彩色图像检索方法

对彩色图像的检索进行了研究,提出了彩色图像检索的方法.该方法首先对彩色图像进行聚类,再使用聚类后图像的主颜色进行颜色相似度计算,使用基于奇异值向量的主颜色矩阵进行空间相似度计算,最后给出了基于主颜色的颜色信息和空间分布信息的图像内容相似度计算方法.进行检索时,可根据检索要求自适应地改变颜色和空间分布的权重,增加了系统的有效性.实验结果表明,该方法实现简单,能够更加灵活、准确地描述图像的颜色特征,从而有效提高了图像检索的准确率.     

Image retrieval by texture similarity

Accuracy and efficiency are the two important issues in designing content-based image retrieval systems. In this paper, we present an efficient image retrieval system with high performance of accuracy based on two novel features, the composite sub-band gradient vector and the energy distribution pattern string. Both features are generated from the sub-images of a wavelet decomposition of the original image. A fuzzy matching mechanism based on energy distribution pattern strings serves as a filter to quickly remove undesired images in the database from further consideration. The images passing the filter will be compared with the query image based on composite sub-band gradient vectors which are extremely powerful for discriminating detailed textures. Through several extensive experiments by exercising our prototype system with a database of 2400 images, we demonstrated that both high accuracy and high efficiency can be achieved at the same time by our approach.     

Fast K-means algorithm based on a level histogram for image retrieval

In image retrieval, the image feature is the main factor determining accuracy; the color feature is the most important feature and is most commonly used with a K-means algorithm. To create a fast K-means algorithm for this study, first a level histogram of statistics for the image database is made. The level histogram is used with the K-means algorithm for clustering data. A fast K-means algorithm not only shortens the length of time spent on training the image database cluster centers, but it also overcomes the cluster center re-training problem since large numbers of images are continuously added into the database. For the experiment, we use gray and color image database sets for performance comparisons and analyzes, respectively. The results show that the fast K-means algorithm is more effective, faster, and more convenient than the traditional K-means algorithm. Moreover, it overcomes the problem of spending excessive amounts of time on re-training caused by the continuous addition of images to the image database. Selection of initial cluster centers also affects the performance of cluster center training.     

A multi-level matching method with hybrid similarity for document retrieval

This paper presents a multi-level matching method for document retrieval (DR) using a hybrid document similarity. Documents are represented by multi-level structure including document level and paragraph level. This multi-level-structured representation is designed to model underlying semantics in a more flexible and accurate way that the conventional flat term histograms find it hard to cope with. The matching between documents is then transformed into an optimization problem with Earth Mover’s Distance (EMD). A hybrid similarity is used to synthesize the global and local semantics in documents to improve the retrieval accuracy. In this paper, we have performed extensive experimental study and verification. The results suggest that the proposed method works well for lengthy documents with evident spatial distributions of terms.     

Adaptive tree similarity learning for image retrieval

Learning-enhanced relevance feedback is one of the most promising and active research directions in content-based image retrieval in recent years. However, the existing approaches either require prior knowledge of the data or converge slowly and are thus not coneffective. Motivated by the successful history of optimal adaptive filters, we present a new approach to interactive image retrieval based on an adaptive tree similarity model to solve these difficulties. The proposed tree model is a hierarchical nonlinear Boolean representation of a user query concept. Each path of the tree is a clustering pattern of the feedback samples, which is small enough and local in the feature space that it can be approximated by a linear model nicely. Because of the linearity, the parameters of the similartiy model are better learned by the optimal adaptive filter, which does not require any prior knowledge of the data and supports incremental learning with a fast convergence rate. The proposed approach is simple to implement and achieves better performance than most approaches. To illustrate the performance of the proposed approach, extensive experiments have been carried out on a large heterogeneous image collection with 17,000 images, which render promising results on a wide variety of queries.An early version of part of the system was reported in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition 2001.     

