Showing papers by "Bogdan Smolka published in 2016"

Fast averaging peer group filter for the impulsive noise removal in color images

Abstract: In the paper, a new approach to the impulsive noise removal in color images is presented. The new filtering design is based on the peer group concept, which determines the membership of a central pixel of the filtering window to its local neighborhood, in terms of the number of close pixels. Two pixels are declared as close if their distance in a given color space does not exceed a predefined threshold value. A pixel is treated as not corrupted by the impulsive noise process, if its peer group consists of at least two close pixels, otherwise this pixel is replaced by a weighted average of uncorrupted samples from the local neighborhood. The peer group size assigned to each pixel is used for the averaging operation, so that pixels which have many peers are taken with higher weight. The new filtering design proved to restore efficiently color images corrupted by even strong impulsive noise, while preserving tiny image details. The beneficial property of the proposed filter is its very low computational complexity, which allows its application in real-time image processing tasks.

Advances in Face Detection and Facial Image Analysis

Abstract: This book presents the state-of-the-art in face detection and analysis. It outlines new research directions, including in particular psychology-based facial dynamics recognition, aimed at various applications such as behavior analysis, deception detection, and diagnosis of various psychological disorders. Topics of interest include face and facial landmark detection, face recognition, facial expression and emotion analysis, facial dynamics analysis, face classification, identification, and clustering, and gaze direction and head pose estimation, as well as applications of face analysis.

On the efficiency of techniques for the reduction of impulsive noise in astronomical images

Abstract: The impulsive noise in astronomical images originates from various sources. It develops as a result of thermal generation in pixels, collision of cosmic rays with image sensor or may be induced by high readout voltage in Electron Multiplying CCD (EMCCD). It is usually efficiently removed by employing the dark frames or by averaging several exposures. Unfortunately, there are some circumstances, when either the observed objects or positions of impulsive pixels evolve and therefore each obtained image has to be filtered independently. In this article we present an overview of impulsive noise filtering methods and compare their efficiency for the purpose of astronomical image enhancement. The employed set of noise templates consists of dark frames obtained from CCD and EMCCD cameras working on ground and in space. The experiments conducted on synthetic and real images, allowed for drawing numerous conclusions about the usefulness of several filtering methods for various: (1) widths of stellar profiles, (2) signal to noise ratios, (3) noise distributions and (4) applied imaging techniques. The results of presented evaluation are especially valuable for selection of the most efficient filtering schema in astronomical image processing pipelines.

Automatic finger joint synovitis localization in ultrasound images

Abstract: A long-lasting inflammation of joints results between others in many arthritis diseases. When not cured, it may influence other organs and general patients' health. Therefore, early detection and running proper medical treatment are of big value. The patients' organs are scanned with high frequency acoustic waves, which enable visualization of interior body structures through an ultrasound sonography (USG) image. However, the procedure is standardized, different projections result in a variety of possible data, which should be analyzed in short period of time by a physician, who is using medical atlases as a guidance. This work introduces an efficient framework based on statistical approach to the finger joint USG image, which enables automatic localization of skin and bone regions, which are then used for localization of the finger joint synovitis area. The processing pipeline realizes the task in real-time and proves high accuracy when compared to annotation prepared by the expert.

High dimensional local binary patterns for facial expression recognition in the wild

Abstract: In this paper, we propose an automatic method of facial expressions recognition in static images using the high dimensional Local Binary Patterns (LBP). In this research some existing algorithms for face detection, facial landmarks localization, face normalization and recognition were combined and adopted for facial expressions classification. The novelty of the contribution lies in the application of the Random Frog algorithm used in the gene selection in the microarray experiments together with the high dimensional LBP as features of the Support Vector Machines (SVM) classifier used for the facial expressions classification. The proposed method was evaluated on the Static Facial Expressions in the Wild (SFEW) database, which contains the face images coming from movies and is very similar to real world scenarios. The performed tests show that the high dimensional LBP and features calculated from the regions around facial landmarks can achieve significant improvements over the state-of-the-art methods.

