Constantin Vertan

Adaptive-neighborhood histogram equalization of color images

Histogram equalization (HE) is one of the simplest and most effective techniques for enhancing gray-level images. For color images, HE becomes a more difficult task, due to the vectorial nature of the data. We propose a new method for color image enhancement that uses two hierarchical levels of HE: global and local. In order to preserve the hue, equalization is only applied to intensities. For each pixel (called the ‘‘seed’’ when being processed) a variable-sized, variable-shaped neighborhood is determined to contain pixels that are ‘‘similar’’ to the seed. Then, the histogram of the region is stretched to a range that is computed with respect to the statistical parameters of the region (mean and variance) and to the global HE function (of intensities), and only the seed pixel is given a new intensity value. We applied the proposed color HE method to various images and observed the results to be subjectively ‘‘pleasant to the human eye,’’ with emphasized details, preserved colors, and with the histogram of intensities close to the ideal uniform one. The results compared favorably with those of three other methods (histogram explosion, histogram decimation, and three-dimensional histogram equalization) in terms of subjective visual quality.

A Pseudo-logarithmic Image Processing Framework for Edge Detection

The paper presents a new [pseudo-] Logarithmic Model for Image Processing (LIP), which allows the computation of gray-level addition, substraction and multiplication with scalars within a fixed gray-level range [0; D ] without the use of clipping. The implementation of Laplacian edge detection techniques under the proposed model yields superior performance in biomedical applications as compared with the classical operations (performed either as real axis operations, either as classical LIP models).

COLOR IMAGE ENHANCEMENT IN THE FRAMEWORK OF LOGARITHMIC MODELS

The logarithmic model offers new tools for image processing. An efficient method for image enhancement, is to use an affine transformation with the logarithmic operations: addition and scalar multiplication. By adding a fuzzy setting to our model we gain flexibility and better results are possible. We define some criteria for automatically determining the parameters of the processing and this is done via the fuzzy mean and fuzzy variance computed by logarithmic operations.

Fuzzy Nonlinear Filtering of Color Images: A Survey

This contribution is intended as a survey of the existing fuzzy (or fuzzy related) filtering techniques for multichannel (and color in particular) images. We propose a classification of all these approaches to color image processing into four categories, based on the importance that fuzzy theory receives during the filter design: crude fuzzy, fuzzy paradigm based, fuzzy aggregative and fuzzy inferential. These categories are not necessarily mutually exclusive, and their boundaries can also be fuzzy. We will show how the perceptual notion of JND (Just Noticeable Difference) can provide a fuzzy-like approach to color correctness evaluation.

Color morphology-like operators based on color geometric shape characteristics

Mathematical morphology is based on two infimum- and respectively, supremum-commuting operations (the erosion and the dilation). In the scalar case, these operations are obviously the minimum and maximum. In the vector-valued case, minimum and maximum cannot be easily defined. Pixels within color images are described by three-component vectors, and thus the mathematical morphology is difficult to introduce for colors. We propose pseudo-morphology based on reduced ordering of colors (associate a scalar to each color, order the scalars and impose their ranking to their corresponding colors). The approach has been widely investigated, by proposing different scalars (usually the same scalars as used for distance-based color image filtering). We propose the use of scalars issued as geometrical shape invariants for a triangle-representation of colors.

Learning Pain from Emotion: Transferred HoT Data Representation for Pain Intensity Estimation

Automatic monitoring for the assessment of pain can significantly improve the psychological comfort of patients. Recently introduced databases with expert annotation opened the way for pain intensity estimation from facial analysis. In this contribution, pivotal face elements are identified using the Histograms of Topographical features (HoT) which are a generalization of the topographical primal sketch. In order to improve the discrimination between different pain intensity values and respectively the generalization with respect to the monitored persons, we transfer data representation from the emotion oriented Cohn-Kanade database to the UNBC McMaster Shoulder Pain database.

Can Your Eyes Tell Me How You Think? A Gaze Directed Estimation of the Mental Activity.

