基于跨媒体字典的图像检索。采用标注图像集挖掘文本和图像间的关系,训练建立一个类似于双语字典的跨媒体字典,自动将文本查询转化为视觉查询,分别进行基于文本和基于视觉的图像检索,将2种方法检索到的图像合并作为最终检索结果。实验结果表明,该方法能有效地提高图像的查准率。     

基于文本与语义相关性分析的图像检索

为了更加有效地检索到符合用户复杂语义需求的图像，提出一种基于文本描述与语义相关性分析的图像检索算法。该方法将图像检索分为两步：基于文本语义相关性分析的图像检索和基于SIFT特征的相似图像扩展检索。根据自然语言处理技术分析得到用户文本需求中的关键词及其语义关联，在选定图像库中通过语义相关性分析得到“种子”图像；接下来在图像扩展检索中，采用基于SIFT特征的相似图像检索，利用之前得到的“种子”图像作为查询条件，在网络图像库中进行扩展检索，并在结果集上根据两次检索的图像相似度进行排序输出，最终得到更加丰富有效的图像检索结果。为了证明算法的有效性，在标准数据集Corel5K和网络数据集Deriantart8K上完成了多组实验，实验结果证明该方法能够得到较为精确地符合用户语义要求的图像检索结果，并且通过扩展算法可以得到更加丰富的检索结果。     

基于目标区域的语义图像检索

提出了一种基于高层语义的图像检索方法,该方法首先将图像分割成区域,提取每个区域的颜色、形状、位置特征,然后使用这些特征对图像对象进行聚类,得到每幅图像的语义特征向量;采用模糊C均值算法对图像进行聚类,在图像检索时,查询图像和聚类中心比较,然后在距离最小的类中进行检索。实验表明,提出的方法可以明显提高检索效率,缩小低层特征和高层语义之间的“语义鸿沟”。     

基于图像数据挖掘的有向图模型检索方法

为充分挖掘图像数据信息,提出了一种有向图模型检索方法,结合距离测度初次检索和有向图距离二次检索提高图像检索性能。首先,采用传统的纹理、边缘和颜色特征以及特征之间的欧氏距离测度来进行初次检索,得到一个查询排序列表;在此基础上,结合距离测度与余弦测度设计图像之间的相关测度,在不同的相关测度阈值下构建图像数据集的有向图模型集合;最后,计算有向图距离,据此进行二次检索,降低误检现象。在COREL和ImageCLEF两个数据集上的图像检索实验结果表明,该方法的平均精确度和平均召回率指标高。     

基于哈希编码和卷积神经网络的图像检索方法

针对图像检索,提出一种基于哈希编码和卷积神经网络的方法。主要是在卷积神经网络（CNN）中加入哈希层,采用由粗到精的分级检索策略,根据学习到的哈希码进行粗检索得到与查询图像相同或相似的[m]幅图像构成图像池,计算池内图像与查询图像高层语义特征之间的欧氏距离进行精检索,达到最终的检索目的。提出方法将哈希层的损失作为优化目标之一,结合图像的两种特征进行检索,弥补了现有方法中直接利用CNN深层特征检索耗时、占用内存的不足。在印花织物和CIFAR-10数据集上的实验结果表明,提出方法检索性能优于其他现有方法。     

改进五叉树分解法在遥感图像检索中的应用

由于一幅遥感图像是对一定范围内的地表状态的成像,并且遥感图像具有多样性、复杂性、海量等性质,致使遥感图像检索往往是查询图像和图像库图像的局部区域之间的相似性匹配。为了提高遥感图像的检索效率,必须首先对遥感图像进行分解。提出了一种将遥感图像分层分解的遥感图像检索方法,该方法利用改进五叉树分解法将图像库图像按层次分解成不同大小的子图,在提取子图的纹理特征后,以查询图像和图像库子图之间的欧式距离衡量图像相似度,实现了遥感图像检索。利用海地地震时的航空遥感图像作为实验数据,应用改进五叉树分解法将遥感图像分解后,进行查询检索实验,并与普通五叉树进行了对比。实验结果表明利用改进五叉树分解法进行遥感图像分解后得到的分块图像,可以更精准地查询出用户真正感兴趣的部分,能够获得较高的查全率和查准率,提高查询效率。     

