We present an algorithm for simultaneously recognizing and localizing planar textured objects in an image. The algorithm can scale efficiently with respect to a large number of objects added into the database. In contrast to the current state-of-the-art on large scale image search, our algorithm can accurately work with query images consisting of several specific objects and/or multiple instances of the same object. Our proposed algorithm consists of two major steps. The first step is to generate a set of hypotheses that provides information about the identities and the locations of objects in the image. To serve this purpose, we extend Bag-Of-Visual-Word (BOVW) image retrieval by incorporating a re-ranking scheme based on the Hough voting technique. Subsequently, in the second step, we propose a geometric verification algorithm based on A Contrario decision framework to draw out the final detection results from the generated hypotheses. We demonstrate the performance of the algorithm on the scenario of recognizing CD covers with a database consisting of more than ten thousand images of different CD covers. Our algorithm yield to the detection results of more than 90% precision and recall within a few seconds of processing time per image.

This Letter presents a new feature named structured local binary Kirsch pattern (SLBKP) for image retrieval. Each input color image is decomposed into Y, Cb and Cr components. For each component image, eight 33 Kirsch direction templates are first performed pixel by pixel, and thus each pixel is characterized by an 8-dimenional edge-strength vector. Then a binary operation is performed on each edge-strength vector to obtain its integer-valued SLBKP. Finally, three SLBKP histograms are concatenated together as the final feature of each input colour image. Experimental results show that, compared with the existing structured local binary Haar pattern (SLBHP)-based feature, the proposed feature can greatly improve retrieval performance.

We propose a retrieval method using scale invariant visual phrases (SIVPs). Our method encodes spatial information into the SIVPs which capture translation, rotation and scale invariance, and employs the SIVPs to determine the spatial correspondences between query image and database image. To compute the spatial correspondences efficiently, the SIVPs are introduced into the inverted index, and SIVP verification is investigated to refine the candidate images returned from inverted index. Experimental results demonstrate that our method improves the retrieval accuracy while increasing the retrieval efficiency.

There has recently been much research on content-based image retrieval (CBIR) that uses image features including color, shape, and texture. In CBIR, feature extraction is important because the retrieval result depends on the image feature. Query-by-sketch image retrieval is one of CBIR and query-by-sketch image retrieval is efficient because users simply have to draw a sketch to retrieve the desired images. In this type of retrieval, selecting the optimum feature extraction method is important because the retrieval result depends on the image feature. We have developed a query-by-sketch image retrieval method that uses an edge relation histogram (ERH) as a global and local feature intended for binary line images. This histogram is based on the patterns of distribution of other line pixels centered on each line pixel that have been obtained by global and local processing. ERH, which is a shift- and scale-invariant feature, focuses on the relation among the edge pixels. It is fairly simple to describe rotation- and symmetry-invariant features, and query-by-sketch image retrieval using ERH makes it possible to perform retrievals that are not affected by position, size, rotation, or mirroring. We applied the proposed method to 20,000 images in the Corel Photo Gallery. Experimental results showed that it was an effective means of retrieving images.

Shape is one of the primary low-level image features in content-based image retrieval. In this paper we propose a new shape description method that consists of a rotationally invariant angular radial transform descriptor (IARTD). The IARTD is a feature vector that combines the magnitude and aligned phases of the angular radial transform (ART) coefficients. A phase correction scheme is employed to produce the aligned phase so that the IARTD is invariant to rotation. The distance between two IARTDs is defined by combining differences in the magnitudes and aligned phases. In an experiment using the MPEG-7 shape dataset, the proposed method outperforms existing methods; the average BEP of the proposed method is 57.69%, while the average BEPs of the invariant Zernike moments descriptor and the traditional ART are 41.64% and 36.51%, respectively.

Polar and Spherical Fourier analysis can be used to extract rotation invariant features for image retrieval and pattern recognition tasks. They are demonstrated to show superiorities comparing with other methods on describing rotation invariant features of two and three dimensional images. Based on mathematical properties of trigonometric functions and associated Legendre polynomials, fast algorithms are proposed for multimedia applications like real time systems and large multimedia databases in order to increase the computation speed. The symmetric points are computed simultaneously. Inspired by relative prime number theory, systematic analysis are given in this paper. Novel algorithm is deduced that provide even faster speed. Proposed method are 9–15% faster than previous work. The experimental results on two and three dimensional images are given to illustrate the effectiveness of the proposed method. Multimedia signal processing applications that need real time polar and spherical Fourier analysis can be benefit from this work.

