基于空间上下文加权词汇树的图像检索方法

基于词汇树的词袋模型(Bag-of-Words)表示算法是目前图像检索领域中的主流算法.针对传统词汇树方法中空间上下文信息缺失的问题,提出一种基于空间上下文加权词汇树的图像检索方法.该方法在词汇树框架下,首先生成SIFT点的空间上下文信息描述.然后利用SIFT点间的空间上下文相似度对SIFT间的匹配得分进行加权,得到图像间的相似度.最后,通过相似度排序完成图像检索.实验结果表明,该方法能够大幅度提高图像检索的性能,同时,对大规模图像库有较好的适用性.     

非负局部约束线性编码图像分类算法

基于特征提取的图像分类算法的核心问题是如何对特征进行有效编码. 局部约束线性编码(Locality-constrained linear coding, LLC) 因其良好的特征重构性与局部平滑稀疏性, 已取得了很好的分类性能. 然而, LLC编码的分类性能对编码过程中的近邻数k的大小比较敏感, 随着k的增大, 编码中的某些负值元素与正值元素的差值绝对值也可能增大, 这使得LLC越来越不稳定. 本文通过在LLC优化模型的目标方程中引入非负约束, 提出了一种新型编码方式, 称为非负局部约束线性编码(Non-negative locality-constrained linear coding, NNLLC). 该模型一般采取迭代优化算法进行求解, 但其计算复杂度较大. 因此, 本文提出两种近似非负编码算法, 其编码速度与LLC一样快速. 实验结果表明, 在多个广泛使用的图像数据集上, 相比于LLC, NNLLC编码方式不仅在分类精确率上提高了近1%～4%, 而且对k的选取具有更强的鲁棒性.     

融合颜色词袋特征的视觉词汇树图像检索

针对由图像灰度空间产生的传统词袋模型SIFT特征无法体现图像的颜色信息的问题,提出了一种融合颜色特征的视觉词汇树来对图像进行描述。提取SIFT特征并建立词汇树,获取图像的SIFT表示向量。利用K-means方法对图像库中的所有图像的HSV值进行聚类,获得基于HSV空间的颜色词袋表示向量,避免了传统颜色直方图方法所带来的量化误差。将SIFT特征与颜色词袋特征进行融合,完成了图像的全局特征和局部特征的融合。然后,计算融合特征的相似度,将相似度从高到低排序,完成图像检索。为了验证本方法的有效性,选择Corel图像库对算法性能进行实验分析,从主观评价和客观评价标准分别进行评价,并与传统方法进行了对比。结果表明,特征融合的检索性能与单一特征方法相比有较大提高。特征融合方法的平均检索查准率和查全率-查准率等评价指标,对比传统方法均有不同程度提高。     

Improved AdaBoost-based image retrieval with relevance feedback via paired feature learning

Boost learning algorithm, such as AdaBoost, has been widely used in a variety of applications in multimedia and computer vision. Relevance feedback-based image retrieval has been formulated as a classification problem with a small number of training samples. Several machine learning techniques have been applied to this problem recently. In this paper, we propose a novel paired feature AdaBoost learning system for relevance feedback-based image retrieval. To facilitate density estimation in our feature learning method, we propose an ID3-like balance tree quantization method to preserve most discriminative information. By using paired feature combination, we map all training samples obtained in the relevance feedback process onto paired feature spaces and employ the AdaBoost algorithm to select a few feature pairs with best discrimination capabilities in the corresponding paired feature spaces. In the AdaBoost algorithm, we employ Bayesian classification to replace the traditional binary weak classifiers to enhance their classification power, thus producing a stronger classifier. Experimental results on content-based image retrieval (CBIR) show superior performance of the proposed system compared to some previous methods.     

