Region-based Image Retrieval Research Articles

Efficient histogram for region based image retrieval in the discrete cosine transform domain

<p>Recently, several approaches of content based-image retrieval (CBIR), based on the characteristics of discrete cosine transform (DCT), such as decorrelation and concentration of energy in only a few coefficients, have been proposed. To reduce the semantic gap between high level search and low level patterns, a new concept based on region based search region-based image retrieval (RBIR) has been proposed. Recently, we proposed to use shape-adaptive (SA) DCT in a new RBIR system. In this paper, we propose an efficient histogram optimization suited to our region-based concept. This histogram takes into account the pattern’s from the SA-DCT of the border blocks as well as the DCT coefficients of the internal blocks. Our proposed scheme has greatly improved the results compared to region-based reference methods. Regionbased search is limited to the object of interest only, i.e. a region of the query image can only match a region of another image in the database.</p>

Region-based image retrieval using region of interest (ROI) according to incremental frame and clustering color image

Content-based image retrieval involves the extraction of global feature images for their retrieval performance in large image databases. Extraction of global features image cause problem of the semantic gap between the high-level meaning and low-level visual features images. In this study RBIR, Region of Interest Based (ROI) Image Retrieval Using Incremental Frame of Color Image was proposed. It combines several methods, including filtering process, image partitioning using clustering and incremental frame formation, complementation law of theory set to generate ROI, NROI, or ER of the region. The concept of weighting as well as a significant query is also incorporated as a query strategy. Extensive experiments were also conducted on the Wang database and the color model selected was the CIE lab. Experimental results show the proposed method is efficient in image retrieval. The performance of the proposed method shows a better average IPR value of 3.51% compared to RGB and 22.92% with the HSV color model. Meanwhile, it also performs better by 36%, 5%, and 24% compared to methods CH (8,2,2), CH (8,3,3), and CH (16,4,4).

Content‐based image retrieval using Gaussian–Hermite moments and firefly and grey wolf optimization

Rapid growth in the transfer of multimedia information over the Internet requires algorithms to retrieve a queried image from large image database repositories. The proposed content-based image retrieval (CBIR) uses Gaussian–Hermite moments as the low-level features. Later these features are compressed with principal component analysis. The compressed feature set is multiplied with the weight matrix array, which has the same size as the feature vector. Hybrid firefly and grey wolf optimization (FAGWO) is used to prevent the premature convergence of optimization in the firefly algorithm. The retrieval of images in CBIR is carried out in an OpenCV python environment with K-nearest neighbours and random forest algorithm classifiers. The fitness function for FAGWO is the accuracy of the classifier. The FAGWO algorithm derives the optimum weights from a randomly generated initial population. When these optimized weights are applied, the proposed algorithm shows better precision/recall and efficiency than other techniques such as exact legendre moments, Region-based image retrieval, K-means clustering ​and Color descriptor wavelet-based texture descriptor retrieval technique. In terms of optimization, hybrid FAGWO outperformed various optimization techniques (when used alone) like Particle Swarm Optmization, Genetic Algorithm, Grey-Wolf Optimization and FireFly algorithm.

Region of interest-based image retrieval techniques: a review

<span lang="EN-US">This paper presents a review of the region of interest-based (ROI) image retrieval techniques. In this study, the techniques, the performance evaluation parameters, and databases used in image retrieval process are being reviewed. A part of an image that is considered important or a selected certain area of the image is what defines a region of interest. Retrieval performance in large databases can be improved with the application of content-based image retrieval systems which deals with the extraction of global and region features of images. The capability of reflecting users' specific interests with greater accuracy has shown to be more effective when using region-based features compared to global features. Segmentation, feature extraction, indexing, and retrieval of an image are the tasks required in retrieving images that contain similar regions as specified in a query. The idea of the region of interest-based image retrieval concepts is presented in this paper and it is expected to accommodate researchers that are working in the region-based image retrieval system field. This paper reviews the work of image retrieval researchers in the span of twenty years. The main goal of this paper is to provide a comprehensive reference source for scholars involved in image retrieval based on ROI.</span>

An End-to-End Trainable Multi-Column CNN for Scene Recognition in Extremely Changing Environment.

Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the paper, we interpret scene recognition as a region-based image retrieval problem and present a novel approach for scene recognition with an end-to-end trainable Multi-column convolutional neural network (MCNN) architecture. The proposed MCNN utilizes filters with receptive fields of different sizes to have Multi-level and Multi-layer image perception, and consists of three components: front-end, middle-end and back-end. The first seven layers VGG16 are taken as front-end for two-dimensional feature extraction, Inception-A is taken as the middle-end for deeper learning feature representation, and Large-Margin Softmax Loss (L-Softmax) is taken as the back-end for enhancing intra-class compactness and inter-class-separability. Extensive experiments have been conducted to evaluate the performance according to compare our proposed network to existing state-of-the-art methods. Experimental results on three popular datasets demonstrate the robustness and accuracy of our approach. To the best of our knowledge, the presented approach has not been applied for the scene recognition in literature.

