Showing papers on "Content-based image retrieval published in 2018"
TL;DR: The experimental evaluation on three publicly available image retrieval datasets indicates the effectiveness of the proposed model retraining method in learning more efficient representations for the retrieval task, outperforming other CNN-based retrieval techniques, as well as conventional hand-crafted feature-based approaches in all the used datasets.
166 citations
TL;DR: This work investigates three different quantization schemes and proposes for each one an efficient retrieval approach, exploiting the inherent properties of each quantizer to reduce the drop of retrieval performances resulting from the quantization effect.
Abstract: With the great demand for storing and transmitting images as well as their managing, the retrieval of compressed images is a field of intensive research. While most of the works have been devoted to the case of losslessly encoded images (by extracting features from the unquantized transform coefficients), new studies have shown that lossy compression has a negative impact on the performance of conventional retrieval systems. In this work, we investigate three different quantization schemes and propose for each one an efficient retrieval approach. More precisely, the uniform quantizer, the moment preserving quantizer and the distribution preserving quantizer are considered. The inherent properties of each quantizer are then exploited to design an efficient retrieval strategy, and hence, to reduce the drop of retrieval performances resulting from the quantization effect. Experimental results, carried out on three standard texture databases and a color dataset, show the benefits which can be drawn from the proposed retrieval approaches.
164 citations
TL;DR: The proposed scheme transforms the EMD problem in such a way that the cloud server can solve it without learning the sensitive information, and local sensitive hash (LSH) is utilized to improve the search efficiency.
Abstract: Content-based image retrieval (CBIR) applications have been rapidly developed along with the increase in the quantity, availability and importance of images in our daily life. However, the wide deployment of CBIR scheme has been limited by its the severe computation and storage requirement. In this paper, we propose a privacy-preserving content-based image retrieval scheme, which allows the data owner to outsource the image database and CBIR service to the cloud, without revealing the actual content of the database to the cloud server. Local features are utilized to represent the images, and earth mover's distance (EMD) is employed to evaluate the similarity of images. The EMD computation is essentially a linear programming (LP) problem. The proposed scheme transforms the EMD problem in such a way that the cloud server can solve it without learning the sensitive information. In addition, local sensitive hash (LSH) is utilized to improve the search efficiency. The security analysis and experiments show the security and efficiency of the proposed scheme.
152 citations
TL;DR: This paper proposes a novel hashing approach, dubbed as discrete semantic transfer hashing (DSTH), to directly augment the semantics of discrete image hash codes by exploring auxiliary contextual modalities and guarantees direct semantic transfer and avoid information loss.
Abstract: Unsupervised hashing can desirably support scalable content-based image retrieval for its appealing advantages of semantic label independence, memory, and search efficiency. However, the learned hash codes are embedded with limited discriminative semantics due to the intrinsic limitation of image representation. To address the problem, in this paper, we propose a novel hashing approach, dubbed as discrete semantic transfer hashing (DSTH). The key idea is to directly augment the semantics of discrete image hash codes by exploring auxiliary contextual modalities. To this end, a unified hashing framework is formulated to simultaneously preserve visual similarities of images and perform semantic transfer from contextual modalities. Furthermore, to guarantee direct semantic transfer and avoid information loss, we explicitly impose the discrete constraint, bit-uncorrelation constraint, and bit-balance constraint on hash codes. A novel and effective discrete optimization method based on augmented Lagrangian multiplier is developed to iteratively solve the optimization problem. The whole learning process has linear computation complexity and desirable scalability. Experiments on three benchmark data sets demonstrate the superiority of DSTH compared with several state-of-the-art approaches.
127 citations
TL;DR: A new image retrieval technique using local neighborhood difference pattern (LNDP) has been proposed for local features and shows a significant improvement in the proposed method over existing methods.
Abstract: A new image retrieval technique using local neighborhood difference pattern (LNDP) has been proposed for local features. The conventional local binary pattern (LBP) transforms every pixel of image into a binary pattern based on their relationship with neighboring pixels. The proposed feature descriptor differs from local binary pattern as it transforms the mutual relationship of all neighboring pixels in a binary pattern. Both LBP and LNDP are complementary to each other as they extract different information using local pixel intensity. In the proposed work, both LBP and LNDP features are combined to extract the most of the information that can be captured using local intensity differences. To prove the excellence of the proposed method, experiments have been conducted on four different databases of texture images and natural images. The performance has been observed using well-known evaluation measures, precision and recall and compared with some state-of-art local patterns. Comparison shows a significant improvement in the proposed method over existing methods.
