Image Retrieval Applications Research Articles

Machine learning-based framework for saliency detection in distorted images

Visual saliency detection is useful in carrying out image compression, image segmentation, image retrieval, and other image processing applications. Majority of existing saliency detection algorithms are presented for distortion-free images. However, this situation is not always the case. In this paper, we first evaluate the performances of state-of-the-art saliency detection algorithms against different distortion types and levels. A machine learning-based framework for saliency detection is proposed for two common types of distortions, noise and JPEG compression. First, a machine learning method is proposed to predict the distortion level, and then the distortion is removed using the parameter setting that is tuned for that distortion level. Finally, the saliency map is calculated by using saliency detection algorithms. We evaluate the saliency detection algorithms on Tampere Image Database (TID2013), which is proposed for image quality assessment application. We manually label the salient objects in each image and obtain its ground truth saliency map in order to adapt TID2013 for visual saliency detection application. Experimental results demonstrate that the distortions usually decrease the performances of the saliency detection algorithms, particularly in high levels of distortions. The performance rankings of the saliency detection algorithms for the distortion-free images and distorted images are different. Moreover, our proposed machine learning-based framework for saliency detection improves the performances of saliency detection algorithms in distorted images in most of the distortion levels, particularly in high levels of distortions.

Similarity in spatial utilization distributions measured by the earth mover's distance

Summary Estimating the similarity in space use (spatio‐temporal home range overlap) of animals is important for many questions regarding behavioural ecology, wildlife management and conservation. The current methods that calculate joint space use generally do not account for proximity in space use, as all of them rely on the differences between the exact spatial overlay of utilization distributions, while spatial distances between distributions should be considered to truly quantify similarity. We implemented the earth mover's distance (EMD), a spatially explicit method, that quantifies similarity between utilization distributions by calculating the effort it takes to shape one utilization distribution landscape into another, hence EMD. The EMD is a method commonly used in image retrieval applications, and we propose its use to calculate similarity in space use in the framework of movement ecology. We show that the EMD is a consistent and useful as well as versatile measure of overlap and provide an easy to use implementation in the r package move.

Interpretation of users’ feedback via swarmed particles for content-based image retrieval

While providing relevance feedback (RF) by users proves to be an effective method for content-based image retrieval, how to interpret and learn from the user-provided feedback, however, remains an unsolved problem. In this paper, we propose an integrated users-feedback and learning algorithm by screening individual elements of content features and driving a group of swarmed particles inside the feature space to provide a possible solution. In comparison with the existing approaches, the proposed algorithm achieves a number of advantages, which can be highlighted as: (i) interpretation of users’ feedback is independent of both the content features and relevance feedback schemes, and hence the proposed algorithm can be applicable to any content features and relevance feedback methods; (ii) the RF interpretation is followed by a group of swarmed particles, acting as multiple agents rather than a single query image in searching for the desirable images; (iii) the proposed RF interpretation and learning is exploited not only in reweighting the content similarity measurement, but also in regrouping the database images. Extensive experiments support that our proposed algorithm outperforms the existing representative techniques, providing good potential for further research and development for a wide range of content-based image retrieval applications.

Local extreme complete trio pattern for multimedia image retrieval system

This paper presents a new feature descriptor, namely local extreme complete trio pattern (LECTP) for image retrieval application. The LECTP extracts complete extreme to minimal edge information in all possible directions using trio values. The LECTP integrates the local extreme sign trio patterns (LESTP) with magnitude local operator (MLOP) for image retrieval. The performance of the LECTP is tested by conducting three experiments on Corel-5 000, Corel-10 000 and MIT-VisTex color databases, respectively. The results after investigation show a significant improvement in terms of average retrieval precision (ARP) and average retrieval rate (ARR) as compared to the other state-of-the art techniques in content based image retrieval (CBIR).

IMAGE ANNOTATION USING VISUAL CONTENT AND OPTIMIZING OPEN KNOWLEDGE BASE

Open knowledge bases such as the Cyc and DBPedia contain rich knowledge sources for various applications. In the case of image annotation and retrieval applications, such knowledge can be tapped and exploited to semantically annotate poorly annotated images or even images which have not been annotated. We proposed an approach to annotate images by using the visual content of images and subsequently used such content to assign suitable seeds annotation to target images. These seeds annotation are then mapped to the open knowledge base in order to further enrich its semantic information.

