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: The perceived colour of a stimulus is dependent on multiple factors stemming out either from the context of the stimulus or idiosyncrasies of the observer. The complexity involved in combining these multiple effects is the main reason for the gap between classical calibrated colour spaces from colour science and colour representations used in computer vision, where colour is just one more visual cue immersed in a digital image where surfaces, shadows and illuminants interact seemingly out of control. With the aim to advance a few steps towards bridging this gap we present some results on computational representations of colour for computer vision. They have been developed by introducing perceptual considerations derived from the interaction of the colour of a point with its context. We show some techniques to represent the colour of a point influenced by assimilation and contrast effects due to the image surround and we show some results on how colour saliency can be derived in real images. We outline a model for automatic assignment of colour names to image points directly trained on psychophysical data. We show how colour segments can be perceptually grouped in the image by imposing shading coherence in the colour space.

Abstract: Activity Recognition is an emerging field of research, born from the larger fields of ubiquitous computing, context-aware computing and multimedia. Recently, recognizing everyday life activities becomes one of the challenges for pervasive computing. In our work, we developed a novel wearable system easy to use and comfortable to bring. Our wearable system is based on a new set of 20 computationally efficient features and the Random Forest classifier. We obtain very encouraging results with classification accuracy of human activities recognition of up to 94%.

Abstract: In this paper we propose an efficient queried-by-example retrieval system which is able to retrieve trademark images by similarity from patent and trademark offices' digital libraries. Logo images are described by both their semantic content, by means of the Vienna codes, and their visual contents, by using shape and color as visual cues. The trademark descriptors are then indexed by a locality-sensitive hashing data structure aiming to perform approximate k-NN search in high dimensional spaces in sub-linear time. The resulting ranked lists are combined by using the Condorcet method and a relevance feedback step helps to iteratively revise the query and refine the obtained results. The experiments demonstrate the effectiveness and efficiency of this system on a realistic and large dataset.

Abstract: In this paper we present a methodology for the automatic detection of media-adventitia border (MAb) in Intravascular Ultrasound. A robust computation of the MAb is achieved through a holistic approach where the position of the MAb with respect to other tissues of the vessel is used. A learned quality measure assures that the resulting MAb is optimal with respect to all other tissues. The mean distance error computed through a set of 140 images is 0.2164 (±0.1326) mm.

Abstract: The assessment of arterial luminal area, performed by IVUS analysis, is a clinical index used to evaluate the degree of coronary artery disease. In this paper we propose a novel approach to automatically segment the vessel lumen, which combines model-based temporal information extracted from successive frames of the sequence, with spatial classification using the Growcut algorithm. The performance of the method is evaluated by an in vivo experiment on 300 IVUS frames. The automatic and manual segmentation performances in general vessel and stent frames are comparable. The average segmentation error in vessel, stent and bifurcation frames are 0.17±0.08 mm, 0.18±0.07 mm and 0.31±0.12 mm respectively.