An image segmentation method using histograms and the human characteristics of HSI color space for a scene image

Image segmentation is an important subject for image recognition. Here, we propose a new image segmentation method for scene images. The proposed segmentation method classifies images into several segments based on the human visual sense and achromatic color. We calculate the histograms of the image for each component of the hue, saturation, and intensity (HSI) color space, and obtain three results of image segmentation from each histogram. We consider achromatic colors in order to decrease the number of regions. We compare the results of the proposed method with those of the k-means methods for the effectiveness of the proposed method. This work was presented, in part, at the 10th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2005     

Evaluating a workspace’s usefulness for image retrieval

Image searching is a creative process. We have proposed a novel image retrieval system that supports creative search sessions by allowing the user to organise their search results on a workspace. The workspace’s usefulness is evaluated in a task-oriented and user-centred comparative experiment, involving design professionals and several types of realistic search tasks. In particular, we focus on its effect on task conceptualisation and query formulation. A traditional relevance feedback system serves as a baseline. The results of this study show that the workspace is more useful in terms of both of the above aspects and that the proposed approach leads to a more effective and enjoyable search experience. This paper also highlights the influence of tasks on the users’ search and organisation strategy.     

基于张量积扩散与纹理元相似的医学图像检索

针对医学图像检索中相似性表达的自身困难,以及噪声影响的问题,提出一种通过张量积图进行扩散,利用其他数据点的上下信息改进基于纹理元的成对相似性度量的方法。首先,采用纹理元的统计方法进行医学图像特征描述和提取,并通过对纹理元相似性加权,得到图像的成对相似性;然后,利用张量积图沿着数据点的内在流形进行相似性的传播,实现全局的相似性度量。在ImageCLEFmed 2009上的实验结果表明,该算法与基于Gabor的检索算法相比,其类平均精度提高了32%,与基于尺度不变特征转换(SIFT)的检索算法相比,其类平均精度提高了19%,能良好地应用于医学图像检索。     

样本方差与相似点判断相结合的图像裂缝检测

为解决传统渗流裂缝检测方法速度较慢的问题,提出一种样本方差与相似点判断相结合的图像裂缝检测算法。采用样本方差提取裂缝区域,提出一种偏差处理方式提取裂缝像素点,减少后续像素处理个数;进行初步裂缝渗流检测;提出一种裂缝断裂区间相似点判断算法并进一步渗流检测,避免裂缝断裂现象,提高检测的精确率。实验结果表明,该算法与传统渗流算法的精确率基本保持一致,降低了裂缝连接算法导致的误检测率,检测速度明显提高。     

Ranking consistency for image matching and object retrieval

The goal of object retrieval is to rank a set of images by the similarity of their contents to those of a query image. However, it is difficult to measure image content similarity due to visual changes caused by varying viewpoint and environment. In this paper, we propose a simple, efficient method to more effectively measure content similarity from image measurements. Our method is based on the ranking information available from existing retrieval systems. We observe that images within the set which, when used as queries, yield similar ranking lists are likely to be relevant to each other and vice versa. In our method, ranking consistency is used as a verification method to efficiently refine an existing ranking list, in much the same fashion that spatial verification is employed. The efficiency of our method is achieved by a list-wise min-Hash scheme, which allows rapid calculation of an approximate similarity ranking. Experimental results demonstrate the effectiveness of the proposed framework and its applications.     

Advancing content-based image retrieval by exploiting image color and region features

In this paper, we propose a novel system that strives to achieve advanced content-based image retrieval using seamless combination of two complementary approaches: on the one hand, we propose a new color-clustering method to better capture color properties of the original images; on the other hand, expecting that image regions acquired from the original images inevitably contain many errors, we make use of the available erroneous, ill-segmented image regions to accomplish the object-region-based image retrieval. We also propose an effective image-indexing scheme to facilitate fast and efficient image matching and retrieval. The carefully designed experimental evaluation shows that our proposed image retrieval system surpasses other methods under comparison in terms of not only quantitative measures, but also image retrieval capabilities.     