哈夫曼编码乘积量化的图像哈希检索方法

目的 基于哈希编码的检索方法是图像检索领域中的经典方法。其原理是将原始空间中相似的图片经哈希函数投影、量化后,在汉明空间中得到相近的哈希码。此类方法一般包括两个过程：投影和量化。投影过程大多采用主成分分析法对原始数据进行降维,但不同方法的量化过程差异较大。对于信息量不均衡的数据,传统的图像哈希检索方法采用等长固定编码位数量化的方式,导致出现低编码效率和低量化精度等问题。为此,本文提出基于哈夫曼编码的乘积量化方法。方法 首先,利用乘积量化法对降维后的数据进行量化,以便较好地保持数据在原始空间中的分布情况。然后,采用子空间方差作为衡量信息量的标准,并以此作为编码位数分配的依据。最后,借助于哈夫曼树,给方差大的子空间分配更多的编码位数。结果 在常用公开数据集MNIST、NUS-WIDE和22K LabelMe上进行实验验证,与原始的乘积量化方法相比,所提出方法能平均降低49%的量化误差,并提高19%的平均准确率。在数据集MNIST上,与同类方法的变换编码方法（TC）进行对比,比较了从32 bit到256 bit编码时的训练时间,本文方法的训练时间能够平均缩短22.5 s。结论 本文提出了一种基于多位编码乘积量化的哈希方法,该方法提高了哈希编码的效率和量化精度,在平均准确率、召回率等性能上优于其他同类算法,可以有效地应用到图像检索相关领域。     

融合多尺度码本的全局编码图像分类

目的词袋模型在图像分类领域中的分类效果主要受限于局部特征的量化误差。针对这一点,提出一种融合多尺度码本的全局编码图像分类方法,有效减少特征量化误差。方法通过使用多尺度特征密集采样,构建多尺度码本,使码本具备一种层次结构,通过充分利用图像特征的流形结构,计算码本全局信息,实现全局编码。通过本文方法得到的编码系数比较平滑和准确。最后使用多路径方法,分别将不同尺度的特征表示进行级联,得到最终的图像特征表示。这种特征表示具备了一定程度上的尺度不变性。结果在UIUC-8和Caltech-101两个常用的标准图像数据集上进行测试,分类准确率分别达到88.0%和83.2%。结论实验结果表明,相比于基于固定尺度码本的局部编码方法,本文方法在分类识别率方面有了显著提升。     

量化编码的分层可通航小世界图算法

随着大数据和人工智能的高速发展,针对多媒体数据的结构化处理与基于内容的检索受到极大的关注,面对多媒体数据结构化后的海量高维特征向量,如何快速、准确地检索是人工智能处理大规模数据所必须解决的问题。最近提出的分层可通航小世界图HNSW检索算法在多个公开数据集取得了最佳的性能表现,但该算法存在内存开销大的问题。而基于量化编码的检索算法能够压缩数据集向量,大幅度降低内存占用。将量化编码和分层可通航小世界图算法结合,提出了2种基于量化编码改进的HNSW算法,分别是使用标量量化编码向量的HNSWSQ算法和使用乘积量化编码向量的HNSWPQ算法,2种算法使用不同的量化策略存储原始向量编码,以降低内存开销,再通过HNSW算法建立索引达到缩短检索耗时的目的。其中HNSWSQ算法在多个数据集上获得了与HNSW算法相近的查全率和平均检索耗时,而内存开销大幅降低。实验结果表明,HNSWSQ算法在SIFT-1M和GIST-1M数据集上的内存开销比HNSW算法分别降低了45.1%和70.4%。     

基于SHN模型的商品图像检索方法

近年来电子商务行业快速发展,如何通过图像信息在庞大的商品库中快速、准确地找到所需要的商品具有重要的应用价值。针对商品图像数据规模大、类间数据量差异大、被拍摄商品的尺度相差较大以及压缩图像会损失掉细节信息的特点,提出了一个融合金字塔池化策略与哈希学习的空间金字塔池化哈希网络SHN模型,作为本文商品图像检索方法的特征提取部分。为了提高模型对图像形变的鲁棒性,采用金字塔池化策略实现多尺度特征融合;为了使学习到的哈希码具有更好的独立性,使用量化误差损失及附加权值对哈希编码进行约束。本文方法保留了原始图像信息,解决了图像尺度变化所带来的负面影响,通过哈希编码能够实现快速的商品图像检索,商品图像检索实验中的mAP值达到91.986 3%,完成一次检索所用时间为0.034 856 s,检索性能优于当前主流方法。     

一种深度置信网络和迭代量化的图像检索方法

针对网络图像数据的迅速增多导致传统图像检索的效果不能满足当前需求的问题,提出了一种基于深度置信网络(deep belief network,DBN)和迭代量化(iterative quantization,ITQ)的无监督学习图像检索的方法.首先,构造深度置信网络的模型,此模型是由3层受限玻尔兹曼机堆叠而成;然后,用此深度置信网络模型对原始图像的高维特征进行中维特征提取,再采用迭代量化的哈希方法,对提取图像中维特征进行二值编码;最后,针对MNIST、CIFAR-10和Corel-1000数据集对模型进行实验验证并评估.结果表明,所提出的方法与现在的几种主流方法相比检索性能更好.除此之外,本方法对乳腺数据集DDSM和肺结节CT图像数据集LIDC-IDRI中的检索也取得了较好的效果.     