基于高阶模式间关系的跨模态关联学习

针对多模态数据查询和基于模式之间低阶关系的查询方法存在的局限性,提出一种基于高阶模式之间关系的跨模态关联学习模型。在超网络的基础上,构建一种具有层次结构的分层超网络模型,由超网络数目等于模式数目的模式层和代表几种模式之间关系的集成层构成;经过训练的分层超网络就可以通过跨模态关联推理生成对于给定多模态查询的文本术语和视觉词关键字,实现多模态查询。基于大量带有图像文章的实验结果表明,提出模型可以提高生成关键字的相似性,生成文本术语,成功检索出具有小部分信息的文章。     

基于对象空间关系的图像检索方法研究

描述了图像中对象之间的拓扑关系、投影间隔关系和角度关系,给出了不同空间关系距离的定义,提出了集成查询图像与数据库图像中共有对象数目和空间关系的图像相似性度量方法。实验证明,利用该相似性度量方法实现的图像检索系统的检索精度是较高的。     

基于访问控制安全高效的多用户外包图像检索方案

由于公有云不是可信的实体,通过公有云提供图像检索服务时,它可能会窃取图像数据的敏感信息。近年来,密文图像检索方法被提出,用于保护图像隐私。然而,传统的隐私保护图像检索方案搜索效率较低,且无法支持多用户场景。因此,提出一种基于访问控制安全高效的多用户外包图像检索方案。该方案采用一次一密和矩阵变换方法,实现基于欧几里得距离（简称欧氏距离）相似性的密文图像检索,并利用矩阵分解和代理重加密,实现多用户外包图像检索。采用局部敏感哈希算法构建索引,提高密文图像检索效率。特别地,提出一种基于角色多项式函数的轻量级访问控制策略,该策略能够灵活设定图像访问权限,防止恶意用户窃取隐私信息。安全性分析论证了所提方案能够保护图像和查询请求的机密性;实验结果表明所提方案能够达到高效的图像检索。     

面向细粒度草图检索的对抗训练三元组网络

将草图作为检索示例用于图像检索称之为基于草图的图像检索.在这其中,细粒度检索问题或类内检索问题是2014年被研究者提出并快速成为广受关注的研究方向.目前研究者通常用三元组网络来解决类内检索问题,且取得了不错的效果.但是三元组网络的训练非常困难,很多情况下很难收敛甚至不收敛,且存在着容易过拟合的风险.本文借鉴循环生成对抗训练的思想,设计了SketchCycleGAN帮助提高三元组网络训练过程的效率,以对抗训练的方式使其参与到三元组网络的训练过程中,通过充分挖掘数据集自身信息的方式取代了利用其他数据集进行预训练的过程,在简化训练步骤的基础上取得了更好的检索性能.通过在常用的细粒度草图检索数据集上的一系列对比实验,证明了所提方法的有效性和优越性.     

动态匹配核函数图像检索

目的 在传统的词袋模型图像搜索问题中,许多工作致力于提高局部特征的辨识能力。图像搜索得到的图像在细节部分和查询图像相似,但是有时候这些图像在语义层面却差别很大。而基于全局特征的图像搜索在细节部分丢失了很多信息,致使布局相似实则不相关的图像被认为是相关图像。为了解决这个问题,本文利用深度卷积特征来构建一个动态匹配核函数。方法 利用这个动态匹配核函数,在鼓励相关图像之间产生匹配对的同时,抑制不相关图像之间匹配对的个数。该匹配核函数将图像在深度卷积神经网络全连接层最后一层特征作为输入,构建一个动态匹配核函数。对于相关图像,图像之间的局部特征匹配数量和质量都会相对增强。反之,对于不相关的图像,这个动态匹配核函数会在减少局部特征匹配的同时,降低其匹配得分。结果 从数量和质量上评估了提出的动态匹配核函数,提出了两个指标来量化匹配核函数的表现。基于这两个指标,本文对中间结果进行了分析,证实了动态匹配核函数相比于静态匹配核函数的优越性。最后,本文在5个公共数据集进行了大量的实验,在对各个数据集的检索工作中,得到的平均准确率从85.11%到98.08%,均高于此领域的同类工作。结论 实验结果表明了本文方法是有效的,并且其表现优于当前这一领域的同类工作。本文方法相比各种深度学习特征提取方法具有一定优势,由于本文方法使用特征用于构建动态匹配内核,而不是粗略编码进行相似性匹配,因此能在所有数据集上获得更好的性能。     