123 citations
TL;DR: A new non-dominated sorting based on multi-objective whale optimization algorithm is proposed for content-based image retrieval (NSMOWOA) and shows a good performance in content- based image retrieval problem in terms of recall and precision.
Abstract: In the recent years, there are massive digital images collections in many fields of our life, which led the technology to find methods to search and retrieve these images efficiently. The content-based is one of the popular methods used to retrieve images, which depends on the color, texture and shape descriptors to extract features from images. However, the performance of the content-based image retrieval methods depends on the size of features that are extracted from images and the classification accuracy. Therefore, this problem is considered as a multi-objective and there are several methods that used to manipulate it such as NSGA-II and NSMOPSO. However, these methods have drawbacks such as their time and space complexity are large since they used traditional non-dominated sorting methods. In this paper, a new non-dominated sorting based on multi-objective whale optimization algorithm is proposed for content-based image retrieval (NSMOWOA). The proposed method avoids the drawbacks in other non-dominated sorting multi-objective methods that have been used for content-based image retrieval through reducing the space and time complexity. The results of the NSMOWOA showed a good performance in content-based image retrieval problem in terms of recall and precision.
99 citations
TL;DR: This work proposes a two-step hierarchical shrinking search space, consisting of the most similar images for a given query, to be used for a similarity-based search technique in a retrieval system when local binary patterns are used.
Abstract: Closing the semantic gap in medical image analysis is critical. Access to large-scale datasets might help to narrow the gap. However, large and balanced datasets may not always be available. On the other side, retrieving similar images from an archive is a valuable task to facilitate better diagnosis. In this work, we concentrate on forming a search space, consisting of the most similar images for a given query, to be used for a similarity-based search technique in a retrieval system. We propose a two-step hierarchical shrinking search space when local binary patterns are used. Transfer learning via convolutional neural networks is utilized for the first stage of search space shrinking, followed by creating a selection pool using Radon transform for further reduction. The difference between two orthogonal Radon projections is considered in the selection pool to extract more information. The IRMA dataset, from ImageCLEF initiative, containing 14,400 X-ray images, is used to validate the proposed scheme. We report a total IRMA error of 168.05 (or 90.30% accuracy) which is the best result compared with existing methods in the literature for this dataset when real-time processing is considered.
96 citations
TL;DR: The efficiency and effectiveness of the proposed approach outperforms the existing research in term of average precision and recall values and compared with different other proposed methods with demonstrate the predominance of the method.
Abstract: Due to recent development in technology, the complexity of multimedia is significantly increased and the retrieval of similar multimedia content is a open research problem. Content-Based Image Retrieval (CBIR) is a process that provides a framework for image search and low-level visual features are commonly used to retrieve the images from the image database. The basic requirement in any image retrieval process is to sort the images with a close similarity in term of visually appearance. The color, shape and texture are the examples of low-level image features. The feature plays a significant role in image processing. The powerful representation of an image is known as feature vector and feature extraction techniques are applied to get features that will be useful in classifying and recognition of images. As features define the behavior of an image, they show its place in terms of storage taken, efficiency in classification and obviously in time consumption also. In this paper, we are going to discuss various types of features, feature extraction techniques and explaining in what scenario, which features extraction technique will be better. The effectiveness of the CBIR approach is fundamentally based on feature extraction. In image processing errands like object recognition and image retrieval feature descriptor is an immense among the most essential step. The main idea of CBIR is that it can search related images to an image passed as query from a dataset got by using distance metrics. The proposed method is explained for image retrieval constructed on YCbCr color with canny edge histogram and discrete wavelet transform. The combination of edge of histogram and discrete wavelet transform increase the performance of image retrieval framework for content based search. The execution of different wavelets is additionally contrasted with discover the suitability of specific wavelet work for image retrieval. The proposed algorithm is prepared and tried to implement for Wang image database. For Image Retrieval Purpose, Artificial Neural Networks (ANN) is used and applied on standard dataset in CBIR domain. The execution of the recommended descriptors is assessed by computing both Precision and Recall values and compared with different other proposed methods with demonstrate the predominance of our method. The efficiency and effectiveness of the proposed approach outperforms the existing research in term of average precision and recall values.