Kernel biased discriminant analysis (KBDA), as a subspace learning algorithm, has been an attractive approach for the relevance feedback in content-based image retrieval. Its performance, however, still suffers from the “small sample learning” problem and “kernel learning” problem. Aiming to solve these problems, in this paper, we present a new semi-supervised scheme of KBDA (S-KBDA), in which the projection learning and the “kernel learning” are interweaved into a constrained optimization framework. Specifically, S-KBDA learns a subspace that preserves both the biased discriminant structure among the labeled samples, and the geometric structure among all training samples. In kernel optimization, we directly optimize the kernel matrix, rather than a kernel function, which makes the kernel learning more flexible and appropriate for the retrieval task. To solve the constrained optimization problem, a fast algorithm based on gradient ascent is developed. The image retrieval experiments are given to show the effectiveness of the S-KBDA scheme in comparison with the original KBDA, and the other two state-of-the-art algorithms.

Polar Fourier Descriptor(PFD) and Spherical Fourier Descriptor(SFD) are rotation invariant feature descriptors for two dimensional(2D) and three dimensional(3D) image retrieval and pattern recognition tasks. They are demonstrated to show superiorities compared with other methods on describing rotation invariant features of 2D and 3D images. However in order to increase the computation speed, fast computation method is needed especially for machine vision applications like realtime systems, limited computing environments and large image databases. This paper presents fast computation method for PFD and SFD that are deduced based on mathematical properties of trigonometric functions and associated Legendre polynomials. Proposed fast PFD and SFD are 8 and 16 times faster than direct calculation that significantly boost computation process. Furthermore, the proposed methods are also compact for memory requirements for storing PFD and SFD basis in lookup tables. The experimental results on both synthetic and real data are given to illustrate the efficiency of the proposed method.

In previous studies, the retrieval accuracy of large image databases has been improved as a result of reducing the semantic gap by combining the input sketch with relevance feedback. A further improvement of retrieval accuracy is expected by combining each stroke, and its order, of the input sketch with the relevance feedback. However, this leaves as a problem the fact that the effect of the relevance feedback substantially depends on the stroke order in the input sketch. Although it is theoretically possible to consider all the possible stroke orders, that would cause a realistic problem of creating an enormous amount of data. Consequently, the technique introduced in this paper intends to improve retrieval efficiency by effectively using the relevance feedback by means of conducting data mining of the sketch considering the similarity in the order of strokes. To ascertain the effectiveness of this technique, a retrieval experiment was conducted using 20,000 images of a collection, the Corel Photo Gallery, and the experiment was able to confirm an improvement in the retrieval efficiency.

This Letter proposes a new kind of features for color image retrieval based on Distance-weighted Boundary Predictive Vector Quantization (DWBPVQ) Index Histograms. For each color image in the database, 6 histograms (2 for each color component) are calculated from the six corresponding DWBPVQ index sequences. The retrieval simulation results show that, compared with the traditional Spatial-domain Color-Histogram-based (SCH) features and the DCTVQ index histogram-based (DCTVQIH) features, the proposed DWBPVQIH features can greatly improve the recall and precision performance.

As the multimedia contents market continues its rapid expansion, the amount of image contents used in mobile phone services, digital libraries, and catalog service is increasing remarkably. In spite of this rapid growth, users experience high levels of frustration when searching for the desired image. Even though new images are profitable to the service providers, traditional collaborative filtering methods cannot recommend them. To solve this problem, in this paper, we propose feature-based collaborative filtering (FBCF) method to reflect the user's most recent preference by representing his purchase sequence in the visual feature space. The proposed approach represents the images that have been purchased in the past as the feature clusters in the multi-dimensional feature space and then selects neighbors by using an inter-cluster distance function between their feature clusters. Various experiments using real image data demonstrate that the proposed approach provides a higher quality recommendation and better performance than do typical collaborative filtering and content-based filtering techniques.

The manifold-ranking algorithm has been successfully adopted in content-based image retrieval (CBIR) in recent years. However, while the global low-level features are widely utilized in current systems, region-based features have received little attention. In this paper, a novel attention-driven transductive framework based on a hierarchical graph representation is proposed for region-based image retrieval (RBIR). This approach can be characterized by two key properties: (1) Since the issue about region significance is the key problem in region-based retrieval, a visual attention model is chosen here to measure the regions' significance. (2) A hierarchical graph representation which combines region-level with image-level similarities is utilized for the manifold-ranking method. A novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. Experimental results demonstrate that the proposed approach shows the satisfactory retrieval performance compared to the global-based and the block-based manifold-ranking methods.

We propose a method to retrieve similar and duplicate images from a JPEG (Joint Photographic Image Group) image database. Similarity level is decided based on the DCT (Discrete Cosine Transform) coefficients signs. The method is simple and fast because it uses the DCT coefficients signs as features, which can be obtained directly after partial decoding of JPEG bitstream. The method is robust to JPEG compression, in which similarity level of duplicate images, i.e., images that are compressed from the same original images with different compression ratios, is not disguised due to JPEG compression. Simulation results showed the superiority of the method compared to previous methods in terms of computational complexity and robustness to JPEG compression.

