The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A correlation-enhanced similarity matching framework for medical image retrieval is presented in a local concept-based feature space. In this framework, images are presented by vectors of concepts that comprise of local color and texture patches of image regions in a multi-dimensional feature space. To generate the concept vocabularies and represent the images, statistical models are built using a...
Spatial Gabor energy filters (GE) are one of the most successful approaches to represent facial expressions in computer vision applications, including face recognition and expression analysis. It is well known that these filters approximate the response of complex cells in primary visual cortex. However these neurons are modulated by the temporal, not just spatial, properties of the visual signal...
Age estimation from facial images has promising applications in human-computer interaction, biometrics, visual surveillance, and electronic customer relationship management, etc. Most existing techniques and systems can only handle frontal or near frontal view age estimation due to the difficulties of 1) differentiating diverse variations from uncontrollable and personalized aging patterns on faces...
This paper proposes a method of feature co-occurrence representation based on boosting for object detection. A previously proposed method that combines multiple binary-classified codes by AdaBoost to represent the co-occurrence of features has been shown to be effective in face detection. However, if an input feature is difficult to be assigned to a correct binary code due to occlusion or other factors,...
We propose a real-time method for counting pedestrians and bicyclists by classifying bulks of asynchronous events generated upon scene activities by an event-based 3D dynamic vision system. The inherent detection of moving objects offered by the 3D dynamic vision system comprising a pair of dynamic vision sensors allows event-based stereo vision in real-time and a 3D representation of moving objects...
In this work we tackle the problem of search personalization for on-line soft goods shopping. By learning what the user likes and what the user does not like, better search rankings and therefore a better overall shopping experience can be obtained. The first contribution of the work is in terms of feature selection: given the specific nature of the domain, we combine the traditional visual and text...
In this paper we study some problems important for large-scale human age estimation. First, we study age estimation performance under variations across race and gender. Through a large number of age estimation experiments, significant differences are observed for age estimation between “no crossing” and “crossing.” Our study discovers that crossing race and gender can result in significant error increases...
This paper presents a method to assist in the tedious procedure of reconstructing ceramic vessels from unearthed archaeological shards or fragments using 3D computer vision-enabling technologies. The method uses vessels surface markings combined with a generic model to produce a representation of what the original vessel may have looked like. Generic vessel models used are based on a host of factors...
Tracking and detection of objects often require to apply complex models to cope with the large intra-class variability of the foreground as well as the background class. In this work, we reduce the complexity of a binary classification problem by a context-driven approach. The main idea is to use a hidden multi-class representation to capture multi-modalities in the data finally providing a binary...
This paper proposes a new method for estimating and maintaining over time the pose of a single Pan-Tilt-Zoom camera (PTZ). This is achieved firstly by building offline a keypoints database of the scene; then, in the online step, a coarse localization is obtained from camera odometry and finally refined by visual landmarks matching. A maintenance step is also performed at runtime to keep updated the...
In this paper, the principles of sparse signal representation theory are explored in order to perform facial expressions recognition from frontal views. Motivated by the success such methods have demonstrated in the face recognition problem, we formulate the feature extraction procedure in order to achieve facial expression recognition as an l1 optimization problem. We show that the straightforward...
We propose a structural image representation and show its relevance for multi-modal image registration. Structural representation means that only the structures in the image matter and not the intensity values of their depiction. The representation is formulated as a dense descriptor. We specify three properties an optimal descriptor for structural registration has to fulfill: locality preservation,...
The representation of a 3-D scene is essential to recent multi-view imaging technologies. In this paper we propose a unified geometry and texture representation based on global resampling of the scene. The 3-D coordinates and the associated texture information of the scene points are represented in the polar coordinate system. A novel layered data map representation with distance-dependent nonuniform...
We introduce a mobile system for creating high-resolution panoramic images. The user can rotate the camera around an arbitrary axis to create a 2D sweep and see a miniature preview panorama in real-time. The system tracks camera motion and automatically captures high-resolution images and generates a high-quality wide-view panoramic image. We employ a coarse-to-fine method for high-quality registration,...
This paper proposes a real-time implementation of a clustering and classification method using asynchronous events generated upon scene activities by an event-based dynamic stereo vision system. The inherent detection of moving objects offered by the dynamic stereo vision system comprising a pair of dynamic vision sensors allows event-based stereo vision in real-time and a 3D representation of moving...
The current paper presents a low-complexity approach to the problem of simultaneous tracking of several people in low resolution sequences from multiple calibrated cameras. Redundancy among cameras is exploited to generate a discrete 3D colored representation of the scene. The proposed filtering technique estimates the centroid of a target using only a sparse set of points placed on its surface and...
This paper proposes an algorithm for real-time learning without explicit feedback. The algorithm combines the ideas of semi-supervised learning on graphs and online learning. In particular, it iteratively builds a graphical representation of its world and updates it with observed examples. Labeled examples constitute the initial bias of the algorithm and are provided offline, and a stream of unlabeled...
It is likely that human-level online learning for vision will require a brain-like developmental model. We present a general purpose model, called the Self-Aware and Self-Effecting (SASE) model, characterized by internal sensation and action. Rooted in the biological genomic equivalence principle, this model is a general-purpose cell-centered in-place learning scheme to handle different levels of...
This paper proposes a method for clustering asynchronous events generated upon scene activities by a dynamic 3D vision system. The inherent detection of moving objects offered by the dynamic stereo vision system comprising a pair of dynamic vision sensors allows event-based stereo vision in real-time and a 3D representation of moving objects. The clustering method exploits the sparse spatio-temporal...
In this paper, we present a new perceptual grouping algorithm using sparse semi-supervised learning (SSSL). In SSSL, KD-tree is used for effective representation and efficient retrieval. SSSL performs both transductive and inductive inference with a new dynamic graph concept. The perceptual grouping problem is tackled using SSSL to group different patterns into one object and separate similar patterns...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.