Abstract: In the field of multimedia retrieval in video, text frame classification is essential for text detection, event detection, event boundary detection, etc. We propose a new text frame classification method that introduces a combination of wavelet and median moment with k-means clustering to select probable text blocks among 16 equally sized blocks of a video frame. The same feature combination is used with a new Max–Min clustering at the pixel level to choose probable dominant text pixels in the selected probable text blocks. For the probable text pixels, a so-called mutual nearest neighbor based symmetry is explored with a four-quadrant formation centered at the centroid of the probable dominant text pixels to know whether a block is a true text block or not. If a frame produces at least one true text block then it is considered as a text frame otherwise it is a non-text frame. Experimental results on different text and non-text datasets including two public datasets and our own created data show that the proposed method gives promising results in terms of recall and precision at the block and frame levels. Further, we also show how existing text detection methods tend to misclassify non-text frames as text frames in term of recall and precision at both the block and frame levels.

Abstract: State-of-the-art systems on cognitive surveillance identify and describe complex events in selected domains, thus providing end-users with tools to easily access the contents of massive video footage. Nevertheless, as the complexity of events increases in semantics and the types of indoor/outdoor scenarios diversify, it becomes difficult to assess which events describe better the scene, and how to model them at a pixel level to fulfill natural language requests. We present an ontology-based methodology that guides the identification, step-by-step modeling, and generalization of the most relevant events to a specific domain. Our approach considers three steps: (1) end-users provide textual evidence from surveilled video sequences; (2) transcriptions are analyzed top-down to build the knowledge bases for event description; and (3) the obtained models are used to generalize event detection to different image sequences from the surveillance domain. This framework produces user-oriented knowledge that improves on existing advanced interfaces for video indexing and retrieval, by determining the best suited events for video understanding according to end-users. We have conducted experiments with outdoor and indoor scenes showing thefts, chases, and vandalism, demonstrating the feasibility and generalization of this proposal.

Abstract: This paper describes an affect-responsive interactive photo-frame application that offers its user a different experience with every use. It relies on visual analysis of activity levels and facial expressions of its users to select responses from a database of short video segments. This ever-growing database is automatically prepared by an offline analysis of user-uploaded videos. The resulting system matches its user’s affect along dimensions of valence and arousal, and gradually adapts its response to each specific user. In an extended mode, two such systems are coupled and feed each other with visual content. The strengths and weaknesses of the system are assessed through a usability study, where a Wizard-of-Oz response logic is contrasted with the fully automatic system that uses affective and activity-based features, either alone, or in tandem.

Abstract: Biologically inspired homing methods, such as the Average Landmark Vector, are an interesting solution for local navigation due to its simplicity. However, usually they require a modification of the environment by placing artificial landmarks in order to work reliably. In this paper we combine the Average Landmark Vector with invariant feature points automatically detected in panoramic images to overcome this limitation. The proposed approach has been evaluated first in simulation and, as promising results are found, also in two data sets of panoramas from real world environments.

Abstract: Graphical symbol recognition and spotting recently have become an important research activity. In this work we present a descriptor for symbols, especially for line drawings. The descriptor is based on the graph representation of graphical objects. We construct graphs from the vectorized information of the binarized images, where the critical points detected by the vectorization algorithm are considered as nodes and the lines joining them are considered as edges. Graph paths between two nodes in a graph are the finite sequences of nodes following the order from the starting to the final node. The occurrences of different graph paths in a given graph is an important feature, as they capture the geometrical and structural attributes of a graph. So the graph representing a symbol can efficiently be represent by the occurrences of its different paths. Their occurrences in a symbol can be obtained in terms of a histogram counting the number of some fixed prototype paths, we call the histogram as the Bag-of-GraphPaths (BOGP). These BOGP histograms are used as a descriptor to measure the distance among the symbols in vector space. We use the descriptor for three applications, they are: (1) classification of the graphical symbols, (2) spotting of the architectural symbols on floorplans, (3) classification of the historical handwritten words.

Abstract: Camera-based person detection is of paramount interest due to its potential applications. The task is diffcult because the great variety of backgrounds (scenarios, illumination) in which persons are present, as well as their intra-class variability (pose, clothe, occlusion). In fact, the class person is one of the included in the popular PASCAL visual object classes (VOC) challenge. A breakthrough for this challenge, regarding person detection, is due to Felzenszwalb et al. These authors proposed a part-based detector that relies on histograms of oriented gradients (HOG) and latent support vector machines (LatSVM) to learn a model of the whole human body and its constitutive parts, as well as their relative position. Since the approach of Felzenszwalb et al. appeared new variants have been proposed, usually giving rise to more complex models. In this paper, we focus on an issue that has not attracted suficient interest up to now. In particular, we refer to the fact that HOG is usually computed from RGB color space, but other possibilities exist and deserve the corresponding investigation. In this paper we challenge RGB space with the opponent color space (OPP), which is inspired in the human vision system.We will compute the HOG on top of OPP, then we train and test the part-based human classifer by Felzenszwalb et al. using PASCAL VOC challenge protocols and person database. Our experiments demonstrate that OPP outperforms RGB. We also investigate possible differences among types of scenarios: indoor, urban and countryside. Interestingly, our experiments suggest that the beneficts of OPP with respect to RGB mainly come for indoor and countryside scenarios, those in which the human visual system was designed by evolution.

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.