利用脉冲耦合神经网络的纹理图像检索方法

为提高基于内容的图像检索系统(CBIR)中纹理特征提取的有效性,进一步提升CBIR系统的整体性能。提出了一种基于脉冲耦合神经网络的纹理图像检索方法。脉冲耦合神经网络(PCNN)是新一代的人工神经网络,在数据处理上具有很多优势。特征提取时具有平移、旋转、尺度、扭曲等不变性,以及很好的抗噪性,而这一点非常适合于图像检索系统。利用PCNN及简化模型ICM得到对应于不同灰度值的二值图像序列,计算序列中每幅图像的熵序列,其一维的特征矢量作为纹理特征。采用Eu-clidean距离进行相似度计算,建立了一套基于示例查询图像的纹理图像检索系统。实验结果表明,与小波包等特征提取方法相比,该方法不仅对噪声具有较强的鲁棒性,同时能降低特征向量维数,具有尺度、平移和旋转不变性,而且能取得更高的检索率。     

基于统计特征的DCT压缩域纹理图像检索方法

提出了一种基于离散余弦变换（Discrete Cosine Transfrom,DCT）的纹理图像的检索方法.该方法在DCT压缩域,通过直接对DCT系数计算,获得图像纹理的统计特征,并作为检索的依据.理论分析和实验结果都表明,该方法具有很好的检索准确率和效率,并且对于旋转具有不变性.     

形状的全尺度可视化表示与识别

目的 视觉目标的形状特征表示和识别是图像领域中的重要问题。在实际应用中,视角、形变、遮挡和噪声等干扰因素造成识别精度较低,且大数据场景需要算法具有较高的学习效率。针对这些问题,本文提出一种全尺度可视化形状表示方法。方法 在尺度空间的所有尺度上对形状轮廓提取形状的不变量特征,获得形状的全尺度特征。将获得的全部特征紧凑地表示为单幅彩色图像,得到形状特征的可视化表示。将表示形状特征的彩色图像输入双路卷积网络模型,完成形状分类和检索任务。结果 通过对原始形状加入旋转、遮挡和噪声等不同干扰的定性实验,验证了本文方法具有旋转和缩放不变性,以及对铰接变换、遮挡和噪声等干扰的鲁棒性。在通用数据集上进行形状分类和形状检索的定量实验,所得准确率在不同数据集上均超过对比算法。在MPEG-7数据集上精度达到99.57%,对比算法的最好结果为98.84%。在铰接和射影变换数据集上皆达到100%的识别精度,而对比算法的最好结果分别为89.75%和95%。结论 本文提出的全尺度可视化形状表示方法,通过一幅彩色图像紧凑地表达了全部形状信息。通过卷积模型既学习了轮廓点间的形状特征关系,又学习了不同尺度间的形状特征关系。本文方法在视角变化、局部遮挡、铰接变形和噪声等干扰下能保持较高的识别正确率,可应用于图像采集干扰较多以及红外或深度图像的目标识别,并适用于大数据场景下的识别任务。     

On size invariance texture image retrieval by fuzzy logic classifier and scattering statistical features

The texture image retrieval plays an important role in everyday life of people. In this paper, a new and efficient image features extraction approach based on scattering transform is proposed for size invariance texture image retrieval. The proposed approach obtains texture information in different directions and scales. And, analysis of size invariance texture image retrieval using fuzzy logic classifier and scattering statistical features is carried out. The different size samples of texture image are randomly generated from the original texture images. Also, average success rate of each size samples is obtained, respectively. The study shows that statistical features can achieve good performance from the sixth feature.     

Pulse-coupled neural networks and one-class support vector machines for geometry invariant texture retrieval

The pulse-coupled neural network (PCNN) has been widely used in image processing. The outputs of PCNN represent unique features of original stimulus and are invariant to translation, rotation, scaling and distortion, which is particularly suitable for feature extraction. In this paper, PCNN and intersecting cortical model (ICM), which is a simplified version of PCNN model, are applied to extract geometrical changes of rotation and scale invariant texture features, then an one-class support vector machine based classification method is employed to train and predict the features. The experimental results show that the pulse features outperform of the classic Gabor features in aspects of both feature extraction time and retrieval accuracy, and the proposed one-class support vector machine based retrieval system is more accurate and robust to geometrical changes than the traditional Euclidean distance based system.     