We investigate the possibility of estimating the cognitive process used by a person when addressing a mental challenge by following the Eye Accessing Cue (EAC) model from the Neuro-Linguistic Programming (NLP) theory [1]. This model, showed in figure 1, describes the eyemovements that are not used for visual tasks (non visual movements) and suggests that the direction of gaze, in such a case, can be an indicator for the internal representational system used by a person facing a given query. The actual EAC is thought to be identified by distinguishing between the relative position of the iris and the eye socket (lid edge). Our approach is to determine the four limits of the eye socket: the inner and outer corners, the upper and lower lids and the iris center and to subsequently analyze the identified region. The entire method flowchart is presented in figure 2. The schematics of the method used for independently looking for the position of each eye landmark is described in figure 3. Given the face square position by Viola-Jones algorithm [4] and the eye centers given by the method from [3], we fuse information related to position, normalized luminance, template matching and shape constraining. For position and luminance, we construct priors over the training database, while for template matching we describe a patch by concatenation of integral and edge projections on horizontal and vertical directions. The score of how likely is a patch to be centered on the true landmark position is given by a Multi Layer Perceptron. For the shape constrain, inspired by the CLM [2], we construct the probability density function in the eigenspace of the shapes in the training set. By ordering the landmarks according to a prior confidence (e.g. eye outer corners are more reliable than upper and lower eye boundaries) and by keeping all points fixed with the exception of the current least reliable, we build the likelihood of various current landmark positions. This information is fused with previous stages and we iteratively improve the landmark position. The final landmark position is taken as the weighted center of mass of the convex combination between initial stages and shape likelihood. To study the specific of the gaze direction we introduce Eye-Chimera database, which comprises 1172 frontal face images, grouped according to the 7 gaze directions, with a set of 5 points marked for each eye: the iris center and 4 points delimiting the bounding box. Recognizing individual EACs. The recognition of the EAC case (gaze direction) is done by identifying the position of the iris center inside the eye socket complemented by the information of the interior of the eye delimited shape. The interior of the eye quadrilateral shape is described by the integral projections normalized to 32 samples. For the actual recognition we have trained a random forrest to take as input the EAC feature (landmarks positions and integral features). We consider two types of recognition situations: three cases (looking

Content-based video description for automatic video genre categorization

In this paper, we propose an audio-visual approach to video genre categorization. Audio information is extracted at block-level, which has the advantage of capturing local temporal information. At temporal structural level, we asses action contents with respect to human perception. Further, color perception is quantified with statistics of color distribution, elementary hues, color properties and relationship of color. The last category of descriptors determines statistics of contour geometry. An extensive evaluation of this multi-modal approach based on on more than 91 hours of video footage is presented. We obtain average precision and recall ratios within [87%−100%] and [77%−100%], respectively, while average correct classification is up to 97%. Additionally, movies displayed according to feature-based coordinates in a virtual 3D browsing environment tend to regroup with respect to genre, which has potential application with real content-based browsing systems.

Logarithmic model-based dynamic range enhancement of hip X-ray images

Digital capture with consumer digital still camera of the radiographic film significantly decreases the dynamic range and, hence, the details visibility. We propose a method that boosts the dynamic range of the processed X-ray image based on the fusion of a set of digital images acquired under different exposure values. The fusion is controlled by a fuzzy-like confidence information and the luminance range is oversampled by using logarithmic image processing operators.

A Quantitative Evaluation of the Hip Prosthesis Segmentation Quality in X-Ray Images

X-ray film images are the main medical diagnosis tool in the evaluation of the fit of the hip prostheses inserted in total hip arthroplasty (THA) procedures. In a computer-aided diagnosis tool, one of the most important operations is the automatic segmentation of the X-ray image into the clinical relevant parts: prosthesis, bone (femur) and soft tissue. The paper investigates the use of several classical adaptive region segmentation techniques, using either the initial pixel luminance space (adaptive histogram thresholding), or an extended feature space (fuzzy C-means) and evaluates the segmentation quality, by the standard detection error and ROC (receiver operating characteristics) curves.