In Search of Truth: Analysis of Smile Intensity Dynamics to Detect Deception

Abstract: Detection of deceptive facial expressions, including estimating smile genuineness, is an important and challenging research topic that draws increasing attention from the computer vision and pattern recognition community. The state-of-the-art methods require localizing a number of facial landmarks to extract sophisticated facial characteristics. In this paper, we explore how to exploit fast smile intensity detectors to extract temporal features. This allows for real-time discrimination between posed and spontaneous expressions at the early smile onset phase. We report the results of experimental validation, which indicate high competitiveness of our method for the UvA-NEMO benchmark database.

Segmentation of finger joint synovitis in ultrasound images

Abstract: The arthritis disease may result from the long-lasting inflammation of the joint. The medical diagnosis assumes visual inspection of the joint ultrasonographic (USG) image, before any medical treatment takes place. Nowadays, the annotation of USG data is prepared manually by an expert physician, which is time-consuming and tiresome work. Therefore, in this work a system for automatic joint synovitis region detection for USG images of finger joints is introduced. The system enables accurate localization of skin border, detection of bones regions, calculation of joint center coordinates. All these information are indispensable for the procedure of automatic finger joint synovitis area localization. The accuracy of specific region detection was verified by comparison with manual annotations and proved high correlation, giving satisfactory result.

Smile veracity recognition using 3D texture features for image sequence processing

Abstract: Emotions are one of the most important cues of non-verbal communication, therefore are easily recognized by people. However, correct identification of intentions causes many problems, because telling apart the true emotion expression from the fake one is difficult. Therefore, there is a wide search nowadays for automatic techniques, which use computers to analyze behavior of people and learn the differences between spontaneous and posed emotional gestures. In this research we concentrate on the analysis of facial expressions in order to recognize between Duchenne (real) and fake smiles. Our approach treats the input movie as a dynamic texture and exploits LBP-TOP technique for its description. Additionally, the average facial image is removed from consideration as it is assumed, that only tiny changes differ the smile characters. The results obtained on UVA-NEMO dataset proved that it is possible to classify accurately between the spontaneous and posed smiles. Moreover, the influence of facial parts as well as changes due to a phase of smile are investigated.

A Machine-Learning Approach to the Automated Assessment of Joint Synovitis Activity

Abstract: Medical ultrasound imaging is an important tool in diagnosing and monitoring synovitis, which is an inflammation of the synovial membrane that surrounds a joint. Ultrasound images are examined by medical experts to assess the presence and progression of synovitis. Automating image analysis reduces the costs and increases the availability of the ultrasound diagnosis of synovitis and diminishes or eliminates subjective discrepancies. This article describes research that is concerned with the problem of the automatic estimation of the state of the activity of finger joint inflammation using the information that is present in ultrasonography imaging.

Real-time framework for tensor-based image enhancement for object classification

Abstract: In many practical situations visual pattern recognition is vastly burdened by low quality of input images due to noise, geometrical distortions, as well as low quality of the acquisition hardware. However, although there are techniques of image quality improvements, such as nonlinear filtering, there are only few attempts reported in the literature that try to build these enhancement methods into a complete chain for multi-dimensional object recognition such as color video or hyperspectral images. In this work we propose a joint multilinear signal filtering and classification system built upon the multi-dimensional (tensor) approach. Tensor filtering is performed by the multi-dimensional input signal projection into the tensor subspace spanned by the best-rank tensor decomposition method. On the other hand, object classification is done by construction of the tensor sub-space constructed based on the Higher-Order Singular Value Decomposition method applied to the prototype patters. In the experiments we show that the proposed chain allows high object recognition accuracy in the real-time even from the poor quality prototypes. Even more importantly, the proposed framework allows unified classification of signals of any dimensions, such as color images or video sequences which are exemplars of 3D and 4D tensors, respectively. The paper discussed also some practical issues related to implementation of the key components of the proposed system.

Fast Technique of Impulsive Noise Suppression in Color Images

Abstract: In this work a novel technique of impulsive noise removal in color images is proposed. The new approach is based on the calculation of costs of digital paths which link the central pixel of the processing window with its boundary. The minimum value of these costs serves as a measure of pixel impulsiveness. The output of the proposed filtering design is a weighted average of the central pixel and its robust estimate, calculated utilizing the measures of corruption assigned to pixels in the local neighborhood. The experiments performed on a set of standard color images revealed a very high effectiveness of the new filtering design, comparable with the most efficient methods known from the literature. Additionally, the new filter is extremely fast and therefore it can be applied in real time image enhancement scenarios.

