Abstract: Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. Additionally, we also consider power usage as an evaluation metric. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to (1) keep categorization accuracy intact, (2) decompose the problem and (3) give the same numerical results. In the experiments on large scale datasets it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

Abstract: Most applications dealing with problems involving the face require a robust estimation of the facial salient points. Nevertheless, this estimation is not usually an automated preprocessing step in applications dealing with facial expression recognition. In this paper we present a simple method to detect facial salient points in the face. It is based on a prior Point Distribution Model and a robust object descriptor. The model learns the distribution of the points from the training data, as well as the amount of variation in location each point exhibits. Using this model, we reduce the search areas to look for each point. In addition, we also exploit the global consistency of the points constellation, increasing the detection accuracy. The method was tested on two separate data sets and the results, in some cases, outperform the state of the art.

Abstract: This paper presents a syntactic model for architectural floor plan interpretation. A stochastic image grammar over an And-Or graph is inferred to represent the hierarchical, structural and semantic relations between elements of all possible floor plans. This grammar is augmented with three different probabilistic models, learnt from a training set, to account the frequency of that relations. Then, a Bottom-Up/Top-Down parser with a pruning strategy has been used for floor plan recognition. For a given input, the parser generates the most probable parse graph for that document. This graph not only contains the structural and semantic relations of its elements, but also its hierarchical composition, that allows to interpret the floor plan at different levels of abstraction.

Abstract: A common way to model multi-class classification problems is by means of Error-Correcting Output Codes (ECOC). Given a multi-class problem, the ECOC technique designs a codeword for each class, where each position of the code identifies the membership of the class for a given binary problem.A classification decision is obtained by assigning the label of the class with the closest code. In this paper, we overview the state-of-the-art on ECOC designs and test them in real applications. Results on different multi-class data sets show the benefits of using the ensemble of classifiers when categorizing objects in images.

Abstract: This chapter addresses the recognition of basic facial expressions. It has three main contributions. First, the authors introduce a view- and texture independent schemes that exploits facial action parameters estimated by an appearance-based 3D face tracker. they represent the learned facial actions associated with different facial expressions by time series. Two dynamic recognition schemes are proposed: (1) the first is based on conditional predictive models and on an analysis-synthesis scheme, and (2) the second is based on examples allowing straightforward use of machine learning approaches. Second, the authors propose an efficient recognition scheme based on the detection of keyframes in videos. Third, the authors compare the dynamic scheme with a static one based on analyzing individual snapshots and show that in general the former performs better than the latter. The authors then provide evaluations of performance using Linear Discriminant Analysis (LDA), Non parametric Discriminant Analysis (NDA), and Support Vector Machines (SVM).

Abstract: Image based human detection is of paramount interest for different applications. The most promising human detectors rely on discriminatively learnt classifiers, i.e., trained with labelled samples. However, labelling is a manual intensive task, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, in Marin et al. we have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera and the same type of scenario. Accordingly, in Vazquez et al. we cast the problem as one of supervised domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we use an active learning technique. Thus, ultimately our human model is learnt by the combination of virtual- and real-world labelled samples which, to the best of our knowledge, was not done before. Here, we term such combined space cool world. In this extended abstract we summarize our proposal, and include quantitative results from Vazquez et al. showing its validity.