A soft image representation approach by exploiting local neighborhood structure of self-organizing map (SOM)

When images are described with visual words based on vector quantization of low-level color, texture, and edge-related visual features of image regions, it is usually referred as “bag-of-visual words (BoVW)”-based presentation. Although it has proved to be effective for image representation similar to document representation in text retrieval, the hard image encoding approach based on one-to-one mapping of regions to visual words is not expressive enough to characterize the image contents with higher level semantics and prone to quantization error. Each word is considered independent of all the words in this model. However, it is found that the words are related and their similarity of occurrence in documents can reflect the underlying semantic relations between them. To consider this, a soft image representation scheme is proposed by spreading each region’s membership values through a local fuzzy membership function in a neighborhood to all the words in a codebook generated by self-organizing map (SOM). The topology preserving property of the SOM map is exploited to generate a local membership function. A systematic evaluation of retrieval results of the proposed soft representation on two different image (natural photographic and medical) collections has shown significant improvement in precision at different recall levels when compared to different low-level and “BoVW”-based feature that consider only probability of occurrence (or presence/absence) of a word.     

基于模糊逻辑的图像检索研究

提出一个基于模糊逻辑的图像检索系统.该系统使用模糊语言变量描述图像特征之间的相似性程度,而非图像特征本身,使得图像相似性推理能以非线性方式进行;模糊规则建立在用户对对象的认知基础之上,能够反映用户主观感知.由于具有相似特征变化范围的不同对象可以适用于相同的规则,使得算法对检索图像的不同类别具有良好的鲁棒性.另外,提出一种改进的直方图--平均面积直方图,以提取色彩特征.实验结果表明了模糊检索系统的有效性与可行性.     

ICTEDCT-CBIR: Integrating curvelet transform with enhanced dominant colors extraction and texture analysis for efficient content-based image retrieval

A novel Integrated Curvelet-based image retrieval scheme (ICTEDCT-CBIR) has been proposed, for the purpose of effectively retrieving more similar images from large digital image databases. The proposed model Integrates Curvelet Multiscale ridgelets with Region-based vector codebook Subband Clustering for enhanced dominant colors extraction and texture analysis. An important ingredient of the curvelet transform is to restore sparsity by reducing redundancy across scales. The discrete curvelet transform makes use of a dyadic sequence of scales, and a bank of filters with the property that the pass band filter is concentrated near the frequencies. An enhanced Region-based vector codebook Sub band Clustering (RBSC) has been proposed for effectively extract dominant colors from the color histogram of the transformed image sub-bands. An integrated matching scheme, based on most similar Highest Priority (MSHP) principle, is used to compare the query and target images. Experimental analysis has been carried out to verify the efficiency of the proposed ICTEDCT-CBIR model. Experimental results showed that the proposed approach has better retrieval performance. First, curvelets capture more accurate texture information. Second, as curvelets are tuned to different orientations, it captured more accurate directional features than wavelets. As the experimental results indicated, the proposed technique outperforms other retrieval schemes in terms of average precision with higher precision-recall crossover point values.     

改进的MSF-VQ人脸特征提取方法

MSF-VQ是一种用于人脸识别的图像特征.它先使用预先确定的码书计算出图片的向量量化直方图特征,再通过马尔科夫稳态特征对直方图进行扩展,从而得到MSF-VQ特征.MSF-VQ特征在人脸识别中表现出较高的识别准确率.但是它在码书的确定和空间信息表达上仍有一些不足之处.针对这两个方面,本文提出了一种改进的方法.首先根据人脸数据集来计算码书,从而提高向量量化直方图对人脸的分辨能力,然后通过结合多个方向上采样的MSF特征,增加MSF-VQ特征包含的空间位置信息.实验结果表明,改进的MSF-VQ方法具有更高的人脸识别准确率.     

基于多特征组合的细粒度图像分类方法

针对单一特征表示的局限性会导致细粒度图像分类准确度不高的问题,提出了一种基于卷积神经网络（CNN）和尺度不变特征转换（SIFT）的多特征组合表示方法,综合考虑对目标整体、关键部位和关键点的特征提取。首先,分别以细粒度图像库中的目标整体和头部区域训练CNN得到两个网络模型,用来提取目标的整体和头部CNN特征;然后,对图像库中所有目标区域提取SIFT关键点并通过K均值（K-means）聚类生成码本,再将每个目标区域的SIFT描述子通过局部特征聚合描述符（VLAD）参照码本编码为特征向量;最后,组合多种特征作为最终的特征表示,采用支持向量机（SVM）对细粒度图像进行分类。使用该方法在CUB-200-2011数据库上进行实验,并与单一的特征表示方法进行了比较。实验结果表明,该方法与基于单一CNN特征的细粒度图像分类相比提升了13.31%的准确度,证明了多特征组合对细粒度图像分类的积极作用。     