95 citations
TL;DR: A hybrid feature based efficient CBIR system is proposed using various distance measure to enhance precision binarized statistical image features, color and edge directivity descriptor features are employed for developing efficient CBIr system.
81 citations
03 Mar 2018
TL;DR: The experimental results show that the proposed CBIR technique to fuse color and texture features outperforms with existing CBIR systems and precision and recall methods are used that provides competitive and efficient result.
Abstract: In last few decades. Content Based Image Retrieval System (CBIR) is an emerging field to retrieve relevant images from a database. It utilizes the visual contents of an image for the local and global features. Local feature includes spatial domain which presents the significance of the image as well as the index of an image. Global feature includes shape descriptors, contour representations and texture features. Segmentation process is required in global feature extraction technique. It is a challenging task to simulate visual information in CBIR system. CBIR strategy combines the local and global features to deal with the low level information. In this paper, we proposed new CBIR technique to fuse color and texture features. Color Histogram (CH) is used to extract a color information. Texture features are extracted by Discrete Wavelet Transform (DWT) and Edge Histogram Descriptor (EDH). The features are created for each image and stored as a feature vector in the database. We evaluated our work using Corel 1-k dataset. To examine the accuracy with the other proposed systems, precision and recall methods are used that provides competitive and efficient result. The experimental results show that our proposed method outperforms with existing CBIR systems.
73 citations
TL;DR: A novel image representation based on the weighted average of triangular histograms (WATH) of visual words is presented, which adds the image spatial contents to the inverted index of the BoVW model, reduces overfitting problem on larger sizes of the dictionary and semantic gap issues between high-level image semantic and low- level image features.
Abstract: In recent years, the rapid growth of multimedia content makes content-based image retrieval (CBIR) a challenging research problem. The content-based attributes of the image are associated with the position of objects and regions within the image. The addition of image content-based attributes to image retrieval enhances its performance. In the last few years, the bag-of-visual-words (BoVW) based image representation model gained attention and significantly improved the efficiency and effectiveness of CBIR. In BoVW-based image representation model, an image is represented as an order-less histogram of visual words by ignoring the spatial attributes. In this paper, we present a novel image representation based on the weighted average of triangular histograms (WATH) of visual words. The proposed approach adds the image spatial contents to the inverted index of the BoVW model, reduces overfitting problem on larger sizes of the dictionary and semantic gap issues between high-level image semantic and low-level image features. The qualitative and quantitative analysis conducted on three image benchmarks demonstrates the effectiveness of the proposed approach based on WATH.
TL;DR: In this paper, a new texture descriptor based on the local neighborhood intensity difference is proposed for content based image retrieval (CBIR), which considers the relative intensity difference between a particular pixel and the center pixel by considering its adjacent neighbors and generate a sign and a magnitude pattern.
Abstract: In this paper, a new texture descriptor based on the local neighborhood intensity difference is proposed for content based image retrieval (CBIR). For computation of texture features like Local Binary Pattern (LBP), the center pixel in a 3 × 3 window of an image is compared with all the remaining neighbors, one pixel at a time to generate a binary bit pattern. It ignores the effect of the adjacent neighbors of a particular pixel for its binary encoding and also for texture description. The proposed method is based on the concept that neighbors of a particular pixel hold significant amount of texture information that can be considered for efficient texture representation for CBIR. The main impact of utilizing the mutual relationship among adjacent neighbors is that we do not rely on the sign of the intensity difference between central pixel and one of its neighbors (Ii) only, rather we take into account the sign of difference values between Ii and its adjacent neighbors along with the central pixels and same set of neighbors of Ii. This makes our pattern more resistant to illumination changes. Moreover, most of the local patterns including LBP concentrates mainly on the sign information and thus ignores the magnitude. The magnitude information which plays an auxiliary role to supply complementary information of texture descriptor, is integrated in our approach by considering the mean of absolute deviation about each pixel Ii from its adjacent neighbors. Taking this into account, we develop a new texture descriptor, named as Local Neighborhood Intensity Pattern (LNIP) which considers the relative intensity difference between a particular pixel and the center pixel by considering its adjacent neighbors and generate a sign and a magnitude pattern. Finally, the sign pattern (LNIPS) and the magnitude pattern (LNIPM) are concatenated into a single feature descriptor to generate a more effective feature descriptor. The proposed descriptor has been tested for image retrieval on four databases, including three texture image databases - Brodatz texture image database, MIT VisTex database and Salzburg texture database and one face database - AT&T face database. The precision and recall values observed on these databases are compared with some state-of-art local patterns. The proposed method showed a significant improvement over many other existing methods.