Recently, cars are equipped with a lot of sensors for safety driving. We have been trying to store the driving-scene video with such sensor data and to detect the change of scenery of streets. Detection results can be used for building historical database of town scenery, automatic landmark updating of maps, and so forth. In order to compare images to detect changes, image retrieval taken at nearly identical locations is required as the first step. Since Global Positioning System (GPS) data essentially contain some noises, we cannot rely only on GPS data for our image retrieval. Therefore, we have developed an image retrieval algorithm employing edge-histogram-based image features in conjunction with hierarchical search. By using edge histograms projected onto the vertical and horizontal axes, the retrieval has been made robust to image variation due to weather change, clouds, obstacles, and so on. In addition, matching cost has been made small by limiting the matching candidates employing the hierarchical search. Experimental results have demonstrated that the mean retrieval accuracy has been improved from 65% to 76% for the front-view images and from 34% to 53% for the side-view images.

This letter proposes a fast k nearest neighbors search algorithm based on the wavelet transform. This technique exploits the important information of the approximation coefficients of the transform coefficient vector, from which we obtain two crucial inequalities that can be used to reject those vectors for which it is impossible to be k nearest neighbors. The computational complexity for searching for k nearest neighbors can be largely reduced. Experimental results on texture classification verify the effectiveness of our algorithm.

According to the Gestalt principals, this paper presents a recognition method of grouping areas in trademark images modeling features for measuring the attraction degree between couples of image components. This investigation would be used for content-based image retrieval from the view of mirroring human perception for images. Depending on variability in human perception for trademark images, the proposed method finds grouping areas by calculating Mahalanobis distance with the features to every combination of two components in images. The features are extracted from every combination of two components in images, and the features represent proximity, shape similarity, and closure between two components. In addition, changing combination of the features, plural grouping patterns are output. Besides, this paper shows the efficiency and limits of the proposed method from experimental results. In the experiments, 104 participants have perceived grouping patterns to 74 trademark images and the human perceptions have been compared with outputs by the proposed method for the 74 images.

Content-based image search has long been considered a difficult task. Making correct conjectures on the user intention (perception) based on the query images is a critical step in the content-based search. One key concept in this paper is how we find the user preferred low-level image characteristics from the multiple positive samples provided by the user. The second key concept is how we generate a set of consistent "pseudo images" when the user does not provide a sufficient number of samples. The notion of image feature stability is thus introduced. The third key concept is how we use negative images as pruning criterion. In realizing the preceding concepts, an image search scheme is developed using the weighted low-level image features. At the end, quantitative simulation results are used to show the effectiveness of these concepts.

Question answering (QA) is the task of retrieving an answer in response to a question by analyzing documents. Although most of the efforts in developing QA systems are devoted to dealing with electronic text, we consider it is also necessary to develop systems for document images. In this paper, we propose a method of document image retrieval for such QA systems. Since the task is not to retrieve all relevant documents but to find the answer somewhere in documents, retrieval should be precision oriented. The main contribution of this paper is to propose a method of improving precision of document image retrieval by taking into account the co-occurrence of successive terms in a question. The indexing scheme is based on two-dimensional distributions of terms and the weight of co-occurrence is measured by calculating the density distributions of terms. The proposed method was tested by using 1253 pages of documents about the major league baseball with 20 questions and found that it is superior to the baseline method proposed by the authors.

Semantic image segmentation and appropriate region content description are crucial issues for region-based image retrieval (RBIR). In this paper, a novel region-based image retrieval method is proposed, which performs fast coarse image segmentation and fine region feature extraction using the decomposition property of image wavelet transform. First, coarse image segmentation is conducted efficiently in the Low-Low(LL) frequency subband of image wavelet transform. Second, the feature vector of each segmented region is hierarchically extracted from all different wavelet frequency subbands, which captures the distinctive feature (e.g., semantic texture) inside one region finely. Experiment results show the efficiency and the effectiveness of the proposed method for region-based image retrieval.

Color histograms are effective for representing color visual features. However, the high dimensionality of feature vectors results in high computational cost. Several transformations, including singular value decomposition (SVD) and principal component analysis (PCA), have been proposed to reduce the dimensionality. In PCA, the dimensionality reduction is achieved by projecting the data to a subspace which contains most of the variance. As a common observation, the PCA basis function with the lowest frquency accounts for the highest variance. Therefore, the PCA subspace may not be the optimal one to represent the intrinsic features of data. In this paper, we apply independent component analysis (ICA) to extract the features in color histograms. PCA is applied to reduce the dimensionality and then ICA is performed on the low-dimensional PCA subspace. The experimental results show that the proposed method (1) significantly reduces the feature dimensions compared with the original color histograms and (2) outperforms other dimension reduction techniques, namely the method based on SVD of quadratic matrix and PCA, in terms of retrieval accuracy.