Region-based image retrieval with high-level semantics using decision tree learning

Semantic-based image retrieval has attracted great interest in recent years. This paper proposes a region-based image retrieval system with high-level semantic learning. The key features of the system are: (1) it supports both query by keyword and query by region of interest. The system segments an image into different regions and extracts low-level features of each region. From these features, high-level concepts are obtained using a proposed decision tree-based learning algorithm named DT-ST. During retrieval, a set of images whose semantic concept matches the query is returned. Experiments on a standard real-world image database confirm that the proposed system significantly improves the retrieval performance, compared with a conventional content-based image retrieval system. (2) The proposed decision tree induction method DT-ST for image semantic learning is different from other decision tree induction algorithms in that it makes use of the semantic templates to discretize continuous-valued region features and avoids the difficult image feature discretization problem. Furthermore, it introduces a hybrid tree simplification method to handle the noise and tree fragmentation problems, thereby improving the classification performance of the tree. Experimental results indicate that DT-ST outperforms two well-established decision tree induction algorithms ID3 and C4.5 in image semantic learning.     

基于PCA的哈希图像检索算法

图像哈希算法的步骤大致分为投影和量化两个阶段,为提高哈希编码的性能,分别对这两个阶段进行研究。在投影阶段,通过主成分分析算法将数据投影到新的特征子空间中,以降低原始特征之间的冗余性;在量化阶段,为减少量化所带来的损失,提出一种单双比特结合的量化方法;利用得到的哈希编码进行图像检索。在两个常用的图像数据集上的实验结果表明,提出的算法较现有的主流图像哈希算法在多个评价指标下均有所提高。     

Product Quantization Network for Fast Visual Search

Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By constructing the approximation function, we extend the hard-assignment quantization to soft-assignment quantization. Thanks to the differentiable property of the soft-assignment quantization, the product quantization operation can be integrated as a layer in a convolutional neural network, constructing the proposed product quantization network (PQN). Meanwhile, by extending the triplet loss to the asymmetric triplet loss, we directly optimize the retrieval accuracy of the learned representation based on asymmetric similarity measurement. Utilizing PQN, we can learn a discriminative and compact image representation in an end-to-end manner, which further enables a fast and accurate image retrieval. By revisiting residual quantization, we further extend the proposed PQN to residual product quantization network (RPQN). Benefited from the residual learning triggered by residual quantization, RPQN achieves a higher accuracy than PQN using the same computation cost. Moreover, we extend PQN to temporal product quantization network (TPQN) by exploiting temporal consistency in videos to speed up the video retrieval. It integrates frame-wise feature learning, frame-wise features aggregation and video-level feature quantization in a single neural network. Comprehensive experiments conducted on multiple public benchmark datasets demonstrate the state-of-the-art performance of the proposed PQN, RPQN and TPQN in fast image and video retrieval.

     

Feature grouping and local soft match for mobile visual search

More powerful mobile devices stimulate mobile visual search to become a popular and unique image retrieval application. A number of challenges come up with such application, resulting from appearance variations in mobile images. Performance of state-of-the-art image retrieval systems is improved using bag-of-words approaches. However, for visual search by mobile images with large variations, there are at least two critical issues unsolved: (1) the loss of features discriminative power due to quantization; and (2) the underuse of spatial relationships among visual words. To address both issues, this paper presents a novel visual search method based on feature grouping and local soft match, which considers properties of mobile images and couples visual and spatial information consistently. First features of the query image are grouped using both matched visual features and their spatial relationships; and then grouped features are softly matched to alleviate quantization loss. An efficient score scheme is devised to utilize inverted file index and compared with vocabulary-guided pyramid kernels. Finally experiments on Stanford mobile visual search database and a collected database with more than one million images show that the proposed method achieves promising improvement over the approach with a vocabulary tree, especially when large variations exist in query images.     