TL;DR: The qualitative and quantitative analysis performed on three image collections shows that proposed technique based on visual words fusion significantly improved the performance of the CBIR as compared to the feature fusion of both descriptors and state-of-the-art image retrieval techniques.
Abstract: For the last three decades, content-based image retrieval (CBIR) has been an active research area, representing a viable solution for retrieving similar images from an image repository. In this article, we propose a novel CBIR technique based on the visual words fusion of speeded-up robust features (SURF) and fast retina keypoint (FREAK) feature descriptors. SURF is a sparse descriptor whereas FREAK is a dense descriptor. Moreover, SURF is a scale and rotation-invariant descriptor that performs better in the case of repeatability, distinctiveness, and robustness. It is robust to noise, detection errors, geometric, and photometric deformations. It also performs better at low illumination within an image as compared to the FREAK descriptor. In contrast, FREAK is a retina-inspired speedy descriptor that performs better for classification-based problems as compared to the SURF descriptor. Experimental results show that the proposed technique based on the visual words fusion of SURF-FREAK descriptors combines the features of both descriptors and resolves the aforementioned issues. The qualitative and quantitative analysis performed on three image collections, namely Corel-1000, Corel-1500, and Caltech-256, shows that proposed technique based on visual words fusion significantly improved the performance of the CBIR as compared to the feature fusion of both descriptors and state-of-the-art image retrieval techniques.
15 Oct 2018
TL;DR: APANet as mentioned in this paper proposes an attention-based pyramid aggregation network to encode the multi-size buildings containing geo-information and uses the attention block as a region evaluator for suppressing the confusing regional features.
Abstract: Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the complex urban scene, and buildings with repetitive structures may cause over-counting and the burstiness problem degrading the image representations. To address these problems, we present an Attention-based Pyramid Aggregation Network (APANet), which is trained in an end-to-end manner for place recognition. One main component of APANet, the spatial pyramid pooling, can effectively encode the multi-size buildings containing geo-information. The other one, the attention block, is adopted as a region evaluator for suppressing the confusing regional features while highlighting the discriminative ones. When testing, we further propose a simple yet effective PCA power whitening strategy, which significantly improves the widely used PCA whitening by reasonably limiting the impact of over-counting. Experimental evaluations demonstrate that the proposed APANet outperforms the state-of-the-art methods on two place recognition benchmarks, and generalizes well on standard image retrieval datasets.
TL;DR: Locality Preserving Projection is employed to reduce the length of the feature vector to enhance the performance of image retrieval system and the highest precision rate is accomplished using proposed CBIR system.
Abstract: In the progression of web and multi-media, substantial measure of pictures is created and appropriated, to viably store and offer such vast measure of bulky database is a big issue. In this way, Content Based Image Retrieval (CBIR) techniques are used to retrieve images from the massive database based on the desired information. In this proposed work, we are considering two local image feature extraction methods, namely, SIFT and ORB. Scale Invariant Feature Transform (SIFT) is used for detecting features and feature descriptor of an image. Oriented Fast Rotated and BRIEF (ORB) uses FAST (Features from Accelerated Segment Test) key point detector and binary BRIEF (Binary Robust Independent Elementary Features) descriptor of an image. K-Means clustering algorithm is also used in the present paper for analyzing the data, which generates number of clusters using the descriptor vector. Locality Preserving Projection (LPP) is employed to reduce the length of the feature vector to enhance the performance of image retrieval system. For classification, we have considered two classifiers, namely, BayesNet and K-Nearest Neighbours (K-NN). Wang image dataset has been used for experimentation work. We have accomplished the highest precision rate of 88.9% using proposed CBIR system.
TL;DR: An effective novel technique is introduced to improve the performance of CBIR on the basis of visual words fusion of scale-invariant feature transform (SIFT) and local intensity order pattern (LIOP) descriptors which overcomes the aforementioned issues and significantly improves the performanceof CBIR.
