Showing papers on "Multimedia database published in 2014"

Efficient Filter Approximation Using the Earth Mover's Distance in Very Large Multimedia Databases with Feature Signatures

Abstract: The Earth Mover's Distance, proposed in computer vision as a distance-based similarity model reflecting the human perceptual similarity, has been widely utilized in numerous domains for similarity search applicable on both feature histograms and signatures. While efficiency improvement methods towards the Earth Mover's Distance were frequently investigated on feature histograms, not much work is known to study this similarity model on feature signatures denoting object-specific feature representations. Given a very large multimedia database of features signatures, how can k-nearest-neighbor queries be processed efficiently by using the Earth Mover's Distance? In this paper, we propose an efficient filter approximation technique to lower bound the Earth Mover's Distance on feature signatures by restricting the number of earth flows locally. Extensive experiments on real world data indicate the high efficiency of the proposal, attaining order-of-magnitude query processing time cost reduction for high dimensional feature signatures.

Multimedia recommendation method and corresponding server and client side

Abstract: The invention provides a multimedia recommendation method which is applied to a server to bring convenience to the server for recommending multimedia to a client side. The server is provided with a multimedia database which is used for storing multimedia and geographic information related to the multimedia. The multimedia recommendation method comprises the steps that the server receives geographical location information sent by the client side; the server searches the multimedia database for the multimedia with the geographical location information matched with the geographical location information sent by the client side according to the geographical location information sent by the client side; the server sends the found multimedia with the geographical location information matched with the geographical location information sent by the client side to the client side, so that a client side user can play the multimedia at the geographic position of the user. The invention further provides the server and client side corresponding to the multimedia recommendation method.

Multimedia Question Answering System and Method

Abstract: An embodiment provides a multimedia question answering system and method. The system includes a question input unit, configured to receive a text question input by a user, a parsing unit, configured to acquire feature information and a semantic category of the text question, a category determining unit, configured to determine whether the semantic category exists in a preset multimedia database. The system further includes a similarity acquiring unit, configured to, when a determination result is yes, match the feature information with all text features corresponding to the semantic category in the database, so as to acquire a similarity between each text feature and the feature information. The system also includes a multimedia answer output unit, configured to acquire a corresponding text feature when the similarity is greater than a preset threshold, and output multimedia answer information corresponding to the text feature and prestored in the multimedia database.

Lungsounds@UA Interface and Multimedia Database

Abstract: The development of graphical user interfaces GUIs has been an emergent demand in the area of healthcare technologies. Specifically for respiratory healthcare there is a lack of tools to produce a complete multimedia database, where respiratory sounds and other clinical data are available in a single repository. This is essential for a complete patients' assessment and management in research/clinical settings. Therefore, this study aimed to develop a usable interface to collect and organise respiratory-related data in a single multimedia database. A GUI, named LungSounds@UA, composed by a multilayer of windows, was developed. The usability of the user-centred interface was assessed in a pilot study and in an evaluation session. The users testified the utility of the application and its great potential for research/clinical settings. However, some drawbacks were identified, such as a certain difficulty to intuitively navigate in the great amount of the available information, which will inform future developments.

Multimedia interactive learning system and method for paper textbooks

Abstract: The invention relates to the field of teaching and learning, provides a set of convenient and interactive multimedia solution and system for paper textbooks, and particularly relates to a multimedia interactive learning system and method for the paper textbooks. The system comprises an image information acquiring unit, an image processing module, an image and multimedia database, an image recognition module and a multimedia control and interaction module. After students, teachers and other users use the system on an intelligent terminal, corresponding multimedia materials can be directly acquired according to read paper textbook content, and gesture and voice operation can be carried out on some three-dimensional images or animation therein. According to the scheme, the efficiency of the textbook users for learning the textbooks is improved, and the learning interests of the users are increased. Meanwhile, a solution of paper textbook electronic reformation for textbook publishing houses is provided, and the solution is beneficial to being comprehensively popularized in the market.

DHSR: A Novel Semantic Retrieval Approach for Ubiquitous Multimedia

Abstract: Semantic features are critical intelligence information for mobile ubiquitous multimedia, how to manage and retrieve the semantic information has been an important issue. In this paper, a novel semantic retrieval approach named Data Hiding based Semantic Retrieval (DHSR) for ubiquitous multimedia is proposed. This approach consists of the following features: (1) Every multimedia document has to be semantically annotated by several users before saved into multimedia database. (2) Semantic information described by object ontology will be hidden in the multimedia document data. (3) Semantic information will not be lost even if the multimedia document is copied, cut or leave the database. Our work provides a search engine with convenient user interfaces. The experimental results show that DHSR can search the multimedia documents reflecting users' query intent more effectively compared with some traditional approaches.