Automatic image–text alignment for large-scale web image indexing and retrieval

In this paper, an automatic image–text alignment algorithm is developed to achieve more effective indexing and retrieval of large-scale web images by aligning web images with their most relevant auxiliary text terms or phrases. First, a large number of cross-media web pages (which contain web images and their auxiliary texts) are crawled and segmented into a set of image–text pairs (informative web images and their associated text terms or phrases). Second, near-duplicate image clustering is used to group large-scale web images into a set of clusters of near-duplicate images according to their visual similarities. The near-duplicate web images in the same cluster share similar semantics and are simultaneously associated with a same or similar set of auxiliary text terms or phrases which co-occur frequently in the relevant text blocks, thus performing near-duplicate image clustering can significantly reduce the uncertainty on the relatedness between the semantics of web images and their auxiliary text terms or phrases. Finally, random walk is performed over a phrase correlation network to achieve more precise image–text alignment by refining the relevance scores between the web images and their auxiliary text terms or phrases. Our experiments on algorithm evaluation have achieved very positive results on large-scale cross-media web pages.     

基于快速小波变换的高适应性图像检索技术研究

在目前已有的研究工作中,基于自适应小波的图像特征在基于内容的图 像检索领域获得了广泛的应用。但这些方法存在一个共同问题,即采用相同的小波基描述不 同的查询图像。为了提高图像检索技术的自适应能力,本文对不同的查询图像设计不同的小 波基表示,从而实现用可调整的距离测度表征不同类别图像的特征改变。为了进一步降低表 征图和表征导数图的求取时间,该文使用了近似泰勒展开。实验结果表明,这种新的图像检 索技术具有高度的自适应能力,检索性能也大幅度提高。     

Near-duplicate document image matching: A graphical perspective

A near-duplicate document image matching approach characterized by a graphical perspective is proposed in this paper. Document images are represented by graphs whose nodes correspond to the objects in the images. Consequently, the image matching problem is then converted to graph matching. To deal with the instability of object segmentation, a multi-granularity object tree is constructed for a document image. Each level in the tree corresponds to one possible object segmentation, while different levels are characterized by various object granularities. Some graphs can be generated from the tree and the objects associated with each graph may be of different granularities. Two graphs with the maximum similarity are found from the multi-granularity object trees of the two near-duplicate document images which are to be matched. The encouraging experimental results have demonstrated the effectiveness of the proposed approach.     

Multiscale video sequence matching for near-duplicate detection and retrieval

As one of key technologies in content-based near-duplicate detection and video retrieval, video sequence matching can be used to judge whether two videos exist duplicate or near-duplicate segments or not. Despite a lot of research efforts devoted in recent years, how to precisely and efficiently perform sequence matching among videos (which may be subject to complex audio-visual transformations) from a large-scale database still remains a pretty challenging task. To address this problem, this paper proposes a multiscale video sequence matching (MS-VSM) method, which can gradually detect and locate the similar segments between videos from coarse to fine scales. At the coarse scale, it makes use of the Maximum Weight Matching (MWM) algorithm to rapidly select several candidate reference videos from the database for a given query. Then for each candidate video, its most similar segment with respect to the given query is obtained at the middle scale by the Constrained Longest Ascending Matching Subsequence (CLAMS) algorithm, and then can be used to judge whether that candidate exists near-duplicate or not. If so, the precise locations of the near-duplicate segments in both query and reference videos are determined at the fine scale by using bi-directional scanning to check the matching similarity at the segments’ boundaries. As such, the MS-VSM method can achieve excellent near-duplicate detection accuracy and localization precision with a very high processing efficiency. Extensive experiments show that it outperforms several state-of-the-art methods remarkably on several benchmarks.