Abstract: Content-based image retrieval (CBIR) is a mechanism that is used to retrieve similar images from an image collection. In this paper, an effective novel technique is introduced to improve the performance of CBIR on the basis of visual words fusion of scale-invariant feature transform (SIFT) and local intensity order pattern (LIOP) descriptors. SIFT performs better on scale changes and on invariant rotations. However, SIFT does not perform better in the case of low contrast and illumination changes within an image, while LIOP performs better in such circumstances. SIFT performs better even at large rotation and scale changes, while LIOP does not perform well in such circumstances. Moreover, SIFT features are invariant to slight distortion as compared to LIOP. The proposed technique is based on the visual words fusion of SIFT and LIOP descriptors which overcomes the aforementioned issues and significantly improves the performance of CBIR. The experimental results of the proposed technique are compared with another proposed novel features fusion technique based on SIFT-LIOP descriptors as well as with the state-of-the-art CBIR techniques. The qualitative and quantitative analysis carried out on three image collections, namely, Corel-A, Corel-B, and Caltech-256, demonstrate the robustness of the proposed technique based on visual words fusion as compared to features fusion and the state-of-the-art CBIR techniques.
TL;DR: Qualitative and quantitative analyses performed on four standard image collections demonstrate the effectiveness of the proposed technique based on visual words fusion of SURF and HOG feature descriptors, which gives classification accuracy of 98.40% and image retrieval accuracy of 80.61%, respectively.
Abstract: Due to the advancements in digital technologies and social networking, image collections are growing exponentially. The important aim in content-based image retrieval (CBIR) is to reduce the semantic gap issue that improves the performance of image retrieval. In this paper, the objective is achieved by introducing effective visual words fusion technique based on speeded-up robust features (SURF) and histograms of oriented gradients (HOG) feature descriptors. HOG is used to extract global features, whereas SURF is used for the extraction of local features. Global features are preferred for large-scale image retrieval, whereas local features perform better on those systems that support semantic queries with close visual appearance. Moreover, SURF is scale and rotation-invariant as compared to HOG descriptor and it works better for low illumination. On the contrary, HOG performs better for scene-recognition- or activity-recognition-based applications. In the proposed technique, visual words fusion of SURF and HOG feature descriptors is carried which performed better than features fusion of SURF and HOG feature descriptors as well as state-of-the-art CBIR techniques. The proposed technique based on visual words fusion gives classification accuracy of 98.40% using support vector machine while image retrieval accuracy of 80.61%. Qualitative and quantitative analyses performed on four standard image collections namely, Corel-1000, Corel-1500, Corel-5000, and Caltech-256 demonstrate the effectiveness of the proposed technique based on visual words fusion of SURF and HOG feature descriptors.
TL;DR: A new two-step CBIR scheme (TSCBIR) for computer-aided diagnosis of lung nodules, where semantic relevance and visual similarity are introduced to measure the similarity of different nodules.
Abstract: Similarity measurement of lung nodules is a critical component in content-based image retrieval (CBIR), which can be useful in differentiating between benign and malignant lung nodules on computer tomography (CT). This paper proposes a new two-step CBIR scheme (TSCBIR) for computer-aided diagnosis of lung nodules. Two similarity metrics, semantic relevance and visual similarity, are introduced to measure the similarity of different nodules. The first step is to search for K most similar reference ROIs for each queried ROI with the semantic relevance metric. The second step is to weight each retrieved ROI based on its visual similarity to the queried ROI. The probability is computed to predict the likelihood of the queried ROI depicting a malignant lesion. In order to verify the feasibility of the proposed algorithm, a lung nodule dataset including 366 nodule regions of interest (ROIs) is assembled from LIDC-IDRI lung images on CT scans. Three groups of texture features are implemented to represent a nodule ROI. Our experimental results on the assembled lung nodule dataset show good performance improvement over existing popular classifiers.
TL;DR: A parallel deep solution approach based on convolutional neural networks followed by a local search using LBP, HOG and Radon features is proposed, which surpasses the dictionary approach and many other learning methods applied on the same dataset.
TL;DR: This new approach to color image retrieval is validated after extensive comparisons with several existing state of the art approaches on two benchmark datasets including the Wang's dataset and large size of the Corel-10000 dataset.
Abstract: In this paper, we propose a novel color image retrieval approach by using an effective fusion of two types of histograms extracted from color and local directional pattern (LDP), respectively. First, we describe the extraction process of color histogram and LDP. Secondly we present these two features and then develop an effective fusion procedure including feature normalization and a new similarity metric. Thirdly, this new approach is validated after extensive comparisons with several existing state of the art approaches on two benchmark datasets including the Wang’s dataset and large size of the Corel-10000 dataset. Finally, a friendly interface for this proposed retrieval system is designed and used to show some retrieval results.
