Jurandy Almeida

VISON: VIdeo Summarization for ONline applications

Recent advances in technology have increased the availability of video data, creating a strong requirement for efficient systems to manage those materials. Making efficient use of video information requires that data to be accessed in a user-friendly way. This has been the goal of a quickly evolving research area known as video summarization. Most of existing techniques to address the problem of summarizing a video sequence have focused on the uncompressed domain. However, decoding and analyzing of a video sequence are two extremely time-consuming tasks. Thus, video summaries are usually produced off-line, penalizing any user interaction. The lack of customization is very critical, as users often have different demands and resources. Since video data are usually available in compressed form, it is desirable to directly process video material without decoding. In this paper, we present VISON, a novel approach for video summarization that works in the compressed domain and allows user interaction. The proposed method is based on both exploiting visual features extracted from the video stream and on using a simple and fast algorithm to summarize the video content. Results from a rigorous empirical comparison with a subjective evaluation show that our technique produces video summaries with high quality relative to the state-of-the-art solutions and in a computational time that makes it suitable for online usage.

Spam filtering: how the dimensionality reduction affects the accuracy of Naive Bayes classifiers

E-mail spam has become an increasingly important problem with a big economic impact in society. Fortunately, there are different approaches allowing to automatically detect and remove most of those messages, and the best-known techniques are based on Bayesian decision theory. However, such probabilistic approaches often suffer from a well-known difficulty: the high dimensionality of the feature space. Many term-selection methods have been proposed for avoiding the curse of dimensionality. Nevertheless, it is still unclear how the performance of Naive Bayes spam filters depends on the scheme applied for reducing the dimensionality of the feature space. In this paper, we study the performance of many term-selection techniques with several different models of Naive Bayes spam filters. Our experiments were diligently designed to ensure statistically sound results. Moreover, we perform an analysis concerning the measurements usually employed to evaluate the quality of spam filters. Finally, we also investigate the benefits of using the Matthews correlation coefficient as a measure of performance.

Online video summarization on compressed domain

Abstract Recent advances in technology have increased the availability of video data, creating a strong requirement for efficient systems to manage those materials. Making efficient use of video information requires that data to be accessed in a user-friendly way. Ideally, one would like to understand a video content, without having to watch it entirely. This has been the goal of a quickly evolving research area known as video summarization. In this paper, we present a novel approach for video summarization that works in the compressed domain and allows the progressive generation of a video summary. The proposed method relies on exploiting visual features extracted from the video stream and on using a simple and fast algorithm to summarize the video content. Experiments on a TRECVID 2007 dataset show that our approach presents high quality relative to the state-of-the-art solutions and in a computational time that makes it suitable for online usage.

A scalable re-ranking method for content-based image retrieval

Content-based Image Retrieval (CBIR) systems consider only a pairwise analysis, i.e., they measure the similarity between pairs of images, ignoring the rich information encoded in the relations among several images. However, the user perception usually considers the query specification and responses in a given context. In this scenario, re-ranking methods have been proposed to exploit the contextual information and, hence, improve the effectiveness of CBIR systems. Besides the effectiveness, the usefulness of those systems in real-world applications also depends on the efficiency and scalability of the retrieval process, imposing a great challenge to the re-ranking approaches, once they usually require the computation of distances among all the images of a given collection. In this paper, we present a novel approach for the re-ranking problem. It relies on the similarity of top-k lists produced by efficient indexing structures, instead of using distance information from the entire collection. Extensive experiments were conducted on a large image collection, using several indexing structures. Results from a rigorous experimental protocol show that the proposed method can obtain significant effectiveness gains (up to 12.19% better) and, at the same time, improve considerably the efficiency (up to 73.11% faster). In addition, our technique scales up very well, which makes it suitable for large collections.

Comparison of video sequences with histograms of motion patterns

Making efficient use of video information requires the development of a video signature and a similarity measure to rapidly identify similar videos in a huge database. Most of existing techniques to address this problem have focused on the uncompressed domain. However, decoding and analyzing of a video sequence are extremely time-consuming tasks. Since video data are usually available in compressed form, it is desirable to directly process video material without decoding. In this paper, we present a novel approach for comparing video sequences that works in the compressed domain. The proposed method is based on recognizing motion patterns extracted from the video stream and their occurrence histogram is proven to be a powerful feature for describing the video content. Experiments on a TRECVID 2010 dataset show that our approach presents high accuracy relative to the state-of-the-art solutions and in a computational time that makes it suitable for large collections.

