Página 1 dos resultados de 253 itens digitais encontrados em 0.004 segundos

Indexação multimídia escalável e busca por similaridade em alta dimensionalidade; Scalable multimedia indexing and similarity search in high dimensionality

Fernando Cesar Akune
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 01/08/2011 Português
Relevância na Pesquisa
57.96992%
A disseminação de grandes coleções de arquivos de imagens, músicas e vídeos tem aumentado a demanda por métodos de indexação e sistemas de recuperação de informações multimídia. No caso de imagens, os sistemas de busca mais promissores são os sistemas baseados no conteúdo, que ao invés de usarem descrições textuais, utilizam vetores de características, que são representações de propriedades visuais, como cor, textura e forma. O emparelhamento dos vetores de características da imagem de consulta e das imagens de uma base de dados é implementado através da busca por similaridade. A sua forma mais comum é a busca pelos k vizinhos mais próximos, ou seja, encontrar os k vetores mais próximos ao vetor da consulta. Em grandes bases de imagens, um índice é indispensável para acelerar essas consultas. O problema é que os vetores de características podem ter muitas dimensões, o que afeta gravemente o desempenho dos métodos de indexação. Acima de 10 dimensões, geralmente é preciso recorrer aos métodos aproximados, sacrificando a eficácia em troca da rapidez. Dentre as diversas soluções propostas, existe uma abordagem baseada em curvas fractais chamadas curvas de preenchimento do espaço. Essas curvas permitem mapear pontos de um espaço multidimensional em uma única dimensão...

Aplicación del modelo Bag-of-Words al reconocimiento de imágenes

Pardo Feijoo, Sara
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: info:eu-repo/semantics/bachelorThesis; info:eu-repo/semantics/masterThesis Formato: application/pdf
Português
Relevância na Pesquisa
69.043296%
Object recognition on images has been more investigated in the recent years. Its principal application is the image retrieval and, therefore, image searchers would find the solution to the query based on whether the image has certain objects in its visual content or not instead of based on the adjacent textual annotations. Content based image retrieval would improve notoriously the quality of searchers. It is neccesary to have models that classify an image based on its low level features. In this project, it is used the ‘Bag of words’ model. Multimedia information retrieval entails many fields involved, and has many applications. The objective of this project is the indexing of images of a database based on content. It tries to eliminate the semantic gap finding the descriptors of each imagen, and therefore decide to which class or which semantic concept belongs.--------------------------------------------------------------------; El reconocimiento de objetos en imágenes es un campo cada vez más investigado y que se aplica principalmente a la recuperación de imágenes basada en contenido, es decir, a buscadores de imágenes que encontrarán la solución a una consulta basándose en si la imagen contiene ciertos objetos o no en función de su contenido visual...

Query by Browsing: An Alternative Hypertext Information Retrieval Method

Frisse, Mark E.; Cousins, Steve B.
Fonte: PubMed Publicador: PubMed
Tipo: Artigo de Revista Científica
Publicado em 08/11/1989 Português
Relevância na Pesquisa
57.91024%
In this paper we discuss our efforts to develop programs which enhance the ability to navigate through large medical hypertext systems. Our approach organizes hypertext index terms into a belief network and uses reader feedback to update the degree of belief in the index terms' utility to a query. We begin by describing various possible configurations for indexes to hypertext. We then describe how belief network calculations can be applied to these indexes. After a brief discussion of early results using manuscripts from a medical handbook, we close with an analysis of our approach's applicability to a wider range of hypertext information retrieval problems.

Content Base Image Retrieval Using Phong Shading

Singh, Uday Pratap; Jain, Sanjeev; Ahmed, Gulfishan Firdose
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 24/05/2010 Português
Relevância na Pesquisa
58.462397%
The digital image data is rapidly expanding in quantity and heterogeneity. The traditional information retrieval techniques does not meet the user's demand, so there is need to develop an efficient system for content based image retrieval. Content based image retrieval means retrieval of images from database on the basis of visual features of image like as color, texture etc. In our proposed method feature are extracted after applying Phong shading on input image. Phong shading, flattering out the dull surfaces of the image The features are extracted using color, texture & edge density methods. Feature extracted values are used to find the similarity between input query image and the data base image. It can be measure by the Euclidean distance formula. The experimental result shows that the proposed approach has a better retrieval results with phong shading.; Comment: IEEE Publication format, International Journal of Computer Science and Information Security, IJCSIS, Vol. 8 No. 1, April 2010, USA. ISSN 1947 5500, http://sites.google.com/site/ijcsis/