TL;DR: A collaborative index embedding method to implicitly integrate the index matrices of deep convolutional neural network features and achieves competitive accuracy performance with less memory overhead and efficient query computation.
Abstract: In content-based image retrieval, SIFT feature and the feature from deep convolutional neural network (CNN) have demonstrated promising performance. To fully explore both visual features in a unified framework for effective and efficient retrieval, we propose a collaborative index embedding method to implicitly integrate the index matrices of them. We formulate the index embedding as an optimization problem from the perspective of neighborhood sharing and solve it with an alternating index update scheme. After the iterative embedding, only the embedded CNN index is kept for on-line query, which demonstrates significant gain in retrieval accuracy, with very economical memory cost. Extensive experiments have been conducted on the public datasets with million-scale distractor images. The experimental results reveal that, compared with the recent state-of-the-art retrieval algorithms, our approach achieves competitive accuracy performance with less memory overhead and efficient query computation.
TL;DR: An improved SIFT algorithm is proposed, which preserves the advantages of SIFT algorithms in fuzzy, compression, rotation and scaling invariance advantages, and improves the matching speed, the correct match rate is increased by an average of 40% to 55%.
Abstract: This paper proposed a high-performance image retrieval framework, which combines the improved feature extraction algorithm SIFT (Scale Invariant Feature Transform), improved feature matching, impro...
TL;DR: A novel BoVW-based method that incorporates texture and spatial information for the content-based image retrieval to assist radiologists in clinical diagnosis and preliminary results indicate that the texture-specific features and the SCM-based BoVW features can effectively characterize various liver lesions.
Abstract: The bag of visual words (BoVW) model is a powerful tool for feature representation that can integrate various handcrafted features like intensity, texture, and spatial information. In this paper, we propose a novel BoVW-based method that incorporates texture and spatial information for the content-based image retrieval to assist radiologists in clinical diagnosis. This paper presents a texture-specific BoVW method to represent focal liver lesions (FLLs). Pixels in the region of interest (ROI) are classified into nine texture categories using the rotation-invariant uniform local binary pattern method. The BoVW-based features are calculated for each texture category. In addition, a spatial cone matching (SCM)-based representation strategy is proposed to describe the spatial information of the visual words in the ROI. In a pilot study, eight radiologists with different clinical experience performed diagnoses for 20 cases with and without the top six retrieved results. A total of 132 multiphase computed tomography volumes including five pathological types were collected. The texture-specific BoVW was compared to other BoVW-based methods using the constructed dataset of FLLs. The results show that our proposed model outperforms the other three BoVW methods in discriminating different lesions. The SCM method, which adds spatial information to the orderless BoVW model, impacted the retrieval performance. In the pilot trial, the average diagnosis accuracy of the radiologists was improved from 66 to 80% using the retrieval system. The preliminary results indicate that the texture-specific features and the SCM-based BoVW features can effectively characterize various liver lesions. The retrieval system has the potential to improve the diagnostic accuracy and the confidence of the radiologists.
TL;DR: The experimental results demonstrate that the proposed CBIR technique outperforms other multiscale LBP techniques as well as some of the other state-of-the-art CBIR methods.
Abstract: With the development of different image capturing devices, huge amount of complex images are being produced everyday. Easy access to such images requires proper arrangement and indexing of images which is a challenging task. The field of Content-Based Image Retrieval (CBIR) deals with finding solutions to such problems. This paper proposes a CBIR technique through multiscale Local Binary Pattern (LBP). Instead of considering consecutive neighbourhood pixels, Local Binary Pattern of different combinations of eight neighbourhood pixels is computed at multiple scales. The final feature vector is constructed through Gray Level Co-occurrence Matrix (GLCM). Advantage of the proposed multiscale LBP scheme is that it overcomes the limitations of single scale LBP and acts as more robust feature descriptor. It efficiently captures large scale dominant features of some textures which single scale LBP fails to do and also overcomes some of the limitations of other multiscale LBP techniques. Performance of the proposed technique is tested on five benchmark datasets, namely, Corel-1K, Olivia-2688, Corel-5K, Corel-10K, and GHIM-10K and measured in terms of precision and recall. The experimental results demonstrate that the proposed method outperforms other multiscale LBP techniques as well as some of the other state-of-the-art CBIR methods.
