A distributed Content-Based Video Retrieval system for large datasets

Due to the availability of large number of digital images, development of an efficient content-based indexing and retrieval method is required. Also, the emergence of smartphones and modern PDAs has further substantiated the need of such systems. This paper proposes a combination of Local Ternary Pattern (LTP) and moments for Content-Based Image Retrieval. Image is divided into blocks of equal size and LTP codes of each block are computed. Geometric moments of LTP codes of each block are computed followed by computation of distance between moments of LTP codes of query and database images. Then, the threshold using distance values is applied to retrieve images similar to the query image. Performance of the proposed method is compared with other state-of-the-art methods on the basis of results obtained on Corel-1,000 database. The comparison shows that the proposed method gives better results in terms of precision and recall as compared to other state-of-the-art image retrieval methods.

In the field of computer vision and image processing CBIR (Content based image retrieval) system become an active research area. The CBIR technique involves feature extraction based on image features (like color, shape and texture) and defining rules for comparing image. A classifier is also used by authors for image classification. For this purpose an image database taken from James Z. Wang research group website is used by many authors. Due to enormous increase in the size of database traditional methods of image retrieval by using keywords does not provide accurate result. Thus the concept of CBIR system is emerged. In last couple of years many method of feature extraction is developed but since now researcher are not able to develop a system which has gained high accuracy of human visual perception in distinguishing pictures. Therefore earlier researchers have concentrated to increase the retrieval accuracy of CBIR system by using different combination of features. The objective of this paper is to present review on a CBIR technique which combined four kinds of features set including every kind of feature for developing feature vector. Color based features (histogram), statistical features (mean, median and standard deviation), spatial features (Gabor feature and wavelet features) and texture features (GLCM) is used for forming feature vector. A SVM classifier is used with CBIR system to increase retrieval accuracy. SVM (support vector machine) is a machine learning classifier which provides good classification accuracy. Keywords: CBIR, SVM, NN, GLCM, HSV Color space, Euclidean distance matrix.

In this paper, we propose a user-based video-indexing method, that automatically generates thumbnails of the most important scenes of an online video stream, by analyzing users’ interactions with a web video player. As a test bench to verify our idea we have extended the YouTube video player into the VideoSkip system. In addition, VideoSkip uses a web-database (Google Application Engine) to keep a record of some important parameters, such as the timing of basic user actions (play, pause, skip). Moreover, we implemented an algorithm that selects representative thumbnails. Finally, we populated the system with data from an experiment with nine users. We found that the VideoSkip system indexes video content by crowdsourcing implicit users interactions, such as pause and thirty seconds skip. Our early findings point toward improvements of the web video player and its thumbnail generation technique. The VideoSkip system could compliment content-based algorithms, in order to achieve efficient video-indexing in difficult videos, such as lectures or sports.KeywordsVideoIndexingThumbnailsPragmaticsSemanticscrowdsourcing

To achieve more efficient video indexing and access, we introduce a video database management framework and strategies for video content structure and events mining. The video shot segmentation and representative frame selection strategy are first utilized to parse the continuous video stream into physical units. Video shot grouping, group merging, and scene clustering schemes are then proposed to organize the video shots into a hierarchical structure using clustered scenes, scenes, groups, and shots, in increasing granularity from top to bottom. Then, audio and video processing techniques are integrated to mine event information, such as dialog, presentation and clinical operation, from the detected scenes. Finally, the acquired video content structure and events are integrated to construct a scalable video skimming tool which can be used to visualize the video content hierarchy and event information for efficient access. Experimental results are also presented to evaluate the performance of the proposed framework and algorithms.

This paper presents novel approaches for combining re-ranking and rank aggregation methods aiming at improving the effectiveness of Content-Based Image Retrieval (CBIR) systems. Given a query image as input, CBIR systems retrieve the most similar images in a collection by taking into account image visual properties. In this scenario, accurately ranking collection images is of great relevance. Aiming at improving the effectiveness of CBIR systems, re-ranking and rank aggregation algorithms have been proposed. However, different re-ranking and rank aggregation approaches, applied to different image descriptors, may produce different and complementary image rankings. In this paper, we present four novel approaches for combining these rankings aiming at obtaining more effective results. Several experiments were conducted involving shape, color, and texture descriptors. The proposed approaches are also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate that our approaches can improve significantly the effectiveness of image retrieval systems.

This paper presents a corpus of deep features extracted from the YFCC100M images considering the fc6 hidden layer activation of the HybridNet deep convolutional neural network. For a set of random selected queries we made available k-NN results obtained sequentially scanning the entire set features comparing both using the Euclidean and Hamming Distance on a binarized version of the features. This set of results is ground truth for evaluating Content-Based Image Retrieval (CBIR) systems that use approximate similarity search methods for efficient and scalable indexing. Moreover, we present experimental results obtained indexing this corpus with two distinct approaches: the Metric Inverted File and the Lucene Quantization. These two CBIR systems are public available online allowing real-time search using both internal and external queries.