A Novel Image Retrieval Technique using Automatic and Interactive Segmentation

In this paper, we present a new region-based image retrieval technique based on robust image segmentation. Traditional content-based image retrieval deals with the global description of a query image. We combine the state-of-the-art segmentation algorithms with the traditional approach to narrow the area of interest to a specific region within a query image. In case of automatic segmentation, the algorithm divides a query image automatically and computes Zernike moments for each region. For interactive segmentation, our proposed scheme takes as input a query image and some information regarding the region of interest. The proposed scheme then works by computing the Geodesic-based segmentation of the query image. The segmented image is our region of interest which is then used for computing the Zernike moments. The Euclidean distance is then used to retrieve different relevant images. The experimental results clearly show that the proposed scheme works efficiently and produces excellent results.

Merged region based image retrieval

In Region based Image Retrieval (RBIR) methods, region matching mainly focuses on region-to-region and image-to-image methods. The former may cause loss of image information and the latter may lead to similar regions being matched repeatedly. To solve these problems, we propose a new image retrieval method based on merged regions, and feature extraction and matching are processed at the category level. Merged regions in an image belong to the same category to some extent, and are obtained by a statistical region merging and affinity propagation (SRM-AP) algorithm. For feature extraction, regional convolution mapping feature (RCMF) based on the convolutional neural networks (CNN) are extracted. RCMF is further combined with the number and distribution of regions to represent the characteristics of merged regions. Moreover, to match the merged regions according to their significance in images, an integrated category matching (ICM) method is designed. Experimental results on Corel-1000 and Caltech-256 show that the proposed method is more effective than some existing RBIR methods.

A FLEXIBLE SUB-BLOCK IN REGION BASED IMAGE RETRIEVAL BASED ON TRANSITION REGION

One of the techniques in region based image retrieval (RBIR) is comparing the global feature of an entire image and the local feature of image’s sub-block in query and database image. The determined sub-block must be able to detect an object with varying sizes and locations. So the sub-block with flexible size and location is needed. We propose a new method for local feature extraction by determining the flexible size and location of sub-block based on the transition region in region based image retrieval. Global features of both query and database image are extracted using invariant moment. Local features in database and query image are extracted using hue, saturation, and value (HSV) histogram and local binary patterns (LBP). There are several steps to extract the local feature of sub-block in the query image. First, preprocessing is conducted to get the transition region, then the flexible sub-block is determined based on the transition region. Afterward, the local feature of sub-block is extracted. The result of this application is the retrieved images ordered by the most similar to the query image. The local feature extraction with the proposed method is effective for image retrieval with precision and recall value are 57%.

Region Based Image Retrieval Using Ratio of Proportional Overlapping Object

In Region Based Image Retrieval (RBIR), determination of the relevant block in query region is based on the percentage of image objects that overlap with each sub-blocks. But in some images, the size of relevant objects are small. It may cause the object to be ignored in determining the relevant sub-blocks. Therefore, in this study we proposed a system of RBIR based on the percentage of proportional objects that overlap with sub-blocks. Each sub-blocks is selected as a query region. The color and texture features of the query region will be extracted by using HSV histogram and Local Binary Pattern (LBP), respectively. We also used shape as global feature by applying invariant moment as descriptor. Experimental results show that the proposed method has average precision with 74%.

GEO matching regions: multiple regions of interests using content based image retrieval based on relative locations

Information retrieval systems are getting more attention in the era of multimedia technologies such as an image, video, audio and text files. The large numbers of images are challenges in computer systems field to store, manage data effectively and efficiently. The shape retrieval feature of different objects in the image also remains a difficult problem due to distinct angle view of different objects in a scene only; few studies have reported solution to the problem of finding relative locations of ROIs. In this paper, we proposed three methods such as1. Geolocation-based image retrieval (GLBIR), 2.Unsupervised feature technique Principal component analysis (PCA) and 3.multiple region-based image retrieval. The first proposed (GLBIR) method identifies geo location an image using visual attention based mechanism and its color layout descriptors. These features are extracted from geo-location of query image from Flickr database. Our proposed model does not fully semantic understanding of image content, uses visual metrics for example; the proximity ,color contrast, size and nearness to image's boundaries to locate viewer's attention. We analyzed results and compared with state of art CBIR Systems and GLBIR Technique. Our second method to refine images exploiting and fusing by unsupervised feature technique using principal component analysis (PCA). The visually similar images clustering together with analyses image retrieval process and remove outliers initially retrieved image set by PCA. To evaluation our proposed approach, we used thousands of images downloaded from Flickr and CIFAR-10 databases using Flickr public API. Finally, we determinately proposed a system for image retrieval based on region. It provides a user interface for availing to designate the watershed ROI within an input image. During the retrieval of images, regions' feature vectors having codes of region homogeneous to a region of input image are utilized for comparison. Standard datasets are used for evaluation of proposed approach. The experiment demonstrates and effectiveness of the proposed method to achieve higher annotation performance increases accuracy and reduces image retrieval time. We evaluated our proposed approach on images dataset from Flickr and CIFAR-10.