Integrating users' needs into multimedia information retrieval system

Maghrebi, Hanène; David, Amos
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 21/08/2007 Português
Relevância na Pesquisa
89.4085%
The exponential growth of multimedia information and the development of various communication media generated new problems at various levels including the rate of flow of information, problems of storage and management. The difficulty which arises is no longer the existence of information but rather the access to this information. When designing multimedia information retrieval system, it is appropriate to bear in mind the potential users and their information needs. We assumed that multimedia information representation which takes into account explicitly the users' needs and the cases of use could contribute to the adaptation potentials of the system for the end-users. We believe also that responses of multimedia information system would be more relevant to the users' needs if the types of results to be used from the system were identified before the design and development of the system. We propose the integration of the users' information needs. More precisely integrating usage contexts of resulting information in an information system (during creation and feedback) should enhance more pertinent users' need. The first section of this study is dedicated to traditional multimedia information systems and specifically the approaches of representing multimedia information. Taking into account the dynamism of users...

Dynamic Multimedia Content Retrieval System in Distributed Environment

Sivaraman, R.; Prabakaran, R.; Sujatha, S.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/09/2009 Português
Relevância na Pesquisa
58.487915%
WiCoM enables remote management of web resources. Our application Mobile reporter is aimed at Journalist, who will be able to capture the events in real-time using their mobile phones and update their web server on the latest event. WiCoM has been developed using J2ME technology on the client side and PHP on the server side. The communication between the client and the server is established through GPRS. Mobile reporter will be able to upload, edit and remove both textual as well as multimedia contents in the server.; Comment: 4 Pages IEEE format, International Journal of Computer Science and Information Security, IJCSIS 2009, ISSN 1947 5500, Impact Factor 0.423, http://sites.google.com/site/ijcsis/

A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data

Zheng, Yin; Zhang, Yu-Jin; Larochelle, Hugo
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
58.001665%
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks. Another popular approach to model the multimodal data is through deep neural networks, such as the deep Boltzmann machine (DBM). Recently, a new type of topic model called the Document Neural Autoregressive Distribution Estimator (DocNADE) was proposed and demonstrated state-of-the-art performance for text document modeling. In this work, we show how to successfully apply and extend this model to multimodal data, such as simultaneous image classification and annotation. First, we propose SupDocNADE, a supervised extension of DocNADE, that increases the discriminative power of the learned hidden topic features and show how to employ it to learn a joint representation from image visual words, annotation words and class label information. We test our model on the LabelMe and UIUC-Sports data sets and show that it compares favorably to other topic models. Second, we propose a deep extension of our model and provide an efficient way of training the deep model. Experimental results show that our deep model outperforms its shallow version and reaches state-of-the-art performance on the Multimedia Information Retrieval (MIR) Flickr data set.; Comment: 24 pages...

An Active Learning Based Approach For Effective Video Annotation And Retrieval

Chatterjee, Moitreya; Leuski, Anton
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 27/04/2015 Português
Relevância na Pesquisa
58.405415%
Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [16] require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the training data, allows for a good performance even before the training data is fully annotated. In this work we propose an active learning algorithm, which combines a novel measure of sample uncertainty with a novel clustering-based approach for determining sample density and diversity and integrate it with NormCRM. The clusters are also iteratively refined to ensure both feature and label-level agreement among samples. We show that our approach outperforms multiple baselines both on a recent, open character animation dataset and on the popular TRECVID corpus at both the tasks of annotation and text-based retrieval of videos.; Comment: 5 pages, 3 figures, Compressed version published at ACM ICMR 2015