Visual homograph: A novel basic visual element

The bag-of-visual-words (BoW) model has been broadly applied to represent images in a variety of image retrieval applications. Ideal visual word vocabulary should obtain two important properties, completeness and distinctiveness (i.e., containing all the similar image patches and eliminating different ones accurately). However, the traditional definition of basic visual elements tend to lack in either generality or particularity, which will lead to the incoherence problem and further ruin the image retrieval performance. To address this issue, in this paper, we propose a novel basic visual element called Visual Homograph – groups of local patches which have indivisible descriptors but differ in origins. To generate Visual Homograph based vocabulary, we also propose a novel similarity metric named Integrated Perceptual Similarity which systematically combines center-based and boundary-based measures. Experimental results on standard datasets demonstrate the superiority of Visual Homograph based method over state-of-the-art visual vocabulary generation approaches, in terms of alleviating incoherence problem, and enhancing retrieval performance in practical applications.

Local directional mask maximum edge patterns for image retrieval and face recognition

This study proposes a new feature descriptor, local directional mask maximum edge pattern, for image retrieval and face recognition applications. Local binary pattern (LBP) and LBP variants collect the relationship between the centre pixel and its surrounding neighbours in an image. Thus, LBP based features are very sensitive to the noise variations in an image. Whereas the proposed method collects the maximum edge patterns (MEP) and maximum edge position patterns (MEPP) from the magnitude directional edges of face/image. These directional edges are computed with the aid of directional masks. Once the directional edges (DE) are computed, the MEP and MEPP are coded based on the magnitude of DE and position of maximum DE. Further, the robustness of the proposed method is increased by integrating it with the multiresolution Gaussian filters. The performance of the proposed method is tested by conducting four experiments onopen access series of imaging studies-magnetic resonance imaging, Brodatz, MIT VisTex and Extended Yale B databases for biomedical image retrieval, texture retrieval and face recognition applications. The results after being investigated the proposed method shows a significant improvement as compared with LBP and LBP variant features in terms of their evaluation measures on respective databases.

Combining Block DCV and Support Vector Machine for Ear Recognition

In recent years, automatic ear recognition has become a popular research. Effective feature extraction is one of the most important steps in Content-based ear image retrieval applications. In this paper, the authors proposed a new vectors construction method for ear retrieval based on Block Discriminative Common Vector. According to this method, the ear image is divided into 16 blocks firstly and the features are extracted by applying DCV to the sub-images. Furthermore, Support Vector Machine is used as classifier to make decision. The experimental results show that the proposed method performs better than classical PCA+LDA, so it is an effective human ear recognition method.

A Combined Graph and Texture Based Approach for Recognition of Animal Contour Images of MPEG-7 Database

Animal image recognition, classification and retrieval from a database based on shape features are of research interest in image processing. This paper proposes a combined graph and texture based approach for recognition of animal contour images. The methodology uses texture features of the complete graph image obtained from the contour of an object. MPEG-7 database is used for testing. The recognition accuracy of 96% is achieved and is an improvement over the state-of-the-reported results. The work has potential applications in image retrieval from databases.

Local tri-directional patterns: A new texture feature descriptor for image retrieval

Texture is a prominent feature of image and very useful in feature extraction for image retrieval application. Statistical and structural patterns have been proposed for image retrieval and browsing. In the proposed work, a new texture feature descriptor is developed. The proposed method uses local intensity of pixels based on three directions in the neighborhood and named as the local tri-directional pattern (LTriDP). Also, one magnitude pattern is merged for better feature extraction. The proposed method is tested on three databases, in which first two, Brodatz texture image database and MIT VisTex database are texture image databases and third one is the AT&T face database. Further, the effectiveness of the proposed method is proven by comparing it with existing algorithms for image retrieval application.

English

English

Features Conduction Neural Response and Its Application in Content-Based Image Retrieval

A novel image representation is proposed for content-based image retrieval (CBIR). The core idea of the proposed method is to do deep learning for the local features of image and to melt semantic component into the representation through a hierarchical architecture which is built to simulate human visual perception system, and then a new image descriptor of features conduction neural response (FCNR) is constructed. Compared with the classical neural response (NR), FCNR has lower computational complexity and is more suitable for CBIR tasks. The results of experiments on a commonly used image database demonstrate that, compared with those of NR related methods or some other image descriptors that were originally developed for CBIR, the proposed method has wonderful performance on retrieval efficiency and effectiveness.

User-adaptive image retrieval via fusing pointwise and pairwise labels

In many Web image retrieval applications, adapting the retrieval results according to some model of the user is a desired feature as the returned images can be made specifically relevant to a user’s needs. Making retrieval user-adaptive faces several practical challenges, including the ambiguity of user query, the lack of user-adaptive training data, and lack of proper mechanisms for supporting adaptive learning. To address some of these challenges, we propose a hybrid learning strategy that fuses knowledge from both pointwise and pairwise training data into one framework for attribute-based, user-adaptive image retrieval. An online learning algorithm is developed for updating the ranking performance based on user feedback. The framework is also derived into a kernel form allowing easy application of kernel techniques. We use both synthetic and real-world datasets to evaluate the performance of the proposed algorithm. Comparison with other state-of-the-art approaches suggests that our method achieves obvious performance gains over ranking and zero-shot learning. Further, our online learning algorithm was found to be able to deliver much better performance than batch learning, given the same elapsed running time.