Inferring Home Location from User's Photo Collections based on Visual Content and Mobility Patterns

Abstract: Precise home location detection has been actively studied in the past few years. It is indispensable in the researching fields such as personalized marketing and disease propagation. Since the last few decades, the rapid growth of geotagged multimedia database from online social networks provides a valuable opportunity to predict people's home location from temporal, spatial and visual cues. Among the massive amount of social media data, one important type of data is the geotagged web images from image-sharing websites. In this paper, we developed a reliable photo classifier based on the Convolutional Neutral Networks to classify photos as either home or non-home. We then proposed a novel approach to home location prediction by fusing together the visual content of web images and the spatiotemporal features of people's mobility pattern. Using a linear SVM classifier, we showed that the robust fusion of visual and temporal feature achieves significant accuracy improvement over each of the features alone.

A survey on content based image retrieval using various operators

Abstract: Retrieval of images plays a major role in different domains including medical diagnosis, biometrics, industry inspection, geographical information satellite systems, web searching and historical research and so on. When size of the database increases continuously, the applications involving images face new challenges and crucial problems such as storage management, indexing, knowledge management and retrieval presentation. We need an efficient retrieval mechanism to retrieve images from the multimedia database. CBIR — Content-based image retrieval is an image retrieval technique used to retrieve images efficiently by using low level image features texture, shape and color. In CBIR system, an image query is characterised by primitive, logical features and abstract attributes. Queries with primitive features are directly derivable from the images but logical and abstract features require logical inference and objects semantic reasoning. This survey paper focuses on different features descriptors for image retrieval and analysis of various retrieval operators like LBP-Local Binary patterns, LTP-Local Ternary patterns, LDP-Local Derivative Patterns and LTrP-Local Tetra patterns using high level features to improve the performance and accuracy in CBIR system.

On Efficient Query Processing with the Earth Mover's Distance

Abstract: The Earth Mover's Distance which is proposed in computer vision as a distance-based similarity model has been widely used and investigated in various domains for similarity search. Although there exists the opportunity to apply this well-known similarity model reflecting the human perceptual similarity both on feature histograms and signatures as feature representation techniques, efficiency improvement approaches towards the Earth Mover's Distance were often investigated on feature histograms. Thus, it can be brought into question how k-nearest-neighbor queries can be processed efficiently by using this distance-based similarity model in a database of feature signatures, such as in a multimedia database. In this paper, the work in progress is presented regarding the new lower bound Independent Minimization for Signatures (IM-Sig) to the Earth Mover's Distance on feature signatures as an efficient filter approximation approach. Furthermore, the problems and challenging issues regarding efficient query processing on feature signatures are presented. The ongoing experimental evaluation on real data points out the high efficiency of the proposed lower bound, contributing to a promising start in the research field of efficient query processing with the Earth Mover's Distance.

An exhaustive study on data mining techniques in mining of Multimedia database

Abstract: Multimedia database can be define as a collection of storage and retrieval systems, in which large amount of media objects are created, modified, searched and retrieved, where as Multimedia is the combination of text, image, graphics, animations, audio and video. The extension of database application to handle multimedia objects requires synchronization of multiple media data streams. Multimedia data mining refers to the extraction of implicit knowledge, data relationships, or other patterns which are not stored in multimedia files explicitly. The system's overall performance in retrieval can be increase by indexing and classification of multimedia data with efficient information fusion of the different modalities is mandatory. Apart from text retrieval, the current waves in web searching and multimedia data retrieval are the search for and delivery of 3D scenes, images, music and video. The content-based multimedia information retrieval provides new techniques and methods for searching various multimedia databases over the world.

A Database Perspective on Large Scale High-Dimensional Indexing

Abstract: This manuscript gives an overview of several years of research aiming at inventing and evaluating systems and techniques for building efficient content-based retrieval systems managing extremely large databases of multimedia material. It has focused on the management of still images. Most of the work described in this manuscript has been achieved while keeping in mind a database perspective. The most important notion that sheds a particular light on the high-dimensional indexing techniques we have been developing is the \emph{mandatory need for secondary storage}. In essence, secondary storage is needed to cope with failures, which is a requirement for systems running in the real world. Secondary storage is also needed to handle truly large scale datasets.