Multiple representations, similarity matching, and results fusion for content-based image retrieval

In this paper, we show how the use of multiple content representations and their fusion can improve the performance of content-based image retrieval systems. We consider the case of texture and propose a new algorithm for texture retrieval based on multiple representations and their results fusion. Texture content is modeled using two different models: the well-known autoregressive model and a perceptual model based on perceptual features such as coarseness and directionality. In the case of the perceptual model, two viewpoints are considered: perceptual features are computed based on the original images viewpoint and on the autocovariance function viewpoint (corresponding to original images). So we consider a total of three content representations. The similarity measure used is based on Gower's index of similarity. Simple results of the fusion models are used to merge search results returned by different representations. Experimentations and benchmarking carried out on the well-known Brodatz database show a drastic improvement in search effectiveness with the fused model without necessarily altering their efficiency in an important way.     

A novel scale and rotation invariant texture image retrieval method using fuzzy logic classifier

A novel approach for content-based texture image retrieval system using fuzzy logic classifier is proposed in this paper. The novelty of this method is demonstrated by handling the complexity issues in texture image retrieval arising from rotation and scale variance. These issues are divided into four groups as non rotated non scaled, rotation invariant, scale invariant and scale and rotation invariant texture retrieval for retrieval performance analysis. Features of texture images are obtained using discrete wavelet transform based statistical features and gray level co-occurrence matrix based co-occurrence features. The fuzzy logic classifier is developed with Gaussian membership function with mean and standard deviations of the features. The retrieval performance improvement is carried out by considering various combinations of the features. The average retrieval rates for the four issues have been achieved at 99.40% with 40 features, 91% with 80 features, 65.2% with 40 features, and 63.4% with 65 features respectively. This method outperforms the existing methods in terms of average retrieval rate. The scale and rotation invariant texture retrieval is an incomparable work that has been demonstrated in the present paper.     

基于脉冲耦合神经网络的图像NMI特征提取及检索方法

为了简单有效地提取图像重要特征信息, 从而更好地提高检索图像的精度, 提出了一种基于脉冲耦合神经网络(Pulse coupled neural networks, PCNN)的图像归一化转动惯量(Normalized moment of inertia, NMI)特征提取及检索算法. 首先利用改进简化PCNN模型相似神经元同步时空特性及指数衰降机制将图像分解为具有相关性的二值系列图像, 然后提取反映原始图像目标形状、结构分布二值系列图像的一维NMI特征矢量信号, 并将其应用在图像检索中; 同时, 考虑到二值系列图像间的相关性及不同图像间NMI序列值的差异性, 引入了马氏距离结合Pearson积矩相关法的 综合相似性度量方法. 实验结果表明, 所提算法对图像特征矢量序列具有良好抗几何畸变不变特性及对图像表述的唯一性,且具有较好的图像检索效果.     

基于纹理谱描述子的图像检索

提出一种新的纹理谱描述子应用于基于内容的图像检索中.讨论了小波变换的思想和纹理谱概念的联系,根据纹理的视觉特性,提出纹理模式等价类的概念,设计出更合理的纹理谱描述子来描述图像的纹理特征.该纹理模式刻画了领域内像素灰度变化模式,以纹理谱直方图方式表示图像纹理内容.分析了纹理谱的对称不变性和旋转鲁棒性的特点.应用于图像检索,与G曲or纹理特征相比较,该纹理谱描述子特征提取速度快,检索准确率高.     

Feed-forward content based image retrieval using adaptive tetrolet transforms

This paper proposes a new approach for content based image retrieval based on feed-forward architecture and Tetrolet transforms. The proposed method addresses the problems of accuracy and retrieval time of the retrieval system. The proposed retrieval system works in two phases: feature extraction and retrieval. The feature extraction phase extracts the texture, edge and color features in a sequence. The texture features are extracted using Tetrolet transform. This transform provides better texture analysis by considering the local geometry of the image. Edge orientation histogram is used for retrieving the edge feature while color histogram is used for extracting the color features. Further retrieval phase retrieves the images in the feed-forward manner. At each stage, the number of images for next stage is reduced by filtering out irrelevant images. The Euclidean distance is used to measure the distance between the query and database images at each stage. The experimental results on COREL- 1 K and CIFAR - 10 benchmark databases show that the proposed system performs better in terms of the accuracy and retrieval time in comparison to the state-of-the-art methods.     