Overview of the MPEG-CDVS Standard.

Compact descriptors for visual search (CDVS) is a recently completed standard from the ISO/IEC moving pictures experts group (MPEG). The primary goal of this standard is to provide a standardized bitstream syntax to enable interoperability in the context of image retrieval applications. Over the course of the standardization process, remarkable improvements were achieved in reducing the size of image feature data and in reducing the computation and memory footprint in the feature extraction process. This paper provides an overview of the technical features of the MPEG-CDVS standard and summarizes its evolution.

Local quantized extrema patterns for content-based natural and texture image retrieval

AbstractThis paper proposes a novel feature descriptor, named local quantized extrema patterns (LQEP) for content based image retrieval. The standard local quantized patterns (LQP) collect the directional relationship between the center pixel and its surrounding neighbors and the directional local extrema patterns (DLEP) collect the directional information based on local extrema in 0°, 45°, 90°, and 135° directions for a given center pixel in an image. In this paper, the concepts of LQP and DLEP are integrated to propose the LQEP for image retrieval application. First, the directional quantized information is collected from the given image. Then, the directional extrema is collected from the quantized information. Finally, the RGB color histogram is integrated with the LQEP for a feature vector generation. The performance of the proposed method is tested by conducting three experiments on Coel-1K, Corel-5K and MIT VisTex databases for natural and texture image retrieval. The performance of the proposed method is evaluated in terms of precision, recall, average retrieval precision and average retrieval rate on benchmark databases. The results after investigation show a considerable improvements in terms of their evaluation measures as compared to the existing methods on respective databases.

Effective Image Retrieval System Using Dot-Diffused Block Truncation Coding Features

This paper presents a new approach to derive the image feature descriptor from the dot-diffused block truncation coding (DDBTC) compressed data stream. The image feature descriptor is simply constructed from two DDBTC representative color quantizers and its corresponding bitmap image. The color histogram feature (CHF) derived from two color quantizers represents the color distribution and image contrast, while the bit pattern feature (BPF) constructed from the bitmap image characterizes the image edges and textural information. The similarity between two images can be easily measured from their CHF and BPF values using a specific distance metric computation. Experimental results demonstrate the superiority of the proposed feature descriptor compared to the former existing schemes in image retrieval task under natural and textural images. The DDBTC method compresses an image efficiently, and at the same time, its corresponding compressed data stream can provide an effective feature descriptor for performing image retrieval and classification. Consequently, the proposed scheme can be considered as an effective candidate for real-time image retrieval applications.

Image Retrieval Using RGB,HSV

This paper proposes a novel feature descriptor called local oppugnant color space extrema patterns (LOCSEP) for image indexing retrieval. The existing directional local extrema pattern (DLEP) extracts the directional edge information based on local extrema in 0o, 45o, 90o, and 135o directions in an image. The proposed method integrates the concepts of color and texture features. First, the color image is converted into RGB (red, green and blue) and HSV (hue, saturation and value) color spaces. Then oppugnant color spaces, RH, GH, BH are used for the extract of oppugnant DLEP features (LOCSEP). The performance of the proposed method is tested by conducting two experiments on benchmark databases viz. Corel-1K and MIT VisTex databases. The performance of the proposed method is compared with the state-of-the-art methods for image retrieval and face recognition applications in terms of average retrieval precision (ARP) and average retrieval rate (ARR). The results after being investigated show a significant improvement in terms of their evaluation measures as compared to state-of-the-art methods on respective databases.

A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval.

Feature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse coding for image retrieval. In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly. Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval. Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.

Fuzzy Shape of Objects in Images with Similarity Measure for Image Retrieval Applications

The object present in an image is an important content and can be used in CBIR applications. Identifying and representing the shape of the object is highly complex because there are uncertainties in the boundary of the object of interest. In this paper, the authors have proposed Fuzzy-Object-Shape to capture the shape of the object of interest along with the degree of impreciseness in the boundary information. The Fuzzy-Object-Shape information is extracted from each object in an image. This information provides a measure of closeness of the object of interest with well-known shapes. For each object, the fuzzy membership values are calculated and considered as feature vector. A similarity measure is proposed for measuring the degree of closeness of objects present in both query and database images. The performance of the proposed approach is compared with some of the recently proposed similar approaches. Benchmark dataset and uncontrolled dataset are used for the experiments and found that the performance of the proposed approach is encouraging.

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.