Ontology-based Secure Retrieval of Semantically Significant Visual Contents

Muhammad, Khan; Mehmood, Irfan; Lee, Mi Young; Ji, Su Mi; Baik, Sung Wook
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 07/10/2015 Português
Relevância na Pesquisa
58.55071%
Image classification is an enthusiastic research field where large amount of image data is classified into various classes based on their visual contents. Researchers have presented various low-level features-based techniques for classifying images into different categories. However, efficient and effective classification and retrieval is still a challenging problem due to complex nature of visual contents. In addition, the traditional information retrieval techniques are vulnerable to security risks, making it easy for attackers to retrieve personal visual contents such as patients records and law enforcement agencies databases. Therefore, we propose a novel ontology-based framework using image steganography for secure image classification and information retrieval. The proposed framework uses domain-specific ontology for mapping the low-level image features to high-level concepts of ontologies which consequently results in efficient classification. Furthermore, the proposed method utilizes image steganography for hiding the image semantics as a secret message inside them, making the information retrieval process secure from third parties. The proposed framework minimizes the computational complexity of traditional techniques, increasing its suitability for secure and real-time visual contents retrieval from personalized image databases. Experimental results confirm the efficiency...

CoPhIR: a Test Collection for Content-Based Image Retrieval

Bolettieri, Paolo; Esuli, Andrea; Falchi, Fabrizio; Lucchese, Claudio; Perego, Raffaele; Piccioli, Tommaso; Rabitti, Fausto
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
58.200854%
The scalability, as well as the effectiveness, of the different Content-based Image Retrieval (CBIR) approaches proposed in literature, is today an important research issue. Given the wealth of images on the Web, CBIR systems must in fact leap towards Web-scale datasets. In this paper, we report on our experience in building a test collection of 100 million images, with the corresponding descriptive features, to be used in experimenting new scalable techniques for similarity searching, and comparing their results. In the context of the SAPIR (Search on Audio-visual content using Peer-to-peer Information Retrieval) European project, we had to experiment our distributed similarity searching technology on a realistic data set. Therefore, since no large-scale collection was available for research purposes, we had to tackle the non-trivial process of image crawling and descriptive feature extraction (we used five MPEG-7 features) using the European EGEE computer GRID. The result of this effort is CoPhIR, the first CBIR test collection of such scale. CoPhIR is now open to the research community for experiments and comparisons, and access to the collection was already granted to more than 50 research groups worldwide.; Comment: 15 pages

Visual Information Retrieval in Endoscopic Video Archives

Roldan-Carlos, Jennifer; Lux, Mathias; Giró-i-Nieto, Xavier; Muñoz, Pia; Anagnostopoulos, Nektarios
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/04/2015 Português
Relevância na Pesquisa
58.469243%
In endoscopic procedures, surgeons work with live video streams from the inside of their subjects. A main source for documentation of procedures are still frames from the video, identified and taken during the surgery. However, with growing demands and technical means, the streams are saved to storage servers and the surgeons need to retrieve parts of the videos on demand. In this submission we present a demo application allowing for video retrieval based on visual features and late fusion, which allows surgeons to re-find shots taken during the procedure.; Comment: Paper accepted at the IEEE/ACM 13th International Workshop on Content-Based Multimedia Indexing (CBMI) in Prague (Czech Republic) between 10 and 12 June 2015

Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture

Sandouk, Ubai; Chen, Ke
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 17/06/2015 Português
Relevância na Pesquisa
57.91024%
One of the biggest challenges in Multimedia information retrieval and understanding is to bridge the semantic gap by properly modeling concept semantics in context. The presence of out of vocabulary (OOV) concepts exacerbates this difficulty. To address the semantic gap issues, we formulate a problem on learning contextualized semantics from descriptive terms and propose a novel Siamese architecture to model the contextualized semantics from descriptive terms. By means of pattern aggregation and probabilistic topic models, our Siamese architecture captures contextualized semantics from the co-occurring descriptive terms via unsupervised learning, which leads to a concept embedding space of the terms in context. Furthermore, the co-occurring OOV concepts can be easily represented in the learnt concept embedding space. The main properties of the concept embedding space are demonstrated via visualization. Using various settings in semantic priming, we have carried out a thorough evaluation by comparing our approach to a number of state-of-the-art methods on six annotation corpora in different domains, i.e., MagTag5K, CAL500 and Million Song Dataset in the music domain as well as Corel5K, LabelMe and SUNDatabase in the image domain. Experimental results on semantic priming suggest that our approach outperforms those state-of-the-art methods considerably in various aspects.

