This work addresses the development of a unified approach to content-based indexing and retrieval of digital videos from television archives. The proposed approach has been designed to deal with arbitrary television genres, making it suitable for various applications. To achieve this goal, the main steps of a content-based video retrieval system are addressed in this work, namely: video segmentation, key-frame extraction, content-based video indexing and the video retrieval operation itself. Video segmentation is addressed as a typical TV broadcast structuring problem, which consists in automatically determining the boundaries of each broadcasted program (like movies, news, among others) and inter-program (for instance, commercials). Specifically, to segment the videos, Electronic Program Guide (EPG) metadata is combined with the detection of two special cues, namely, audio cuts (silence) and dark monochrome frames. On the other hand, a color histogram-based approach performs key-frame extraction. Video indexing and retrieval are accomplished by using hashing and k-d tree methods, while visual signatures containing color, shape and texture information are estimated for the key-frames, by using image and frequency domain techniques. Experimental results with the dataset of a multimedia information system especially developed for managing television broadcast archives demonstrate that our approach works efficiently, retrieving videos in 0.16 seconds on average and achieving recall, precision and F1 measure values, as high as 0.76, 0.97 and 0.86 respectively.
This paper addresses the problem of object-based image retrieval, by using local feature extraction and a relevance feedback mechanism for quickly narrowing down the image search process to the user needs. This approach relies on the hypothesis that semantically similar images are clustered in some feature space and, in this scenario: (i) computes image signatures that are invariant to scale and rotation using SIFT, (ii) calculates the vector of locally aggregated descriptors (VLAD) to make a fixed length descriptor for the images, (iii) reduce the VLAD descriptor dimensionality with Principal Component Analysis (PCA) and (iv) uses the k-Means algorithm for grouping images that are semantically similar. The proposed approach has been successfully validated using 33,192 images from the ALOI database, obtaining a mean recall value of 47.4% for searches of images containing objects that are identical to the object query and 20.7% for searches of images containing different objects (albeit visually similar) to the object query.
General TermsContent-based image retrieval, relevance feedback, feature extraction.
KeywordsObject-based image retrieval, scale invariant feature transform, principal component analysis, vector of locally aggregated descriptors, clustering algorithms.
ResumoAbstract -This paper proposes a digital library to organize properly the course monographs of graduate schools. Such a proposed digital library aims the monographs storage generated by students, improving the research by the academic community. In order to demonstrate the effectiveness and the efficiency of the proposed digital library, a prototype was built and practical experiments were performed by real users, to analyze the accuracy on the issues of usability, requirements for interface and quality of the obtained results. keywords -digital library, metadata, dublin core.
Several information recovery systems use functions to determine similarity among objects in a collection. Such functions require a similarity threshold, from which it becomes possible to decide on the similarity between two given objects. Thus, depending on its value, the results returned by systems in a search may be satisfactory or not. However, the definition of similarity thresholds is difficult because it depends on several factors. Typically, specialists fix a threshold value for a given system, which is used in all searches. However, an expert-defined value is quite costly and not always possible. Therefore, this study proposes an approach for automatic and online estimation of the similarity threshold value, to be specifically used by content-based visual information retrieval system (image and video) search engines. The experimental results obtained with the proposed approach prove rather promising. For example, for one of the case studies, the performance of the proposed approach achieved 99.5 % efficiency in comparison with that obtained by a specialist using an empirical similarity threshold. Moreover, such automated approach becomes more scalable and less costly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.