互信息启发的相似度组合图像检索算法

图像的视觉特征与用户描述之间的差距一直是影响基于内容的图像检索准确度的最主要因素。对多种相似度进行组合来检索图像是近几年图像检索领域涌现出的一个研究热点,也是缩小这种差距的一种有效途径。如何选择更好的组合方法则是该领域很多研究者关注的核心问题。提出一种新的相似度组合算法。该算法基于互信息度量相对熵的原理,计算连续变量相似度与离散变量相似性之间的相关性,对多种相似度进行选择,以“和规则”组合相似度。在公用数据集上进行检索实验,该算法优于当前其他的“和规则”下的组合方法。     

Spatial inference and similarity retrieval of an intelligent image database system based on object's spanning representation

In this paper, we presented a novel image representation method to capture the information about spatial relationships between objects in a picture. Our method is more powerful than all other previous methods in terms of accuracy, flexibility, and capability of discriminating pictures. In addition, our method also provides different degrees of granularity for reasoning about directional relations in both 8- and 16-direction reference frames. In similarity retrieval, our system provides twelve types of similarity measures to support flexible matching between the query picture and the database pictures. By exercising a database containing 3600 pictures, we successfully demonstrated the effectiveness of our image retrieval system. Experiment result showed that 97.8% precision rate can be achieved while maintaining 62.5% recall rate; and 97.9% recall rate can be achieved while maintaining 51.7% precision rate. On an average, 86.1% precision rate and 81.2% recall rate can be achieved simultaneously if the threshold is set to 0.5 or 0.6. This performance is considered to be very good as an information retrieval system.     

Genetic algorithms for a family of image similarity models incorporated in the relevance feedback mechanism

We propose two extensions of the Local Similarity Pattern/Weighted Local Similarity Pattern (LSP/WLSP) image similarity models, proposed by Steji (2002). The objective is to improve the retrieval precision, by increasing the expressive power of the LSP/WLSP models. We formalize LSP and WLSP as special cases of a general similarity model, which defines image similarity as a weighted mean of the corresponding region similarities, and, in turn, each region similarity as a weighted mean of the corresponding feature similarities. In the case of LSP/WLSP models, region and feature weights have discrete non-negative values. The proposed two extensions are: (1) LSP-C+/WLSP-C+ models, with continuous non-negative weight values; and (2) LSP-C±/WLSP-C± models, with continuous positive and negative weight values. Similar to the LSP/WLSP, the proposed four models are incorporated in the relevance feedback mechanism, using genetic algorithm (GA) to infer the (sub-)optimal assignment of region and feature weights, which maximizes the similarity between the query image and the set of relevant images, chosen by the user. Accordingly, for the weight inference, GAs used for the LSP/WLSP models are extended from the integer-coded to the real-coded ones, and, in addition, new chromosome coding, two crossover modifications, six new mutation types, and a weights normalization operator are proposed. The proposed four models are evaluated on five test databases, with around 2500 images, covering 62 semantic categories. Compared with the existing image similarity models, including LSP/WLSP, and other models based on relevance feedback, proposed LSP-C±/WLSP-C± models bring in average over 10% increase in the retrieval precision. The main contributions, not limited to the LSP/WLSP models and the image retrieval, are: (1) the introduction of negative weights into the weighted mean of similarities, which increases the expressive power of the similarity model, and results in a significantly higher retrieval precision; and (2) new real-coded genetic operators suitable for the weight inference in general.     

两种基于游程描述的彩色图像检索方法

借助于颜色游程的概念,提出了一种基于游程矩阵的彩色图像特征描述方法,并在此基础上定义了两种图像相似性测度。为了增强图像特征描述的稳健性,对游程矩阵引进了累积变换。对真实图像检索的实验表明,本文的方法对于纹理图像的检索具有很好的检索效果。