Content-based image retrieval by using tree-structured features and multi-layer self-organizing map

A new approach for content-based image retrieval (CBIR) is described. In this study, a tree-structured image representation together with a multi-layer self-organizing map (MLSOM) is proposed for efficient image retrieval. In the proposed tree-structured image representation, a root node contains the global features, while child nodes contain the local region-based features. This approach hierarchically integrates more information of image contents to achieve better retrieval accuracy compared with global and region features individually. MLSOM in the proposed method provides effective compression and organization of tree-structured image data. This enables the retrieval system to operate at a much faster rate than that of directly comparing query images with all images in databases. The proposed method also adopts a relevance feedback scheme to improve the retrieval accuracy by a respectable level. Our obtained results indicate that the proposed image retrieval system is robust against different types of image alterations. Comparative results corroborate that the proposed CBIR system is promising in terms of accuracy, speed and robustness.     

融合特征的快速SURF配准算法

目的 针对基于SURF特征点的图像配准算法对颜色单一的彩色图像提取的特征点较少及配准时间复杂度高等问题,提出一种基于融合特征的快速SURF(speed up robust features)配准算法.方法 该算法首先提取图像的颜色不变量边缘特征和CS-LBP(central symmetry-local binary patterns)纹理特征形成融合特征灰度图,并利用颜色直方图的方差自适应调节融合特征间的权重.其次,在融合特征灰度图上提取SURF(speed up robust features)特征点及描述子.再次,用最近邻匹配法形成粗匹配对,结合改进的快速RANSAC(random sample consensus)算法得到精匹配对.最后,使用最小二乘法求出映射关系用于配准图像.结果 本文算法能够在融合特征上提取更稳定的SURF特征点,用该特征点进行配准能提高配准5％精度,且减少时间复杂度15％,实现了对普通场景下图像的快速配准.结论 本文算法能提取稳定数量的特征点,提高了精确度与鲁棒性,并通过改进的RANSAC算法提高了执行效率,降低了迭代次数.     

一种基于多特征融合的彩色图像检索方法

提出了一种基于特征融合的图像检索方法。利用图像的HSV直方图特征建立图像颜色直方图,并采用直方图二次式距离公式取得图像相似性度量值;利用图像的纹理特征建立256维的LBP特征向量,并利用欧式距离取得相似性度量值;通过两特征融合的方法取得图像检索中关键图和检索图之间的相似度值,使得检索取得更好的效果。实验表明,在查准率和...     

动作识别中局部时空特征的运动表示方法研究

近年来,基于局部时空特征的运动表征方法已被越来越多地运用于视频中的动作识别问题,相关研究人员已经提出了多种特征检测和描述方法,并取得了良好的效果。但上述方法在适应摄像头移动、光照以及穿着变化等方面还存在明显不足。为此,提出了基于时空兴趣点局部时空特征的运动表示方法,实现了基于时空单词的动作识别。首先采用基于Gabor滤波器和Gaussian滤波器相结合的检测算法从视频中提取时空兴趣点,然后抽取兴趣点的静态特征、运动特征和时空特征,并分别对运动进行表征,最后利用基于时空码本的动作分类器对动作进行分类识别。在Weizmann和KTH两个行为数据集进行了测试,实验结果表明：基于时空特征的运动表示能够更好地适应摄像头移动、光照变化以及施动者的穿着和动作差异等环境因素的影响,取得更好的识别效果。     

基于多尺度特征映射匹配的图像表示方法

在卷积神经网络模型中,空间金字塔池化方法将空间信息融入到深度特征的生成过程中,最终生成的图像表示可以有效地用于提高图像检索性能,但是此方法会导致生成的图像表示中不同维度之间描述的信息存在重复且相同维度描述的图像内容不匹配。为此提出了一种基于多尺度特征映射匹配（multi-scale feature map matching,MFMM）的图像表示方法,此方法首先利用深度特征的方差与协方差矩阵提出了一种特征映射选择算法,用于增强图像表示中不同维度特征的独立性。其次,依据相同通道特征映射中高响应值位置有较高匹配性的特点,结合激活映射中最大响应位置的深度特征提出了一种优化的特征映射中心点选择方法。最后,按照不同的中心点通过多尺度窗口采样的方式,从特征映射中提取出带有空间信息的深度特征用于表示图像内容。实验结果表明,提出的方法在图像检索任务中能够取得良好的效果。     

空间金字塔颜色直方图在图像分类中的应用

颜色直方图在图像分类系统中有着重要的应用。针对像颜色直方图特征的空间关系,提出空间金字塔颜色直方图作为图像的特征表示。它结合了图像的全局特征以及分块特征的优点。使用支持向量机（SVM）以及常用的4种核函数进行了测试。在corel图像库上的实验结果表明,该特征可以有效地结合全局与空间特征,提高了图像的分类准确率。     