Fast large-scale multimedia indexing and searching

Abstract: Searching for digital images in large-scale multimedia database is a hard problem due to the rapid increase of the digital assets. Metric Permutation Table is an efficient data structure for large-scale multimedia indexing. This data structure is based on the Permutation-based indexing, that aims to predict the proximity between elements encoding their location with respect to their surrounding. The main constraint of the Metric Permutation Table is the indexing time. With the exponential increase of multimedia data, parallel computation is needed. Opening the GPUs to general purpose computation allows to perform parallel computation on a powerful platform. In this paper, we propose efficient indexing and searching algorithms for the Metric Permutation Table using GPU and multi-core CPU. We study the performance and efficiency of our algorithms on large-scale datasets of millions of images. Experimental results show a decrease of the indexing time while preserving the quality of the results.

Multimedia Database Retrieval: Technology and Applications

Abstract: This book explores multimedia applications that emerged from computer vision and machine learning technologies. These state-of-the-art applications include MPEG-7, interactive multimedia retrieval, multimodal fusion, annotation, and database re-ranking. The application-oriented approach maximizes reader understanding of this complex field. Established researchers explain the latest developments in multimedia database technology and offer a glimpse of future technologies. The authors emphasize the crucial role of innovation, inspiring users to develop new applications in multimedia technologies such as mobile media, large scale image and video databases, news video and film, forensic image databases and gesture databases. With a strong focus on industrial applications along with an overview of research topics, Multimedia Database Retrieval: Technology and Applications is an indispensable guide for computer scientists, engineers and practitioners involved in the development and use of multimedia systems. It also serves as a secondary text or reference for advanced-level students interested in multimedia technologies.

LHI-tree: An efficient disk-based image search application

Abstract: Querying of nearest neighbour (NN) elements on large data collections is an important task for several information or content retrieval tasks. In the paper Local Hash-indexing tree (LHI-tree) is introduced, which is a disk-based index scheme that uses RAM for quick space partition localization and hard disks for the hash indexing. When large collections are considered, such hybrid data structure should be used to implement an effective indexing service. The proposed structure can produce list of approximate nearest neighbours. We compare LHI-tree to FLANN (Fast Library for Approximate Nearest Neighbors), an effective and frequently instanced implementation of ANN search. We show that they produce similar lists of retrieved images (although FLANN works only on RAM). In case of huge multimedia database a disk based indexing and retrieval method has a significant advantage against a vector based system running in RAM data. For the visual content indexing we built an image descriptor composed of four different information representations: edge histogram, entropy histogram, pattern histogram and dominant component colour characteristics. The paper will mention the content based retrieval of Hungarian Wikipedia images.

Method and device for triggering multimedia database scanning of Android equipment

Abstract: The invention discloses a method and a device for triggering multimedia database scanning of Android equipment. The method comprises the following steps: establishing a scanner client class to inherit a multimedia database inquiry service class; establishing a scanning class to instantiate the scanner client class; writing a scanning service background; modifying an adb push command; copying a file to the Android equipment through the adb push command; when the file data of push is finished, acquiring the route of the file; when judging that the route of the file is legal, transmitting the file route parameter to the scanning service background and starting the scanning service background; according to the file route parameter, setting the scanning route through the scanner client class; according to the scanning route, establishing connection between the scanner client class and background multimedia service through the scanning class and triggering multimedia database scanning. According to the method and the device, the resource-critical problem of a system caused by full scanning when data is acquired every time can be avoided.

Wally: A Scalable Distributed Automated Video Surveillance System with Rich Search Functionalities

Abstract: In this demo, we present Wally, a scalable distributed automated video surveillance system. Wally provides users with rich search functionalities for surveillance, such as instant and historical search based on face or clothing feature by specifying multiple conditions. Unlike most existing systems that focus on video analysis but do not well consider system scalability and search functionality, Wally takes into account both of them, and is developed as a commercial level system for realistic surveillance. To achieve this, we 1) employ relational database, in-memory cache, key-value store, and indexing techniques to ensure the system scalability when it meets Big Data, and 2) develop user-friendly interfaces to enable users to search key frames by rich functionalities. It is estimated by our extensive evaluations that Wally can complete a search task within 50 minutes from the videos captured one day by 1000 real-time cameras, while human monitoring needs 1000x24 man-hours.

