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.
Visual saliency is the property of a scene to draw the attention of different people to the same objects within it. Its investigation and development enabled many practical applications. In this paper we aim to use it for the study of visual art. As a first contribution we introduce an extensive database annotated in terms of visual saliency by considering data acquired from many users. Secondly,...
In this paper we approach the problem of scene recognition in paintings. We tackle this task with the aid of Convolutional Neural Networks and a large database consisting of around 80,000 paintings. The main purpose is to identify an efficient method to enlarge the database by domain transfer from photographic content to artistic content. Thus, we discuss the practical capabilities of a recent method...
The Otsu thresholding is a classical binarization method that partitions graylevel images according to a within-class variance minimization principle. The Otsu method is a particular case of the general Lloyd-Max optimal quantization. We propose the alternative use of Otsu/Lloyd thresholds, computed locally, as local features that describe the image content. This description can be used directly within...
This paper presents a new approach towards the selection of color image features to be used in the classification of burn wounds. The features are selected such that they generate similarity matrices and multidimensional scaling (MDS) plots that match the similarity matrix and the MDS-plot resulting from a subjective visual burn area similarity test performed by trained surgeons. We show that standard...
Burns are some of the most severe forms of accidental trauma across the world. Burn injuries require specialized care and an early and accurate distinction between superficial dermal burns and deep dermal burns which require further surgical procedures, as they do not heal spontaneously. This paper proposes a multispectral imaging based diagnosis support system for the identification of severe burns...
To facilitate computer analysis of visual art, in the form of paintings, we introduce Pandora (Paintings Dataset for Recognizing the Art movement) database, a collection of digitized paintings labelled with respect to the artistic movement. Noting that the set of databases available as benchmarks for evaluation is highly reduced and most existing ones are limited in variability and number of images,...
In this paper we introduce a novel color transfer method to address the underexposed image amplification problem. Targeted scenario implies a dual acquisition, containing a normally exposed, possibly blurred, image and an underexposed/low-light but sharp one. The problem of enhancing the low-light image is addressed as a color transfer problem. To properly solve the color transfer, the scene is split...
This papers presents the use of color imaging as a starting point of burn wound evaluation, by the discrimination between healthy skin and burn wound. The skin/burn area identification is performed pixel-wise, according to the properties of an entire encompassing patch. The classification is learned under a supervised scenario, according to a ground truth defined by specialist surgeons from a large...
This paper addresses the problem of recognizing illogical object juxtaposing in the specific form of classifying digitized paintings in art movements. More precisely we distinguish between realism and surrealism movements. We propose a system based on feature extraction and machine learning that is able to understand the scene in the digitized paintings and to classify the art works from the two movements...
In this paper we concentrate our efforts on the analysis of the facial landmarks dynamics as being a relevant method to access the subject's emotion. Given the person's facial landmarks we describe their trajectory with respect to the neutral pose and out of this trajectory we extract relevant features that are subsequently entered into a classification system for the actual recognition of emotion...
The infrared imaging (comprising both the thermal infrared and the near infrared bands) became an imaging modality at hand, with the potential of providing insights in the unseen components of various physical and biological processes. Various experiments have shown that the focusing of infrared images is significant different from the focus of visible band images, posing significant problems in autofocus...
Robust, reliable head pose estimation is a key step in many practical applications involving face analysis tasks. We address the problem of head pose estimation in still gray scale images, assuming a standard camera with limited resolution details. To achieve the proposed goal, we rely on the standard pattern recognition approach: we describe the previously detected faces with easy-to-compute image...
In this paper we address the problem of motion blur in still image acquisition by prevention and compensation. In the prevention step, we reduce the exposure time below “the motion limit” thus drastically diminishing the chance for the motion blur to happen. We compensate the poor illumination and colors levels by employing a color transfer process from a secondary normally exposed image of the same...
The X-ray film image is the main medical diagnosis tool in the evaluation of the fit of the hip prostheses inserted in total hip arthroplasty (THA) procedures. In the design of a computer-aided diagnosis tool, one of the most important operations is the digital capture of the film images. This contribution investigates the use of a consumer-grade digital still camera as a digital acquisition tool...
In this paper we describe a new system for eye center (pupil) localization. The patch centered on the eye is described by concatenations of integral and edge projections. Next, for dimensionality reduction, the Principal Component Analysis (PCA) technique is employed, while the discrimination among possible candidates is performed with a Bagged ensemble of Regression Trees (BRT) classifier. The accuracy...
In this paper we describe a new system for localization of landmarks in eye region. Firstly, in the upper face area possible the eye regions are described by concatenations of integral and edge projections. The features dimension is reduced through Principal Component Analysis (PCA) technique, to accelerate the computation. The resulting features are fed into a properly-trained Multi-Layer Perceptron...
The use of digital image processing as a medical diagnosis aid is now well established, being slowly but successfully integrated directly within the medical imaging devices. The traditional use of digital image processing as a post-imaging technique is still interesting, especially for new approaches to classical applications or for pioneering new ones. Our studies in the field of near automatic interpretation...
This paper presents a study of three classification methods applied on natural images with the goal of detecting the eye regions. The challenge that we aim to solve is finding the eyes on faces expressing emotions - this is extremely difficult because the shape of the facial features changes drastically when the subject goes through an emotional state. We attempt to solve this challenge by looking...
This paper deals with the issue of thrown or dropped object detection as an application of the 3D time-of-flight (ToF) camera. The use of distance information provided by the ToF camera makes the segmentation step straight forward. Then, instead of high computational motion detection and estimation algorithms, mainly a labeling and tracking procedure is used. This approach provides real time low complexity...
This paper proposes a solution for detecting the Eye Accessing Cue (EAC) model used in Neuro-Linguistic Programming based on the position of the eye center inside the bounding box of the eye. The eye points are determined using an iris center detection method based on the curvature of the isophote and a facial points detection method based on graph models. The distribution of luminance is analyzed...
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.