A visual approach for video geocoding using bag-of-scenes

This paper presents a novel approach for video representation, called bag-of-scenes. The proposed method is based on dictionaries of scenes, which provide a high-level representation for videos. Scenes are elements with much more semantic information than local features, specially for geotagging videos using visual content. Thus, each component of the representation model has self-contained semantics and, hence, it can be directly related to a specific place of interest. Experiments were conducted in the context of the MediaEval 2011 Placing Task. The reported results show our strategy compared to those from other participants that used only visual content to accomplish this task. Despite our very simple way to generate the visual dictionary, which has taken photos at random, the results show that our approach presents high accuracy relative to the state-of-the art solutions.

Evaluation of Approaches for Dimensionality Reduction Applied with Naive Bayes Anti-Spam Filters

There are different approaches able to automatically detect e-mail spam messages, and the best-known ones are based on Bayesian decision theory. However, the most of these approaches have the same difficulty: the high dimensionality of the feature space. Many term selection methods have been proposed in the literature. Nevertheless, it is still unclear how the performance of naive Bayes anti-spam filters depends on the methods applied for reducing the dimensionality of the feature space. In this paper, we compare the performance of most popular methods used as term selection techniques, such as document frequency, information gain, mutual information, X 2 statistic, and odds ratio used for reducing the dimensionality of the term space with four well-known different versions of naive Bayes spam filter.

Rapid Video Summarization on Compressed Video

Recent advances in technology have increased the availability of video data, creating a strong requirement for efficient systems to manage those materials. Making efficient use of video information requires that data be accessed in a user-friendly way. This has been the goal of a quickly evolving research area known as video summarization. Most of existing techniques to address the problem of summarizing a video sequence have focused on the uncompressed domain. However, decoding and analyzing of a video sequence are two extremely time-consuming tasks. Since video data are usually available in compressed form, it is desirable to directly process video material without decoding. In this paper, we present a novel approach for video summarization that works in the compressed domain. The proposed method is based on both exploiting visual features extracted from the video stream and on using a simple and fast algorithm to summarize the video content. Results from a rigorous empirical comparison with a subjective evaluation show that our approach produces video summaries with superior quality relative to the state-of-the-art solutions and in a computational time that allows on-the-fly usage.

Fusion of Local and Global Descriptors for Content-Based Image and Video Retrieval

Recently, fusion of descriptors has become a trend for improving the performance in image and video retrieval tasks. Descriptors can be global or local, depending on how they analyze visual content. Most of existing works have focused on the fusion of a single type of descriptor. Different from all of them, this paper aims to analyze the impact of combining global and local descriptors. Here, we perform a comparative study of different types of descriptors and all of their possible combinations. Extensive experiments of a rigorous experimental design show that global and local descriptors complement each other, such that, when combined, they outperform other combinations or single descriptors.

Applying machine learning based on multiscale classifiers to detect remote phenology patterns in Cerrado savanna trees

Abstract Plant phenology is one of the most reliable indicators of species responses to global climate change, motivating the development of new technologies for phenological monitoring. Digital cameras or near remote systems have been efficiently applied as multi-channel imaging sensors, where leaf color information is extracted from the RGB (Red, Green, and Blue) color channels, and the changes in green levels are used to infer leafing patterns of plant species. In this scenario, texture information is a great ally for image analysis that has been little used in phenology studies. We monitored leaf-changing patterns of Cerrado savanna vegetation by taking daily digital images. We extract RGB channels from the digital images and correlate them with phenological changes. Additionally, we benefit from the inclusion of textural metrics for quantifying spatial heterogeneity. Our first goals are: (1) to test if color change information is able to characterize the phenological pattern of a group of species; (2) to test if the temporal variation in image texture is useful to distinguish plant species; and (3) to test if individuals from the same species may be automatically identified using digital images. In this paper, we present a machine learning approach based on multiscale classifiers to detect phenological patterns in the digital images. Our results indicate that: (1) extreme hours (morning and afternoon) are the best for identifying plant species; (2) different plant species present a different behavior with respect to the color change information; and (3) texture variation along temporal images is promising information for capturing phenological patterns. Based on those results, we suggest that individuals from the same species and functional group might be identified using digital images, and introduce a new tool to help phenology experts in the identification of new individuals from the same species in the image and their location on the ground.