基于元学习的深度哈希检索算法

随着移动互联网技术的发展,图像数据的规模越来越大,大规模图像检索任务已经成为了一个紧要的问题。由于检索速度快和存储消耗低,哈希算法受到了研究者的广泛关注。基于深度学习的哈希算法要达到较好的检索性能,需要一定数量的高质量训练数据来训练模型。然而现存的哈希方法通常忽视了数据集存在数据类别非平衡的问题,而这可能会降低检索性能。针对上述问题,提出了一种基于元学习网络的深度哈希检索算法。所提算法可以直接从数据中自动学习加权函数。该加权函数是只有一个隐含层的多层感知机（MLP）,在少量无偏差元数据的指导下,加权函数的参数可以和模型训练过程中的参数同时进行优化更新。元学习网络参数的更新方程可以解释为：较符合元学习数据的样本权重将被提高,而不符合元学习数据的样本权重将被减小。基于元学习网络的深度哈希检索算法可以有效减少非平衡数据对图像检索的影响,并可以提高模型的鲁棒性。在CIFAR-10等广泛使用的基准数据集上进行的大量实验表明,在非平衡比率较大时,所提算法的平均准确率均值（mAP）最佳;在非平均比率为200的条件下,所提算法的mAP比中心相似度量化算法、非对称深度监督哈希（ADSH）算法和快速可扩展监督哈希（FSSH）算法分别提高0.54个百分点,30.93个百分点和48.43个百分点。     

Object recognition algorithm using a vocabulary tree and a pre-matching array

A vocabulary tree algorithm builds a tree structure with the off-line learning method using a large training image dataset. After constructing the tree structure, we can retrieve a query image class very quickly by searching it. This algorithm has come into the spotlight recently because of the great reduction in computation time. In this article, we suggest a method which improves the classification accuracy by searching a vocabulary tree many times for each test dataset. The information which is given by the pre-matching array determines how the tree is visited. Using our new algorithm, we can reduce the miss-classification rate considerably. On the other hand, losses in computation time and memory allocation are negligible with respect to real-time recognition.     

字典重建和空间分布关系约束下的特征选择与图像拼接

目的 针对大型图像检索领域中,复杂图像中SIFT特征描述子的冗余和高维问题,提出了一种基于字典重建和空间分布关系约束的特征选择的方法,来消除冗余特征并保留最具表现力的、保留原始空间结构性的SIFT特征描述子。方法 首先,实验发现了特征选择和字典学习方法在稀疏表示方面的内在联系,将特征选择问题转化为字典重构任务;其次,在SIFT特征选择问题中,为了保证特征空间中特征的鲁棒性,设计了新型的字典学习模型,并采用模拟退火算法进行迭代求解;最后,在字典学习的过程中,加入熵理论来约束特征的空间分布,使学习到的特征描述子能最大限度保持原始SIFT特征空间的空间拓扑关系。结果 在公开数据集Holiday大型场景图片检索数据库上,通过与国际公认的特征选择方法进行实验对比,本文提出的特征选择方法在节省内存空间和提高时间效率（30%~ 50%）的同时,还能保证所筛选的特征描述子的检索准确率比同类特征提高8%~ 14.1%;在国际通用的大型场景图片拼接数据库IPM上,验证本文方法在图像拼接应用中特征提取和特征匹配上的有效性,实验表明本文方法能节省（50% ~70%）图像拼接时间。结论 与已有的方法比较,本文的特征选择方法既不依赖训练数据集,也不丢失重要的空间结构和纹理信息,在大型图像检索、图像拼接领域和3D检索领域中,能够精简特征,提高特征匹配效率和准确率。     

MapReduce-based clustering for near-duplicate image identification

In this paper, an effective algorithm is developed for tackling the problem of near-duplicate image identification from large-scale image sets, where the LLC (locality-constrained linear coding) method is seamlessly integrated with the maxIDF cut model to achieve more discriminative representations of images. By incorporating MapReduce framework for image clustering and pairwise merging, the near duplicates of images can be identified effectively from large-scale image sets. An intuitive strategy is also introduced to guide the process for parameter selection. Our experimental results on large-scale image sets have revealed that our algorithm can achieve significant improvement on both the accuracy rates and the computation efficiency as compared with other baseline methods.