改进颜色和小波变换纹理的图像检索方法研究

针对传统图像检索无法体现对检索示例图像中多个不同对象的检索要求程度的问题,提出一种改进颜色特征和小波变换纹理特征的图像检索方法。首先提取出图像的多个感兴趣区域,由感兴趣的不同程度分别赋予不同大小的权值;然后提取颜色特征和纹理特征,分别用对应位置相似度计算、感兴趣区域与检索数据库中图像整体的相似度计算和整体检索示例图像与检索图像数据库中图像相似度计算三种不同方法计算出两幅图像的相似度,取最大的相似度作为两幅图像的最终相似度;对检索示例图像与检索数据库中每个图像的相似度按大小进行排序,选择最相似的图像作为检索结果。实验结果表明,该方法提高了对图像检索的性能,体现了个性化检索,对图像检索具有很好的效果。     

基于加强的前景图像纹理的图像检索方法

针对人们对前景图像比较敏感的特性,提出了一种加强前景信息并弱化背景信息的新方法.该方法首先通过图像的阈值得到前景图像与背景图像,利用某个值加强前景并弱化背景,结合原始图像提取纹理特征,从而进行图像检索.对真实图像数据库的检索实验表明,该方法与其他基于纹理的方法相比,具有较好的检索效果和性能.     

A new matching strategy for content based image retrieval system

Adopting effective model to access the desired images is essential nowadays with the presence of a huge amount of digital images. The present paper introduces an accurate and rapid model for content based image retrieval process depending on a new matching strategy. The proposed model is composed of four major phases namely: features extraction, dimensionality reduction, ANN classifier and matching strategy. As for the feature extraction phase, it extracts a color and texture features, respectively, called color co-occurrence matrix (CCM) and difference between pixels of scan pattern (DBPSP). However, integrating multiple features can overcome the problems of single feature, but the system works slowly mainly because of the high dimensionality of the feature space. Therefore, the dimensionality reduction technique selects the effective features that jointly have the largest dependency on the target class and minimal redundancy among themselves. Consequently, these features reduce the calculation work and the computation time in the retrieval process. The artificial neural network (ANN) in our proposed model serves as a classifier so that the selected features of query image are the input and its output is one of the multi classes that have the largest similarity to the query image. In addition, the proposed model presents an effective feature matching strategy that depends on the idea of the minimum area between two vectors to compute the similarity value between a query image and the images in the determined class. Finally, the results presented in this paper demonstrate that the proposed model provides accurate retrieval results and achieve improvement in performance with significantly less computation time compared with other models.     

基于颜色纹理的图像多特征检索技术在中医舌诊中的应用研究

为了对传统的中医舌诊数字化提出新的方法,并实现通过计算机来进行舌像图像的分类检索,此文将一种结合了颜色和纹理特征的、基于内容的多特征图像检索算法引入到中医舌像的分析中。该算法将表现颜色和纹理的20个特征值作为表达图像内容特征的特征向量,并以此作为舌像检索的距离度量标准。实验结果证明这种算法不仅具有移动、旋转、尺度变换不变性,而且还具有优良的检索性能。因此,此算法可以很好的实现舌像图像的分类检索。     

Shape-based Invariant Texture Indexing

This paper introduces a new texture analysis scheme, which is invariant to local geometric and radiometric changes. The proposed methodology relies on the topographic map of images, obtained from the connected components of level sets. This morphological tool, providing a multi-scale and contrast-invariant representation of images, is shown to be well suited to texture analysis. We first make use of invariant moments to extract geometrical information from the topographic map. This yields features that are invariant to local similarities or local affine transformations. These features are invariant to any local contrast change. We then relax this invariance by computing additional features that are invariant to local affine contrast changes and investigate the resulting analysis scheme by performing classification and retrieval experiments on three texture databases. The obtained experimental results outperform the current state of the art in locally invariant texture analysis.     