Systems for retrieving and managing content-based medical images are becoming more important, especially as medical imaging technology advances and the medical image database grows. In addition, these systems can also use medical images to better grasp and gain a deeper understanding of the causes and treatments of different diseases, not just for diagnostic purposes. For achieving all these purposes, there is a critical need for an efficient and accurate content-based medical image retrieval (CBMIR) method. This paper proposes an efficient method (RbQE) for the retrieval of computed tomography (CT) and magnetic resonance (MR) images. RbQE is based on expanding the features of querying and exploiting the pre-trained learning models AlexNet and VGG-19 to extract compact, deep, and high-level features from medical images. There are two searching procedures in RbQE: a rapid search and a final search. In the rapid search, the original query is expanded by retrieving the top-ranked images from each class and is used to reformulate the query by calculating the mean values for deep features of the top-ranked images, resulting in a new query for each class. In the final search, the new query that is most similar to the original query will be used for retrieval from the database. The performance of the proposed method has been compared to state-of-the-art methods on four publicly available standard databases, namely, TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI. Experimental results show that the proposed method exceeds the compared methods by 0.84%, 4.86%, 1.24%, and 14.34% in average retrieval precision (ARP) for the TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI databases, respectively.

The amount of the internet video has been growing rapidly in recent years. Efficient video indexing and retrieval, therefore, is becoming an important research and system-design issue. Reliably extracting metadata from video as indexes is one major step toward efficient video management. There are numerous video types, and everyone can define new video types of his own. We believe an open video analysis framework should help when one needs to automatically process various types of videos. More, the nature of video can be so different that we may end up having a dedicated video analysis module for each video type. It is infeasible to design a system to automatically process every type of video. In the paper, we propose a scene-based video analytic studio that comes with (1) an open video analysis framework where the video analysis modules are developed and deployed as plug-ins, (2) an authoring tool where videos can be manually tagged, and (3) an HTML5-based video player the play backs videos using the metadata we generate. In addition, it provides a runtime environment with standard libraries and proprietary rule-based automaton modules to facilitate the plug-in development. At the end, we will show its application to click able (shoppable) videos, which we plan to apply to our e-learning projects.

A novel efficient method for content-based image retrieval (CBIR) is developed in this paper using both texture and color features. Our motivation is to represent and characterize an input image by a set of local descriptors extracted from characteristic points (i.e., keypoints) within the image. Then, dissimilarity measure between images is calculated based on the geometric distance between the topological feature spaces (i.e., manifolds) formed by the sets of local descriptors generated from each image of the database. In this work, we propose to extract and use the local extrema pixels as our feature points. Then, the so-called local extrema-based descriptor (LED) is generated for each keypoint by integrating all color, spatial as well as gradient information captured by its nearest local extrema. Hence, each image is encoded by an LED feature point cloud and Riemannian distances between these point clouds enable us to tackle CBIR. Experiments performed on several color texture databases including Vistex, STex, color Brodazt, USPtex and Outex TC-00013 using the proposed approach provide very efficient and competitive results compared to the state-of-the-art methods.

Relevance Feedback (RF) is a powerful technique in Content-Based Image Retrieval (CBIR) system and has become a very active research topic in the past few years. At the early stage of CBIR, research primarily focused on exploring various feature representation and ignored the subjectivity of human perception. There exists a gap between high-level concepts and low-level features. As an effective solution, the RF technique has been used on many CBIR systems to improve the retrieval precision. In this paper, a combined automatic weighting and relevance feedback method is proposed to improve the retrieval performance of CBIR. An approach using genetic algorithm for computing the initial weight of feature vector was introduced. By moving the query vector and updating the weighting factors simultaneously, the convergence speed of the relevance feedback retrieval is accelerated. Experimental results show that this method achieves high accuracy and effectiveness in CBIR.