Content Based Multimedia Information Retrieval to Support Digital Libraries

Almunawar, Mohammad Nabil
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 18/07/2012 Português
Relevância na Pesquisa
89.07212%
Content-based multimedia information retrieval is an interesting research area since it allows retrieval based on inherent characteristic of multimedia objects. For example retrieval based on visual characteristics such as colour, shapes or textures of objects in images or retrieval based on spatial relationships among objects in the media (images or video clips). This paper reviews some work done in image and video retrieval and then proposes an integrated model that can handle images and video clips uniformly. Using this model retrieval on images or video clips can be done based on the same framework.; Comment: 15 pages, conference paper

Image Retrieval And Classification Using Local Feature Vectors

Verma, Vikas
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 02/09/2014 Português
Relevância na Pesquisa
58.330015%
Content Based Image Retrieval(CBIR) is one of the important subfield in the field of Information Retrieval. The goal of a CBIR algorithm is to retrieve semantically similar images in response to a query image submitted by the end user. CBIR is a hard problem because of the phenomenon known as $\textit {semantic gap}$. In this thesis, we aim at analyzing the performance of a CBIR system build using local feature vectors and Intermediate Matching Kernel. We also propose a Two-Step Matching process for reducing the response time of the CBIR systems. Further, we develop a Meta-Learning framework for improving the retrieval performance of these systems. Our results show that the Two-Step Matching process significantly reduces response time and the Meta-Learning Framework improves the retrieval performance by more than two fold. We also analyze the performance of various image classification systems that use different image representations constructed from the local feature vectors.

Using Local Optimality Criteria for Efficient Information Retrieval with Redundant Information Filters

Rowe, Neil C.
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 29/09/1998 Português
Relevância na Pesquisa
68.580444%
We consider information retrieval when the data, for instance multimedia, is coputationally expensive to fetch. Our approach uses "information filters" to considerably narrow the universe of possiblities before retrieval. We are especially interested in redundant information filters that save time over more general but more costly filters. Efficient retrieval requires that decision must be made about the necessity, order, and concurrent processing of proposed filters (an "execution plan"). We develop simple polynomial-time local criteria for optimal execution plans, and show that most forms of concurrency are suboptimal with information filters. Although the general problem of finding an optimal execution plan is likely exponential in the number of filters, we show experimentally that our local optimality criteria, used in a polynomial-time algorithm, nearly always find the global optimum with 15 filters or less, a sufficient number of filters for most applications. Our methods do not require special hardware and avoid the high processor idleness that is characteristic of massive parallelism solutions to this problem. We apply our ideas to an important application, information retrieval of cpationed data using natural-language understanding...

A New Ranking Principle for Multimedia Information Retrieval

Wechsler, Martin; Schauble, Peter
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 11/02/1999 Português
Relevância na Pesquisa
68.853525%
A theoretic framework for multimedia information retrieval is introduced which guarantees optimal retrieval effectiveness. In particular, a Ranking Principle for Distributed Multimedia-Documents (RPDM) is described together with an algorithm that satisfies this principle. Finally, the RPDM is shown to be a generalization of the Probability Ranking principle (PRP) which guarantees optimal retrieval effectiveness in the case of text document retrieval. The PRP justifies theoretically the relevance ranking adopted by modern search engines. In contrast to the classical PRP, the new RPDM takes into account transmission and inspection time, and most importantly, aspectual recall rather than simple recall.; Comment: submission for DL'99. conference compliant format (two-column, etc.) will be produced later

Unsupervised Visual and Textual Information Fusion in Multimedia Retrieval - A Graph-based Point of View