Multimedia database scanning method and device

Abstract: The invention aims to improve efficiency of multimedia database scanning, and avoid the situation that a path of a meaningless multimedia file is added to a multimedia database A multimedia database scanning method is characterized by including the steps that the obtaining step: information of scanning-free paths is obtained through a server; the scanning step: in the scanning process, the paths which do not need scanning are skipped according to the information of the scanning-free paths In the prior art, software related to multimedia file storage can set multimedia file storage paths, the information of the scanning-free paths is generated according to the multimedia file storage paths and sent to a multimedia terminal through the server, in this way, in the scanning process of the terminal, on one hand, the unnecessary scan paths can be skipped, the efficiency of multimedia database scanning can be improved, and on the other hand, the situation that the path of the meaningless multimedia file is added to the multimedia database can be avoided Through building a functional module architecture, computer program instructions control a computer system to complete the multimedia database scanning, and the computer program instructions are stored in a readable storage medium of a computer

A Novel Approach of Color-Texture based CBIR Using Fuzzy Logic

Abstract: Image retrieval is an emerging research area for multimedia database. It is the basic requirement task in the present scenario. In this paper we propose a novel CBIR approach using Fuzzy clustering. The proposed method firstly clusters the images based on RGB components, using Fuzzy clustering algorithm, secondly the image retrieval is performed based on texture element in the clustered database. The performance of the system is evaluated on the most common evaluation method namely Precision and Recall method. The proposed method achieves higher efficiency than the texture based retrieval techniques.

Towards a Unified Exploitation of Electronic Dialectal Corpora: Problems and Perspectives

Abstract: In this paper, we deal with the problem of storing and retrieving dialectal data in a unified framework. In particular, we discuss issues concerning the design and implementation of a multimedia database which will contain written and oral data from three Greek dialects in Asia Minor. At first, we describe the overall architecture of a system aiming at providing the user with the possibility to store audio recordings, text transcripts, and other annotations. Then we discuss the possibilities and limitations of a retrieval module aiming at combining different linguistic levels for a unified exploitation of oral and written corpora.

Analysis of Audio Descriptor Contribution in Singer Identification Process

Abstract: An audio descriptor describes the information of an audio signal in a compact and precise representation. There are various standards available to extract the audio information in various ways to be used for particular applications such as, speaker recognition, musical instrument identification, singer identification, multimedia database indexing, genre detection and so on. There are various audio descriptor extraction and manipulation tools available to be used with MatLab. Audio descriptor plays vital role for the applications such as singer identification. The process becomes complex with respect to monophonic, homophonic and polyphonic type of music. In North Indian classical music, (homophonic version), an accompanying instrument called Tanpura is continuously played during the vocal performance of the singer. In such cases, merely standard procedures of speaker recognition or singer identification from polyphonic music are not sufficient. The contribution of different audio descriptors changes from one type of input to the other. In this paper, we have established a singer identification system using MIRtoolbox for Timbral feature extraction and K- Means clustering for classification. The purpose of this paper is two folded. A) to design and implement a singer identification system and B) to find the contribution of the audio descriptors from each level to the final accuracy of singer identification result. With the method proposed, an accuracy of 96.6667% is achieved using K-means clustering, for the combination of Zero crossing Rate, Roll off, Brightness and Irregularity audio descriptors, for 3 singers for a studio recorded audio input from North Indian Classical Music recordings with the accompanying background instrument 'Tanpura'.

Algorithms for Recollection of Search Terms Based on the Wikipedia Category Structure

Abstract: The common user interface for a search engine consists of a text field where the user can enter queries consisting of one or more keywords. Keyword query based search engines work well when the users have a clear vision what they are looking for and are capable of articulating their query using the same terms as indexed. For our multimedia database containing 202,868 items with text descriptions, we supplement such a search engine with a category-based interface whose category structure is tailored to the content of the database. This facilitates browsing and offers the users the possibility to look for named entities, even if they forgot their names. We demonstrate that this approach allows users who fail to recollect the name of named entities to retrieve data with little effort. In all our experiments, it takes 1 query on a category and on average 2.49 clicks, compared to 5.68 queries on the database's traditional text search engine for a 68.3% success probability or 6.01 queries when the user also turns to Google, for a 97.1% success probability.

Multimedia Database Techniques for Medical Diagnosis Processes Support

Abstract: Technological capabilities in the field of medical imaging contribute to the increasing use of image analysis in diagnostic medical systems. Medical imaging is one of the key sources of information for health professionals. It is largely due to the fact that the accuracy of the conclusions drawn by the physicians from this form of presentation of the data is very large in comparison with the numerical data. The characteristics of multimedia content requires suitable database solutions which are issues of multimedia databases techniques.