Query Region Determination based on Region Importance Index and Relative Position for Region-based Image Retrieval

Query Region Determination based on Region Importance Index and Relative Position for Region-based Image Retrieval

A car-face region-based image retrieval method with attention of SIFT features

A traffic still image captured by the high-definition camera located in traffic block port often contains several vehicles. It provides an important clue to solve vehicle crime cases to retrieve all these images that contain the given type of car. To enhance the performance of image retrieval, we proposed a car-face region-based image retrieval method with the attention of SIFT features. In our method, the first step is to find all the car-face regions from an original traffic image, and this original image is represented as a set of car-face regions. Secondly, a similarity measure metrics is proposed with a light intense training of the attention value of SIFT key points on a very small identified images set. Finally, according to the similarity between the input region and the target region, all the images with at least one similar region are retrieved. We carry out this method on a training set of 100 positive car-face region-images. Compared with the famous training-based SVM method, our method achieved higher precision at the same recall with lower training intensity.

A New Approach to Region Based Image Retrieval using Shape Adaptive Discrete Wavelet Transform

In this paper, we present an efficient region-based image retrieval method, which uses multi-features color, texture and edge descriptors. In contrast to recent image retrieval methods, which use discrete wavelet transform (DWT), we propose using shape adaptive discrete wavelet transform (SA-DWT). The advantage of this method is that the number of coefficients after transformation is identical to the number of pixels in the original region. Since image data is often stored in compressed formats: JPEG 2000, MPEG 4…; constructing image histograms directly in the compressed domain, allows accelerating the retrieval operation time, and reducing computing complexities. Moreover, SA-DWT represents the best way to exploit the coefficients characteristics, and properties such as the correlation. Characterizing image regions without any conversion or modification is first addressed. Using edge descriptor to complement image region characterizing is then introduced. Experimental results show that the proposed method outperforms content based image retrieval methods and recent region based image retrieval methods

Region-based image retrieval in the compressed domain using shape-adaptive DCT

Content-based image retrieval (CBIR) has drawn substantial research and many traditional CBIR systems search digital images in a large database based on features, such as color, texture and shape of a given query image. A majority of images are stored in compressed format and most of compression technologies adopt different kinds of transforms to achieve compression. Therefore, features can be extracted directly from images in compressed format by using, for example, discrete cosine transform (DCT) for JPEG compressed images. Region-based image retrieval (RBIR) is an image retrieval approach which focuses on contents from regions of images, instead of the content from the entire image in early CBIR. Although RBIR approaches attempt to solve the semantic gap problem existed in global low-level features in CBIR by using local low-level features based on regions of images. This paper proposes a new RBIR approach using Shape adaptive discrete cosine transform (SA-DCT). At a bottom level, local features are constructed from the coefficients of quantized block transforms (low-level features) for each region. Quantization acts for the concentration of block-wise information in a more condense way, which is highly desirable for the retrieval tasks. At an intermediate level, histograms of local image features are used as descriptors of statistical information. Finally, at the top level, the combination of histograms from different image regions (objects) is defined as a way to incorporate high-level semantic information. In this retrieval system, an image has a prior segmentation alpha plane, which is defined exactly as in MPEG-4. Therefore, an image is represented by segmented regions, each of which is associated with a feature vector derived from DCT and SA-DCT coefficients. Users can select any region as the main theme of the query image. The similarity between a query image and any database image is ranked according to a same similarity measure computed from the selected regions between two images. For those images without distinctive objects and scenes, users can still select the whole image as the query condition. The experimental results show that the proposed approach is able to identify main objects and reduce the influence of background in the image, and thus improve the performance of image retrieval in comparison with a conventional CBIR based on DCT.