Over the past two decades, we have seen the rapid adoption of distributed data management systems in industry, with many early adopters leading the way. Preferences are shifting from smaller, local, centralized, monolithic systems towards larger, distributed, concurrent, global systems that are scalable, fault-tolerant, and can provide diverse functionalities over a wider range of data types. Organizations are building next-generation data services using many innovations in distributed systems and information management technology: peer-to-peer and web services architectures, industrial-strength clustering and fault-tolerance technologies, large scale reliable storage systems, and efficient indexing and retrieval methods for unstructured data (Armbrust et al., 2010; Bass et al., 2012; Gollapudi, 2021). At the same time, research efforts in data systems are focusing increasingly on the development of distributed, scalable, and fault-tolerant techniques that can support services such as web-search, information-sensors, click-stream analysis, peer-to-peer storage and publish/subscribe services. There have been interesting ideas, especially in the areas of scalable data access and retrieval services, reliable storage, and high-performance data dissemination services. Today, large amounts of data are being generated and collected by organizations. Simultaneously, businesses are realizing that enormous improvement in profitability can be achieved by employing new tools and approaches for data analysis: mining for knowledge; learning predictive models; performing trend analysis over historical data; performing on-line, real-time analysis and filtering of current data. Many of these organizations are beginning to analyze transaction data from their business processes in conjunction with traditional data-analysis techniques. By employing technology to analyze and filter the data, businesses can make intelligent decisions about managing customer relationships. With increasingly complete data repositories, businesses are increasingly looking to drive customer relationships by collecting explicit data from customers and analyzing their behavior. A strong tool-set for large scale data analysis will allow organizations to automatically enhance their intelligence infrastructure. As these organizations have entered into the hype cycle for such analysis tools, they expect an understanding ecosystem (Krishnan, 2013; Kleppmann, 2017).

Advances in data storage and image acquisition technologies have enabled the creation of large image datasets. Thus, it is necessary to develop appropriate information systems to efficiently manage these datasets. Image classification and retrieval is one of the most important services that must be supported by such systems. The most common approach used is content-based image retrieval (CBIR) systems. This paper presents a new application of rough sets to feature reduction, classification, and retrieval for image databases in the framework of content-based image retrieval systems. The suggested approach combines image texture features with color features to form a powerful discriminating feature vector for each image. Texture features are extracted, represented, and normalized in an attribute vector, followed by a generation of rough set dependency rules from the real value attribute vector. The rough set reduction technique is applied to find all reducts with the minimal subset of attributes associated with a class label for classification

Content-Based Image Retrieval (CBIR) allows to automatically extracting target images according to objective visual contents of the image itself. Representation of visual features and similarity match are important issues in CBIR. Color, texture and shape information have been the primitive image descriptors in content-based image retrieval systems. This paper presents a fast and efficient image indexing and search system based on color and texture features. The color features are represented by combines 2-D histogram and statistical moments and texture features are represented by combines the direction measure and a gray level co-occurrence matrix (GLCM). The detailed experimental analysis is carried out using precision and recall ondataset Wang. The time analysis is also performed to compare processing speeds of the proposed method with the existing similar best. The experimental results demonstrated that proposed method achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved. The performance is measured in terms of recall and precision; also the obtained performances are compared with several state-of-the-art algorithms and showed that our algorithm is simple, fast, and efficient in terms of results and memory. Keywords: Co-occurrence Matrix, Direction Measure, 2-D Histogram, Statistical Moments, CBIR, GLCM

In this paper, a content-based video retrieval (CBVR) system called Bounded Coordinate of Motion Histogram version 2 (BCMH v2) was processed on a distributed computing platform by using Apache Hadoop framework and a real-time distributed storage system using HBase. In fact, the amount of multimedia data is growing exponentially. Most of this data is available in image and video models. Analyzing huge data involves complex algorithms, which leads to challenges in optimizing processing time and data storage capacity. Many content-based video retrieval systems are suitable for processing large video dataset, but they are limited by the computational time and/or storage on a single machine. Thus, this paper presents the effectiveness of the proposed method with the distributed computing platform and its evaluation on the HOLLYWOOD2 video dataset. The experimental results demonstrate the good performances of the proposed approach.

Visual search for objects of interest in complex environment is an important (and still challenging) problem in mobile robotics. In particular, the usage of content-based visual information retrieval (CBVIR) methods, which are a natural choice for such tasks, is often constrained by the real-time requirements, and the mobility of searching agents is sometimes not sufficiently exploited in the search model. In this paper, a CBVIR-based scheme is proposed, which takes into account motion of the searching agents to achieve a low-cost and highspeed detection of objects of interest in cluttered scenes, with good overall performances. We combine standard CBVIR tools, i.e. MSER detector and SIFT descriptor (quantized into sufficiently large vocabularies) assuming additionally that objects become objects of interest only when approached closely enough by the mobile agent, i.e. when seen at an adequately large scale. Thus, an object of interest is considered detected only if a sufficient number of keypoints from the current video-frame are matched (including the corresponding matches of scales) to the keypoints from the database images of the object. Preliminary experiments on a limited-size dataset confirm performances of the scheme, although in the classical task of video-frame retrieval the scheme cannot compete with more sophisticated CBVIR algorithms. The scheme can prospectively become more flexible if combined with a range-finding device so that the approximate distances to the scene components within the currently inspected part of the image can be used to proportionally modify the scale correspondences.