Hybrid adaptation for detecting skin in color images

Abstract: It has been reported in many works on skin detection and segmentation from color images that skin color models suffer from low specificity and high variance of the skin color, and this problem can be addressed by conforming the skin model to a presented scene. Here, we introduce a new hybrid adaptation system which combines two strategies, namely (i) adaptation from a detected facial region and (ii) a self-adaptive scheme that creates a local model based on the response obtained using the global one. As a result of this hybrid adaptation, we obtain a local skin color model and we use it to extract seeds for the geodesic distance transform that determines the boundaries of skin regions. The results of our extensive experimental study confirm that the proposed algorithm outperforms several state-of-the-art methods, as well as our earlier adaptive skin detectors.

Smile Veracity Recognition Using LBP Features for Image Sequence Processing

Abstract: Correct recognition of emotion veracity exhibited in facial gestures is troublesome for people. Yet, there is a belief that computer systems are able to perceive some tiny changes correlated to veracity expression, invisible for people, and therefore are able to improve proper perception of emotions. This work addresses the problem of spontaneous and posed smile recognition and suggests two approaches. The first one uses the visual cues, in which the feature vector describes the content of evenly sampled frames in the movie by applying uniform local binary patterns. The second one, describes the video sequence with smile intensity information derived from information extracted from each frame, where the feature vector is built using simple statistical measures calculated from this data. These two systems and a combination of them are tested on UVA-NEMO database and proved to deliver encouraging results.

Application of the local similarity filter for the suppression of multiplicative noise in medical ultrasound images

Abstract: In this paper we address the problem of the reduction of multiplicative noise in digital images. This kind of image distortion, also known as speckle noise, severely decreases the quality of medical ultrasound images and therefore their effective enhancement and restoration is of vital importance for proper visual inspection and quantitative measurements. The structure of the proposed Pixel-Patch Similarity Filter (PPSF) is a weighted average of pixels in a processing block and the weights are determined calculating the sum of squared differences between the mean of a patch and the intensities of pixels of the local window at the block center. The structure of the proposed design is similar to the bilateral and non-local means filters, however we neglect the topographic distance between pixels, which decreases substantially its computational complexity. The new technique was evaluated on standard gray scale test images contaminated with multiplicative noise modelled using Gaussian and uniform distribution. Its efficiency was also assessed utilizing a set of simulated ultrasonographic images distorted by means of the Field II simulation software and real ultrasound images of a finger joint. The comparison with the state-of-the-art techniques revealed very high efficiency of the proposed filtering framework, especially for strongly degraded images. Visually, the homogeneous areas are smoother, while image edges and small details are better preserved. The experiments have shown that satisfactory results were obtained with patches consisting of only 9 samples belonging to a relatively small processing block of 7x7 pixels, which ensures low computational complexity of the proposed denoising scheme and allows its application in real-time image processing scenarios.

Automated recognition of facial expressions authenticity

Abstract: Recognition of facial expressions authenticity is quite troublesome for humans. Therefore, it is an interesting topic for the computer vision community, as the developed algorithms for facial expressions authenticity estimation may be used as indicators of deception. This paper discusses the state-of-the art methods developed for smile veracity estimation and proposes a plan of development and validation of a novel approach to automated discrimination between genuine and posed facial expressions. The proposed fully automated technique is based on the extension of the high-dimensional Local Binary Patterns (LBP) to the spatio-temporal domain and combines them with the dynamics of facial landmarks movements. The proposed technique will be validated on several existing smile databases and a novel database created with the use of a high speed camera. Finally, the developed framework will be applied for the detection of deception in real life scenarios.

Biomedical image colorization using pixel membership propagation

Abstract: In the paper we present a new algorithm of biomedical image colorization based on distance transformation and modified bilateral filtering approach. The method utilizes the scribbles inserted by the user to properly cover the image regions with desirable colors. We present the idea of our algorithm, explain the role of tunable parameters and provide some examples of biomedical image colorization using our approach.