A. De Albuquerque Araujo

BOSSA: Extended bow formalism for image classification

In image classification, the most powerful statistical learning approaches are based on the Bag-of-Words paradigm. In this article, we propose an extension of this formalism. Considering the Bag-of-Features, dictionary coding and pooling steps, we propose to focus on the pooling step. Instead of using the classical sum or max pooling strategies, we introduced a density function-based pooling strategy. This flexible formalism allows us to better represent the links between dictionary codewords and local descriptors in the resulting image signature. We evaluate our approach in two very challenging tasks of video and image classification, involving very high level semantic categories with large and nuanced visual diversity.

VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

In this paper, we propose an approach for video summarization (VSUMM). The video summaries are generated based on visual features. A factorial experiment is designed to analyze the relative impact of the attributes. We demonstrate the validity of the VSUMM approach by testing it on a collection of videos from Open Video Project. We provide a comparison among results of the proposed summarization technique with Open Video storyboard. A subjective evaluation showed that the summaries are produced with good quality.

Shot Boundary Detection by a Hierarchical Supervised Approach

Video shot boundary detection plays an important role in video processing. It is the first step toward video-content analysis and content-based video retrieval. We develop a hierarchical approach for shot boundary detection based on the assumption that hierarchy helps to take decisions by reducing the amount of indeterminate transitions. Our method consists in first detecting abrupt transitions using a learning-based approach, then non-abrupt transitions are split into gradual transitions and normal frames. We describe in this paper, a machine learning system for shot boundary detection. The core of this system is a kernel-based SVM classifier. We present some results obtained for shot extraction TRECVID 2006 Task.

A Fast Hue-Preserving Histogram Equalization Method for Color Image Enhancement using a Bayesian Framework

In this paper, we introduce a new hue-preserving histogram equalization method based on the ROB color space for image enhancement. We use fi-red, G-green, and B-blue 1D histograms to estimate the histogram to be equalized using a Naive Bayes rule. The histogram equalization is performed by shift hue-preserving transformations. Our method has linear time and space complexities, which complies with realtime applications requirements. A subjective assessment comparing our method and other three is performed. Experiments showed that our method is more robust than the others in the sense that neither unrealistic colors nor over-enhancement are produced.

Segmentation into fuzzy regions using topographic distance

This paper exposes an algorithm which leads to a fuzzy segmentation. This algorithm performs, as in the watershed method, a progressive flood of the gradient image from pixels of lowest gradients. It uses a new distance, called topographic distance. Any local minimum of the gradient norm image constitutes a seed for the region growing, avoiding the use of a marker image. These seeds constitute the cores of the initial fuzzy regions. Then the sites are gradually agglomerated to the region, while their membership degrees to the region decrease, according to the distance to the core and to the gradient norms, by the way of the topographic distance. The numerous fuzzy regions are then merged and the membership degrees of pixels to final regions are computed. Applications concern crisp segmentation of colour or gray scale images and pattern recognition from fuzzy regions.

An interactive video content-based retrieval system

The actual generation of video search engines offers low-level abstractions of the data while users seek for high-level semantics. The main challenge in video retrieval remains bridging the semantic gap. Thus, the effectiveness of video retrieval is based on the result of the interaction between query selection and a goal-oriented human user. The system exploits the human capability for rapidly scanning imagery augmenting it with an active learning loop, which tries to always present the most relevant material based on the current information. We describe in this paper, a machine learning system for interactive video retrieval. The core of this system is a kernel-based SVM classifier. The video retrieval uses the core as an active learning classifier. We perform an experiment against the 2005 NIST TRECVID benchmark in the high-level task.

Video fade detection by discrete line identification

The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect a type of gradual transition, the fade, by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image considering the histogram information, called visual rhythm by histogram. Afterwards, we apply image processing tools to detect specified patterns in this image.

Using the Hough transform to detect circular forms in satellite imagery

The objective of this work is to identify geological circular forms, impact and volcano craters using satellite images. The recognition of objects (circular forms) is the last step in a processing chain which can be described in four phases: image processing, pattern detection, pattern recognition, and identification of the targets (models). The work presents the detection of circular forms in images including the south region of the Minas Gerais State in Brazil.

Classifying images collected on the World Wide Web

This work presents the classification of images collected on the World Wide Web, using a supervised classification method, called ID3 (Itemized Dichotomizer 3). The classification consists in separating the images into two semantic classes: graphics and photographs. Photographs include natural scenes, like people, faces, animals, flowers, landscapes and cities. Graphics are logos, drawings, icons, maps, and backgrounds, usually generated by computer. To validate the classifier we used the k-fold cross-validation method. In the experimental tests 95.6% of the images were correctly classified.

An approach to detect video transitions based on mathematical morphology

The video segmentation problem can be regarded as a problem of detecting the fundamental video units (shots). Due to different ways of linking two consecutive shots this task turns out to be difficult. In this work, we propose a method to detect both cuts and gradual transitions by image segmentation tools instead of using dissimilarity measures or mathematical models. Firstly, the video is transformed into a 2D image, called visual rhythm by sub-sampling. Afterwards, we apply image processing tools to detect all vertical aligned transitions in this image. The main operator applied here is the morphological multiscale gradient. We also present some experimental results.