TL;DR: A novel hierarchical-local-feature extraction scheme for CBIR, whereas complex image segmentation is avoided, and experimental results show that the developed CBIR system produces plausible retrieval results.
Abstract: Recently, with the development of various camera sensors and internet network, the volume of digital images is becoming big. Content-based image retrieval (CBIR), especially in network big data analysis, has attracted wide attention. CBIR systems normally search the most similar images to the given query example among a wide range of candidate images. However, human psychology suggests that users concern more about regions of their interest and merely want to retrieve images containing relevant regions, while ignoring irrelevant image areas (such as the texture regions or background). Previous CBIR system on user-interested image retrieval generally requires complicated segmentation of the region from the background. In this paper, we propose a novel hierarchical-local-feature extraction scheme for CBIR, whereas complex image segmentation is avoided. In our CBIR system, a perception-based directional patch extraction method and an improved salient patch detection algorithm are proposed for local features extraction. Then, color moments and Gabor texture features are employed to index the salient regions. Extensive experiments have been performed to evaluate the performance of the proposed scheme, and experimental results show that the developed CBIR system produces plausible retrieval results.
TL;DR: A new texture descriptor is developed which is a combination of Local Ternary Pattern (LTP) and gray level co-occurrence matrix (GLCM) and inherits the attributes of both LTP and GLCM.
TL;DR: A novel approach to retrieve similar textual images by exploiting visual and textual characteristics of the image using Kernel method, which shows the textual features can be as effective as visual features for CBIR applications.
Journal Article•
TL;DR: The experimental analysis carriedout on two image datasets validates that the proposed image representation based on the division of an image into histograms of rectangles increases the performance of image retrieval.
Abstract: Content-based image retrieval (CBIR) provides a solution to search the images that are similar to a query image. From last few years, the bag-of-visual-words (BoVW) model gained significance and improved the performance of CBIR. In a standard BoVW model, an image is represented as an order-less histogram of visual words, by ignoring the spatial layout of the image. The spatial layout carries significant information that can enhance the image retrieval accuracy. In this paper, we present a novel method of image representation, which is based on the construction of histograms over two rectangular regions of an image. Divisionof the image into two rectangular regions at the time of construction of histograms adds the spatial information to the BoVW model. The proposed image representation uses separate visual words for upper and lower rectangular regions of an image. The experimental analysis carriedout on two image datasets validates that the proposed image representation based on the division of an image into histograms of rectangles increases the performance of image retrieval.
TL;DR: Experimental evaluations with frequently used datasets show that the proposed method yields better results as compared to other state-of-the-art techniques.
Abstract: Content based image retrieval (CBIR) systems allow searching for visually similar images in large collections based on their contents. Visual contents are usually represented based on their properties like colors, shapes, and textures. In this paper, we propose to integrate two properties of images for constructing a discriminative and robust representation. Firstly, the input image is transformed into the HSV color space and then quantized into a limited number of representative colors. Secondly, texture features based on uniform patterns of rotated local binary patterns (RLBP) are extracted. The characteristics of color histogram populated from the quantized images and texture features are compared and analyzed for image representation. Consequently, the quantized color histogram and histogram of uniform patterns in RLBP are fused together to form a feature vector. Experimental evaluations with frequently used datasets show that the proposed method yields better results as compared to other state-of-the-art techniques.
01 Jun 2018
TL;DR: This paper reviews the recent works in CBIR that attempts to reduce the semantic gap in extracting the features from medical images, precisely for mammogram images and suggests approaches such as the use of relevance feedback, ontology as well as machine learning algorithms.
Abstract: Content-based Image Retrieval (CBIR) aids radiologist to identify similar medical
images in recalling previous cases during diagnosis. Although several algorithms have been
introduced to extract the content of the medical images, the process is still a challenge due to
the nature of the feature itself where most of them are extracted in low level form. In addition
to the dimensionality reduction problem caused by the low-level features, current features are
also insufficient to convey the semantic meaning of the images. This paper reviews the recent
works in CBIR that attempts to reduce the semantic gap in extracting the features from medical
images, precisely for mammogram images. Approaches such as the use of relevance feedback,
ontology as well as machine learning algorithms are summarized and discussed.