Erratum to: Region-based image retrieval using shape-adaptive DCT

Erratum to: Region-based image retrieval using shape-adaptive DCT

Locality‐sensitive hashing for region‐based large‐scale image indexing

In this study, the authors present an efficient method for approximate large-scale image indexing and retrieval. The proposed method is mainly based on the visual content of the image regions. Indeed, regions are obtained by a fuzzy segmentation and they are described using high-frequency sub-band wavelets. Moreover, because of the difficulty in managing a huge amount of data, which is caused by the exponential growth of the processing time, approximate nearest neighbour algorithms are used to improve the retrieval speed. Therefore they adopted locality-sensitive hashing (LSH) for region-based indexing of images. In particular, since LSH performance depends fundamentally on the hash function partitioning the space, they exposed a new function, inspired from the E8 lattice, that can efficiently be combined with the multi-probe LSH and the query-adaptive LSH. To justify the adopted theoretical choices and to highlight the efficiency of the proposed method, a set of experiments related to the region-based image retrieval are carried out on the challenging ‘Wang’ data set.

Region-based image retrieval using shape-adaptive DCT

Content-based image retrieval (CBIR) is the process of searching digital images in a large database based on features, such as color, texture and shape of a given query image. As many images are compressed by transforms, constructing the feature vector directly in transform domain is a very popular topic. Therefore, features can be extracted directly from images in compressed format by using, for example, discrete cosine transform (DCT) for JPEG compressed images. Also, region-based image retrieval (RBIR) has attracted great interest in recent years. This paper proposes a new RBIR approach using shape-adaptive discrete cosine transform (SA-DCT). In this retrieval system, an image has a prior segmentation alpha plane, which is defined exactly as in MPEG-4. Therefore, an image is represented by segmented regions, each of which is associated with a feature vector derived from DCT and SA-DCT coefficients. Users can select any region as the main theme of the query image. The similarity between a query image and any database image is ranked according to a same similarity measure computed from the selected regions between two images. For those images without distinctive objects and scenes, users can still select the whole image as the query condition. The experimental results show that the proposed approach is able to identify main objects and reduce the influence of background in the image, and thus improve the performance of image retrieval in comparison with a conventional CBIR based on DCT.

Adaptive learning region importance for region‐based image retrieval

This study addresses the issue of region representation in region-based image retrieval (RBIR). In order to reduce the user's burden of selecting the region of interest, a statistical index called visual region importance (RI) is constructed to describe the region. By learning from user's current and historical feedback information, visual RI can be automatically updated and semantic RI can be obtained. Furthermore, adaptive learning RI and memory learning RI (MLRI) techniques for RBIR system have been presented. Specifically, the MLRI can mitigate the negative influence of interference regions well. Extensive experiments on the Corel-1000 dataset and the Caltech-256 dataset demonstrate that the proposed frameworks are effective, are robust and achieve significantly better performance than the other existing methods.

High-Dimensional Image Data Sets Retrieval: Improving Accuracy Using a Weighted Relevance Feedback

The user's interaction with the retrieval engines, while seeking a particular image (or set of images) in large-scale databases, defines better his request. This interaction is essentially provided by a relevance feedback step. In fact, the semantic gap is increasing in a remarkable way due to the application of approximate nearest neighbor (ANN) algorithms aiming at resolving the curse of dimensionality. Therefore, an additional step of relevance feedback is necessary in order to get closer to the user's expectations in the next few retrieval iterations. In this context, this paper details a classification of the different relevance feedback techniques related to region-based image retrieval applications. Moreover, a technique of relevance feedback based on re-weighting regions of the query-image by selecting a set of negative examples is elaborated. Furthermore, the general context to carry out this technique which is the large-scale heterogeneous image collections indexing and retrieval is presented. In fact, the main contribution of the proposed work is affording efficient results with the minimum number of relevance feedback iterations for high dimensional image databases. Experiments and assessments are carried out within an RBIR system for "Wang" data set in order to prove the effectiveness of the proposed approaches.

Feature Fusion Based Image Retrieval Using Deep Learning

In the last decades, Content Based Image Retrieval and image classification have become popular, and among them Region-based Image Retrieval is quite active. More and more descriptors and retrieval methods have been proposed and investigated in order to improve the retrieval performance. This paper proposed a feature fusion deep learning method. The features including colors, texture and shape, which are extracted from both the entire image and regions. The features are then trained using diverse deep learning methods. The conducted deep learning methods include Sparse Auto-encoders, Denoising Autoencoding, Deep Belief Nets, Drop Out Neural Networks, and Deep Boltzmann Machine. The method is evaluated through extensive experiments on Corel 10K datasets. Experimental results demonstrate that the introduced methods are comparable with the state-of-arts in this image retrieval application.