Csurka, Gabriela; Ah-Pine, Julien; Clinchant, Stéphane
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 27/01/2014 Português
Relevância na Pesquisa
69.481187%
Multimedia collections are more than ever growing in size and diversity. Effective multimedia retrieval systems are thus critical to access these datasets from the end-user perspective and in a scalable way. We are interested in repositories of image/text multimedia objects and we study multimodal information fusion techniques in the context of content based multimedia information retrieval. We focus on graph based methods which have proven to provide state-of-the-art performances. We particularly examine two of such methods : cross-media similarities and random walk based scores. From a theoretical viewpoint, we propose a unifying graph based framework which encompasses the two aforementioned approaches. Our proposal allows us to highlight the core features one should consider when using a graph based technique for the combination of visual and textual information. We compare cross-media and random walk based results using three different real-world datasets. From a practical standpoint, our extended empirical analysis allow us to provide insights and guidelines about the use of graph based methods for multimodal information fusion in content based multimedia information retrieval.; Comment: An extended version of the paper: Visual and Textual Information Fusion in Multimedia Retrieval using Semantic Filtering and Graph based Methods...

Spaces, Trees and Colors: The Algorithmic Landscape of Document Retrieval on Sequences

Navarro, Gonzalo
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
68.462397%
Document retrieval is one of the best established information retrieval activities since the sixties, pervading all search engines. Its aim is to obtain, from a collection of text documents, those most relevant to a pattern query. Current technology is mostly oriented to "natural language" text collections, where inverted indices are the preferred solution. As successful as this paradigm has been, it fails to properly handle some East Asian languages and other scenarios where the "natural language" assumptions do not hold. In this survey we cover the recent research in extending the document retrieval techniques to a broader class of sequence collections, which has applications bioinformatics, data and Web mining, chemoinformatics, software engineering, multimedia information retrieval, and many others. We focus on the algorithmic aspects of the techniques, uncovering a rich world of relations between document retrieval challenges and fundamental problems on trees, strings, range queries, discrete geometry, and others.

Codebook based Audio Feature Representation for Music Information Retrieval

Vaizman, Yonatan; McFee, Brian; Lanckriet, Gert
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 19/12/2013 Português
Relevância na Pesquisa
68.29228%
Digital music has become prolific in the web in recent decades. Automated recommendation systems are essential for users to discover music they love and for artists to reach appropriate audience. When manual annotations and user preference data is lacking (e.g. for new artists) these systems must rely on \emph{content based} methods. Besides powerful machine learning tools for classification and retrieval, a key component for successful recommendation is the \emph{audio content representation}. Good representations should capture informative musical patterns in the audio signal of songs. These representations should be concise, to enable efficient (low storage, easy indexing, fast search) management of huge music repositories, and should also be easy and fast to compute, to enable real-time interaction with a user supplying new songs to the system. Before designing new audio features, we explore the usage of traditional local features, while adding a stage of encoding with a pre-computed \emph{codebook} and a stage of pooling to get compact vectorial representations. We experiment with different encoding methods, namely \emph{the LASSO}, \emph{vector quantization (VQ)} and \emph{cosine similarity (CS)}. We evaluate the representations' quality in two music information retrieval applications: query-by-tag and query-by-example. Our results show that concise representations can be used for successful performance in both applications. We recommend using top-$\tau$ VQ encoding...

Semantic-Sensitive Web Information Retrieval Model for HTML Documents

Bassil, Youssef; Semaan, Paul
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 01/04/2012 Português
Relevância na Pesquisa
68.543345%
With the advent of the Internet, a new era of digital information exchange has begun. Currently, the Internet encompasses more than five billion online sites and this number is exponentially increasing every day. Fundamentally, Information Retrieval (IR) is the science and practice of storing documents and retrieving information from within these documents. Mathematically, IR systems are at the core based on a feature vector model coupled with a term weighting scheme that weights terms in a document according to their significance with respect to the context in which they appear. Practically, Vector Space Model (VSM), Term Frequency (TF), and Inverse Term Frequency (IDF) are among other long-established techniques employed in mainstream IR systems. However, present IR models only target generic-type text documents, in that, they do not consider specific formats of files such as HTML web documents. This paper proposes a new semantic-sensitive web information retrieval model for HTML documents. It consists of a vector model called SWVM and a weighting scheme called BTF-IDF, particularly designed to support the indexing and retrieval of HTML web documents. The chief advantage of the proposed model is that it assigns extra weights for terms that appear in certain pre-specified HTML tags that are correlated to the semantics of the document. Additionally...