A Cross-Media Music Retrieval System by Converting Color Changes into Tonal Changes

Abstract: We propose a cross-media music retrieval system that provides its users with a toolkit for formulating their own query by describing their emotional requirements for changes in mood of music as a sequence of images. To interpret the query, the system uses a metric space to convert the color changes in images into continuous tonal changes in music, and vice versa. The system provides delta functions for music and images to compute the changes as distance values in the metric space. Our system calculates the sentiment-oriented relevance score of the query and music by comparing their computed distance values. The advantage of the system is that it provides a bridge between heterogeneous image and music criteria by converting the visual impressions of images into a time-oriented invisible impression of music. This bridging operation is the foundation of our visual query construction method. This method allows users to search for music by subtly manipulating the form of a query in a trial-and-error manner by detecting the moods of music as color changes in images. This method is suitable for searching for unknown music that satisfies the preferences of users in web-based music resources that store many types of music, but without any publishing information related to the music.

Application of Multimedia Technology in Database and IT Service Management

Abstract: Multimedia is a blend of two or more media such as text, sound, graphics, animation and video, to effectually converse ideas to the users and this could be in linear or non-linear form [7]. The application of multimedia technology to database and IT service management has improved enormously in recent times. Multimedia system is a distinctive application which is of time-critical in its use in the various areas of computing. The spatial, secular, storage, processing, recovery, grouping and management requirements of data vary momentously from those that are applied for traditional data [2]. Therefore, the purpose of multimedia technology in database management system and in proper management of IT services to clients is to permit for an efficient way of performing these tasks in all its varied forms in an efficient form. A multimedia database management system affords an efficient storage and manoeuvring of multimedia technologies in all its diverse types. Database technology has offered means to store and recover high volumes of data in the various business domains [8]. Although, database systems have always been planned for the administration of alphanumeric data such as names and numbers, the basic nature of multimedia data are also considered and thus highlights the need for multimedia enhanced database management systems, and present the various obligations and issues required for developing such systems. The various areas of applications consist of, but not limited to digital libraries (text documents, images, sound, video etc), art and entertainment, content management, journalism etc [1]. For technology purposes, multimedia is a computer-based systems that apply associative relationships to allow the users of such systems to navigate and retrieve various information that are stored in a location which could be a combination of text, sounds, graphics, video, and other media formats [12].

Map-Based Querying for Multimedia Database

Abstract: : This report describes a quick approach to query for existing assets in a custom multimedia database based on an area of interest. It also describes the augmentation of an Android Tactical Assault Kit (ATAK) to allow for selection and specification of an area of interest.

Retrieval of Data from Very Large Databases Using Apriori Algorithm

Abstract: Now-a-days most of the Very Large Databases like Medical Databases, Multimedia Database are consuming Petabytes of memory. For extracting required data from this enormous amount of memory so many retrieval techniques were already developed. But all these techniques are time consuming. We can also use indexing supported by all the commercial databases. When we create an index internally it uses B-Tree data structure which is used for efficient retrieval of data. But, Oracle10g is supporting R-Tree indexes also which are more efficient than B-Tree indexes. On Very Large Databases it is not sufficient to create a single index because these Databases consist of large number of fields. Moreover, it is not necessary to create index on each and every field and it is also not possible because it requires large memory area. In very large databases also most of the times the user concentrates on few fields only. So, in our proposed system, the solution is to create some suggested indexes. And as and when the user’s query pattern changes the suitable index from the suggested index set is dynamically loaded into the main memory from the local storage. Our proposed technique continuously monitors the query patterns and it creates the suggested indexes using Apriori algorithm and this suggested index set is updated periodically based on the query pattern changes.

Performance Analysis of Content Based Video Retrieval System Using Clustering

Abstract: the multimedia storage grows and the cost for storing multimedia data is cheaper. So there is huge number of videos available in the video repositories. It is difficult to retrieve the relevant videos from large video repository as per user interest as users shift from text based retrieval systems to content based retrieval systems. Video retrieval is very important in multimedia database management. This paper offers an overview of the landscape of general strategies in visual content-based video retrieval, focusing on methods for video structure analysis, including shot boundary detection, key frame extraction, extraction of features including static key frame features, object feature, video retrieval including similarity measures and the proposed procedure consists of the unique aspect of clustering techniques.

The Application of Multimedia Technology in Medical Information Management

Abstract: The development of science and technology has entered the information age. Information rapidly grow which need be accessed by the advanced technology, the development of computer multimedia transmission provides the most intuitive the most powerful support for today's information processing. Combining health care information management and computer multimedia technology, multimedia information system design is introduced in this paper, emphatically from the technical methods to discuss the requirements of the system hardware and software environment, and put forward some design methods from the universal database to tackle multimedia database and its data model. In system design, according to the characteristics of multimedia database, much data, unstructured information, information not fixed, sensitive characteristics of voice, video, and the timeline, the corresponding solutions are put forward.