结合视觉注意机制与递归神经网络的图像检索

目的 图像检索是计算机视觉的一项重要任务。图像检索的关键是图像的内容描述,复杂图像的内容描述很具有挑战性。传统的方法用固定长度的向量描述图像内容,为此提出一种变长序列描述模型,目的是丰富特征编码的信息表达能力,提高检索精度。方法 本文提出序列描述模型,用可变长度特征序列描述图像。序列描述模型首先用CNN(convolutional neural network)提取底层特征,然后用中间层LSTM(long short-term memory)产生局部特征的相关性表示,最后用视觉注意LSTM(attention LSTM)产生一组向量描述一幅图像。通过匈牙利算法计算图像之间的相似性完成图像检索任务。模型采用标签级别的triplet loss函数进行端对端的训练。结果 在MIRFLICKR-25K和NUS-WIDE数据集上进行图像检索实验,并和相关算法进行比较。相对于其他方法,本文模型检索精度提高了512个百分点。相对于定长的图像描述方式,本文模型在多标签数据集上能够显著改善检索效果。结论 本文提出了新的图像序列描述模型,可以显著改善检索效果,适用于多标签图像的检索任务。     

结合深度学习与相关反馈的遥感图像检索

目的 针对基于内容的图像检索存在低层视觉特征与用户对图像理解的高层语义不一致、图像检索的精度较低以及传统的分类方法准确度低等问题，提出一种基于卷积神经网络和相关反馈支持向量机的遥感图像检索方法。方法 通过对比度受限直方图均衡化算法对遥感图像进行预处理，限制遥感图像噪声的放大，采用自学习能力良好的卷积神经网络对遥感图像进行多层神经网络的监督学习提取丰富的图像特征，并将支持向量机作为基分类器，根据测试样本数据到分类超平面的距离进行排序得到检索结果，最后采用相关反馈策略对检索结果进行重新调整。结果 在UC Merced Land-Use遥感图像数据集上进行图像检索实验，在mAP（mean average precision）精度指标上，当检索返回图像数为100时，本文方法比LSH（locality sensitive Hashing）方法提高了29.4%，比DSH（density sensitive Hashing）方法提高了37.2%，比EMR（efficient manifold ranking）方法提高了68.8%，比未添加反馈和训练集筛选的SVM（support vector machine）方法提高了3.5%，对于平均检索速度，本文方法比对比方法中mAP精度最高的方法提高了4倍，针对复杂的遥感图像数据，本文方法的检索效果较其他方法表现出色。结论 本文提出了一种以距离评价标准为核心的反馈策略，以提高检索精度，并采用多距离结合的Top-k排序方法合理筛选训练集，以提高检索速度，本文方法可以广泛应用于人脸识别和目标跟踪等领域，对提升检索性能具有重要意义。     

基于多语义特征融合的图像检索

多媒体技术的发展导致数字图像迅速增长,如何根据语义特征高效检索出满足用户要求的图像,已成为当前各行业迫切需要解决的问题。为此提出一种基于颜色、纹理和形状三种语义特征的图像检索方法,建立了颜色和纹理特征的语义描述,使用BP神经网络实现了低层视觉特征到高层语义特征的映射。选取Corel图像库作为测试图像库,实验通过与基于颜色语义特征的检索方法相比较,取得了良好的实验效果。     

基于空间特征的图像检索

提出一种新的基于空间特征的图像特征描述子SCH,利用基于颜色向量角和欧几里得距离的MCVAE算法共同检测原始彩色图像边缘,同时利用一种新的“最大最小分量颜色不变量模型”对原始图像量化,对边缘像素建立边缘相关矩阵;对非边缘像素使用颜色直方图描述局部颜色分布信息;然后,利用新的sin相似性度量法则衡量图像特征间的相似度。实验采用VC++6.0开发了基于内容的图像检索原型系统“SttImageRetrieval”,基于Oracle 9i数据库建立了一个综合型图像数据库“IMAGEDB”。实验分析结果证明,利用SCH描述子的检索准确度明显高于仅基于颜色统计特征的检索结果。