Search

It has been proven that Logarithmic Image Processing (LIP) models provide a suitable framework for visualizing and enhancing digital images acquired by various sources. The most visible (although simplified) result of using such a model is that LIP allows the computation of graylevel addition, subtraction and multiplication with scalars within a fixed graylevel range without the use of clipping. It is claimed that a generalized LIP framework (i.e., a parameterized family of LIP models) can be constructed on the basis of the fuzzy modelling of gray level addition as an accumulation process described by the Hamacher conorm. All the existing LIP and LIP-like models are obtained as particular cases of the proposed framework in the range corresponding to real-world digital images.

In this paper we emphasize a similarity between the Logarithmic-Type Image Processing (LTIP) model and the Naka-Rushton model of the Human Visual System (HVS). LTIP is a derivation of the Logarithmic Image Processing (LIP), which further replaces the logarithmic function with a ratio of polynomial functions. Based on this similarity, we show that it is possible to present an unifying framework for the High Dynamic Range (HDR) imaging problem, namely that performing exposure merging under the LTIP model is equivalent to standard irradiance map fusion. The resulting HDR algorithm is shown to provide high quality in both subjective and objective evaluations., Comment: 14 pages 8 figures. Accepted at AMCS journal

The Logarithmic Type Image Processing (LTIP) tools are mathematical models that were constructed for the representation and processing of gray tones images. By careful redefinition of the fundamental operations, namely addition and scalar multiplication, a set of mathematical properties are achieved. Here we propose the extension of LTIP models by a novel parameterization rule that ensures preservation of the required cone space structure. To prove the usability of the proposed extension we present an application for low-light image enhancement in images acquired with digital still camera. The closing property of the named model facilitates similarity with human visual system and digital camera processing pipeline, thus leading to superior behavior when compared with state of the art methods.

Total hip replacement is a common procedure in today orthopedics, with high rate of long-term success. Failure prevention is based on a regular follow-up aimed at checking the prosthesis fit and state by means of visual inspection of radiographic images. It is our purpose to provide automatic means for aiding medical personnel in this task. Therefore we have constructed tools for automatic identification of the component parts of the radiograph, followed by analysis of interactions between the bone and the prosthesis. The results form a set of parameters with obvious interest in medical diagnosis.

This paper proposes a new framework for the eye centers localization by the joint use of encoding of normalized image projections and a Multi Layer Perceptron (MLP) classifier. The encoding is novel and it consists in identifying the zero-crossings and extracting the relevant parameters from the resulting modes. The compressed normalized projections produce feature descriptors that are inputs to a properly-trained MLP, for discriminating among various categories of image regions. The proposed framework forms a fast and reliable system for the eye centers localization, especially in the context of face expression analysis in unconstrained environments. We successfully test the proposed method on a wide variety of databases including BioID, Cohn-Kanade, Extended Yale B and Labelled Faces in the Wild (LFW) databases.

Pain assessment through observational pain scales is necessary for special categories of patients such as neonates, patients with dementia, and critically ill patients. The recently introduced Prkachin-Solomon score allows pain assessment directly from facial images opening the path for multiple assistive applications. In this paper, we proposed a system built upon the Histograms of Topographical (HoT) features, which are a generalization of the topographical primal sketch, for the description of the face parts contributing to the mentioned score. We further propose a semi-supervised, clustering oriented self-taught learning procedure developed on the Cohn-Kanade emotion oriented database by adapting the spectral regression. To make use of inter-frame pain correlation we introduce a machine learning based temporal filtering. We use this procedure to improve the discrimination between different pain intensity levels and the generalization with respect to the monitored persons, while testing on the UNBC McMaster Shoulder Pain database. We introduce the Histogram of Topographical (HoT) features to address the variability in face images.We propose a semi-supervised, clustering-oriented, self-taught learning procedure.We propose a machine learning based, temporal filtering to increase the overall accuracy.A system for face dynamic analysis that applied to pain intensity estimation leads to qualitative results.