     

Utilizing similarity relationships among existing data for high accuracy processing of content-based image retrieval

Retrieving similar images based on its visual content is an important yet difficult problem. We propose in this paper a new method to improve the accuracy of content-based image retrieval systems. Typically, given a query image, existing retrieval methods return a ranked list based on the similarity scores between the query and individual images in the database. Our method goes further by relying on an analysis of the underlying connections among individual images in the database to improve this list. Initially, we consider each image in the database as a query and use an existing baseline method to search for its likely similar images. Then, the database is modeled as a graph where images are nodes and connections among possibly similar images are edges. Next, we introduce an algorithm to split this graph into stronger subgraphs, based on our notion of graph’s strength, so that images in each subgraph are expected to be truly similar to each other. We create for each subgraph a structure called integrated image which contains the visual features of all images in the subgraph. At query time, we compute the similarity scores not only between the query and individual database images but also between the query and the integrated images. The final similarity score of a database image is computed based on both its individual score and the score of the integrated image that it belongs to. This leads effectively to a re-ranking of the retrieved images. We evaluate our method on a common image retrieval benchmark and demonstrate a significant improvement over the traditional bag-of-words retrieval model.     

Mining multi-tag association for image tagging

Automatic media tagging plays a critical role in modern tag-based media retrieval systems. Existing tagging schemes mostly perform tag assignment based on community contributed media resources, where the tags are provided by users interactively. However, such social resources usually contain dirty and incomplete tags, which severely limit the performance of these tagging methods. In this paper, we propose a novel automatic image tagging method aiming to automatically discover more complete tags associated with information importance for test images. Given an image dataset, all the near-duplicate clusters are discovered. For each near-duplicate cluster, all the tags occurring in the cluster form the cluster’s “document”. Given a test image, we firstly initialize the candidate tag set from its near-duplicate cluster’s document. The candidate tag set is then expanded by considering the implicit multi-tag associations mined from all the clusters’ documents, where each cluster’s document is regarded as a transaction. To further reduce noisy tags, a visual relevance score is also computed for each candidate tag to the test image based on a new tag model. Tags with very low scores can be removed from the final tag set. Extensive experiments conducted on a real-world web image dataset—NUS-WIDE, demonstrate the promising effectiveness of our approach.     

基于神经网络自学习的图像检索方法

相关反馈技术是近年来图像检索中较为活跃的研究方法之一.提出了一种基于神经网络自学习的图像检索方法,即在检索阶段利用人-机交互技术选出与检索图像相似的正例样本,然后构造出前向神经网络,进行自学习,以逐步达到提高查询效果的目的.神经网络的构造过程即是学习的过程,而且可以不断地学习.使用由9918幅图像组成的图像库进行实验,结果表明,该方法有助于用户表达查询意图和语义概念,可以通过交互式检索逐步求精地查找出更多、更准确的图像,并且具有较强的鲁棒性,可以结合各种特征表示和相似性匹配方法,交互地提高检索性能.     

结合Transformer与非对称学习策略的图像检索

目的 图像检索是计算机视觉领域的一项基础任务,大多采用卷积神经网络和对称式学习策略,导致所需训练数据量大、模型训练时间长、监督信息利用不充分。针对上述问题,本文提出一种Transformer与非对称学习策略相结合的图像检索方法。方法 对于查询图像,使用Transformer生成图像的哈希表示,利用哈希损失学习哈希函数,使图像的哈希表示更加真实。对于待检索图像,采用非对称式学习策略,直接得到图像的哈希表示,并将哈希损失与分类损失相结合,充分利用监督信息,提高训练速度。在哈希空间通过计算汉明距离实现相似图像的快速检索。结果 在CIFAR-10和NUS-WIDE两个数据集上,将本文方法与主流的5种对称式方法和性能最优的两种非对称式方法进行比较,本文方法的mAP(mean average precision)比当前最优方法分别提升了5.06%和4.17%。结论 本文方法利用Transformer提取图像特征,并将哈希损失与分类损失相结合,在不增加训练数据量的前提下,减少了模型训练时间。所提方法性能优于当前同类方法,能够有效完成图像检索任务。