Representations of Keypoint-Based Semantic Concept Detection: A Comprehensive Study

Based on the local keypoints extracted as salient image patches, an image can be described as a ?bag-of-visual-words (BoW)? and this representation has appeared promising for object and scene classification. The performance of BoW features in semantic concept detection for large-scale multimedia databases is subject to various representation choices. In this paper, we conduct a comprehensive study on the representation choices of BoW, including vocabulary size, weighting scheme, stop word removal, feature selection, spatial information, and visual bi-gram. We offer practical insights in how to optimize the performance of BoW by choosing appropriate representation choices. For the weighting scheme, we elaborate a soft-weighting method to assess the significance of a visual word to an image. We experimentally show that the soft-weighting outperforms other popular weighting schemes such as TF-IDF with a large margin. Our extensive experiments on TRECVID data sets also indicate that BoW feature alone, with appropriate representation choices, already produces highly competitive concept detection performance. Based on our empirical findings, we further apply our method to detect a large set of 374 semantic concepts. The detectors, as well as the features and detection scores on several recent benchmark data sets, are released to the multimedia community.     

基于多视觉码本的图像表示

基于词袋模型的图像表示方法的有效性主要受限于局部特征的量化误差。文中提出一种基于多视觉码本的图像表示方法,通过综合考虑码本构建和编码方法这两个方面的因素加以改进。具体包括:1)多视觉码本构建,以迭代方式构建多个紧凑且具有互补性的视觉码本;2)图像表示,首先针对多码本的情况,依次从各码本中选择相应的视觉单词并采用线性回归估计编码系数,然后结合图像的空间金字塔结构形成最终的图像表示。在一些标准测试集合的图像分类结果验证文中方法的有效性。     

用于视觉词语生成的概率预测器

视觉词语的产生是基于字袋模型的图像检索中的重要一环:根据已知的视觉词典,查询图像特征被映射到词典中相应的视觉词语。提出一种新的基于空间相关性的快速视觉词语产生算法。统计视觉词典中任意两个词语在数据库中的共生次数,构建视觉词语共生表。利用共生表,建立一种新的概率预测器来辅助预测已知词语的近邻词语。将预测器与快速近似最近邻查找算法结合,在标准图像检索数据库上进行实验测试,相比较传统的树形搜索算法或哈希算法,新算法在时间效率上获得明显提高。     

Saliency and KAZE features assisted object segmentation

In this paper, we propose an unsupervised salient object segmentation approach using saliency and object features. In the proposed method, we utilize occlusion boundaries to construct a region-prior map which is then enhanced using object properties. To reject the non-salient regions, a region rejection strategy is employed based on the amount of detail (saliency information) and density of KAZE keypoints contained in them. Using the region rejection scheme, we obtain a threshold for binarizing the saliency map. The binarized saliency map is used to form a salient superpixel cluster. Finally, an iterative grabcut segmentation is applied with salient texture keypoints (SIFT keypoints on the Gabor convolved texture map) supplemented with salient KAZE keypoints (keypoints inside saliency cluster) as the foreground seeds and the binarized saliency map (obtained using the region rejection strategy) as a probably foreground region. We perform experiments on several datasets and show that the proposed segmentation framework outperforms the state of the art unsupervised salient object segmentation approaches on various performance metrics.     

基于HOG特征与子区域模糊融合的人耳识别研究

作为一种新兴的生物特征识别技术,人耳识别具有其自身独特优势.利用局部特征信息,研究一类新型的基于梯度方向直方图的人耳身份识别方法,提出一种基于梯度方向直方图与子区域模糊融合相结合的人耳识别方案.将人耳图像划分为不同子区域,分别提取各子区域梯度方向直方图特征,引入模糊隶属度匹配融合策略,获取最终的分类结果.与多种方法的对比实验表明,基于梯度方向直方图的特征提取方法具有高识别性能,针对USTB人耳图像库3的测试实验,可达到99.75％的识别率.     

An adaptive reversible data hiding scheme based on prediction error histogram shifting by exploiting signed-digit representation

A prediction error histogram shifting (PEHS)-based reversible data hiding scheme is proposed in this paper. A novel representation for the secret stream, called signed-digit representation, is proposed to improve the image quality. The secret binary stream is first converted into a signed-digit stream, which results in a high occurrence of ‘0’. Meanwhile, a block-wise-based prediction is performed on the original image to generate prediction errors, which lead to a sharp prediction error histogram. Then, the converted signed-digit stream is embedded into the prediction errors according to the improved histogram shifting (HS)-based scheme with multiple selected peak points, resulting in an adaptive embedding capacity. The experimental results validate that the proposed scheme outperforms state-of-the-art schemes in terms of embedding capacity while maintaining a good image quality.