Branimir Reljin

Adaptive Content-Based Image Retrieval with Relevance Feedback

Retrieval of images, based on similarities between feature vectors of querying image and those from database, is considered. The searching procedure was performed through the two basic steps: an objective one, based on the Euclidean distances and a subjective one based on the users relevance feedback. Images recognized from user as the best matched to a query are labeled and used for updating the query feature vector through a RBF (radial basis function) neural network. The searching process is repeated from such subjectively refined feature vectors. In practice, several iterative steps are sufficient, as confirmed by intensive simulations

Extremely Flat-Top Windows for Harmonic Analysis

The window class, which is generated by multiple time-convolution of weighted-cosine windows, is presented. It is shown that after a convolution of known parent windows, the resultant convoluted (CON) window exhibits high side-lobe attenuation that is capable of suppressing long-range leakage. Moreover, using the expressions describing an error due to the short-range leakage, the optimization procedure was applied to adjust the coefficients of parent windows in order to obtain, as flat as possible, the main lobe of the CON window. As a result, the new window class having both an extremely flat-top (EFT) main lobe and high side-lobe attenuation was generated. Moreover, new windows exhibit faster decaying side lobes than parent windows. The efficiency of EFT windows in high-accuracy harmonic analysis was demonstrated through computer simulations

Multifractal analysis of gray-scale images

The basis of fractal (and multifractal) theory and its application to image analysis is presented. In the multifractal approach the image is described by a measure /spl mu/, or by capacities. Through the multifractal spectrum f(/spl alpha/) both local and global information of the image regularity can be derived. By using a different fractal dimension different parts of analyzed images can be detected, without loosing or introducing any information. This feature is very useful for a global image analysis, edge detection, segmentation, texture classification, etc. The applicability of the multifractal approach to image analysis is verified through different medical images.

H.264/AVC video compressed traces: multifractal and fractal analysis

Publicly available long video traces encoded according to H.264/AVC were analyzed from the fractal and multifractal points of view. It was shown that such video traces, as compressed videos (H.261, H.263, and MPEG-4 Version 2) exhibit inherent long-range dependency, that is, fractal, property. Moreover they have high bit rate variability, particularly at higher compression ratios. Such signals may be better characterized by multifractal (MF) analysis, since this approach describes both local and global features of the process. From multifractal spectra of the frame size video traces it was shown that higher compression ratio produces broader and less regular MF spectra, indicating to higher MF nature and the existence of additive components in video traces. Considering individual frames (I, P, and B) and their MF spectra one can approve additive nature of compressed video and the particular influence of these frames to a whole MF spectrum. Since compressed video occupies a main part of transmission bandwidth, results obtained from MF analysis of compressed video may contribute to more accurate modeling of modern teletraffic. Moreover, by appropriate choice of the method for estimating MF quantities, an inverse MF analysis is possible, that means, from a once derived MF spectrum of observed signal it is possible to recognize and extract parts of the signal which are characterized by particular values of multifractal parameters. Intensive simulations and results obtained confirm the applicability and efficiency of MF analysis of compressed video.

Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine Wigner-Ville distribution and Haar wavelet lifting

Having in mind the availability of electronic stethoscopes, phonocardiograms (PCGs) have become popular for cardiovascular functionality monitoring and signal processing applications. Detection of fundamental heart sounds (HSs), S1s and S2s, is considered to be a crucial step in PCG analysis. Electrocardiogram (ECG), noted as a reference signal, is often synchronously recorded in order to simplify the S1/S2 detection process. Nevertheless, electronic stethoscopes are frequently used without additional ECG equipment. We propose a new algorithm for automatic fundamental HSs detection via: joint time-frequency representation based on pseudo affine Wigner-Ville distribution (PAWVD), Haar wavelet lifting scheme (Haar-LS), normalized average Shannon energy (NASE) and autocorrelation. The performance of the proposed algorithm was calculated on both normal (50) and pathological (75) PCG recordings, eight seconds long each, contributed by 125 different pediatric patients. The algorithm showed relatively high recall (90.41%) and precision (96.39%) rates of S1/S2 detection procedure in a variety of PCG signals, without ECG as a reference. Furthermore, it indicated the ability to overcome splitting within the S1/S2 heart sounds.

Local contrast enhancement in digital mammography by using mathematical morphology

An algorithm for both local contrast enhancement and background texture suppression in digital mammographic images is proposed. The algorithm is based on mathematical morphology applied to gray-scale image processing. Several examples demonstrate the efficiency of the new algorithm in enhancing the details, object extraction and detection of microcalcifications in digital mammograms.

Classification of Prolapsed Mitral Valve versus Healthy Heart from Phonocardiograms by Multifractal Analysis

Phonocardiography has shown a great potential for developing low-cost computer-aided diagnosis systems for cardiovascular monitoring. So far, most of the work reported regarding cardiosignal analysis using multifractals is oriented towards heartbeat dynamics. This paper represents a step towards automatic detection of one of the most common pathological syndromes, so-called mitral valve prolapse (MVP), using phonocardiograms and multifractal analysis. Subtle features characteristic for MVP in phonocardiograms may be difficult to detect. The approach for revealing such features should be locally based rather than globally based. Nevertheless, if their appearances are specific and frequent, they can affect a multifractal spectrum. This has been the case in our experiment with the click syndrome. Totally, 117 pediatric phonocardiographic recordings (PCGs), 8 seconds long each, obtained from 117 patients were used for PMV automatic detection. We propose a two-step algorithm to distinguish PCGs that belong to children with healthy hearts and children with prolapsed mitral valves (PMVs). Obtained results show high accuracy of the method. We achieved 96.91% accuracy on the dataset (97 recordings). Additionally, 90% accuracy is achieved for the evaluation dataset (20 recordings). Content of the datasets is confirmed by the echocardiographic screening.

Neural network for finding optimal path in packet-switched network

Neural networks are very good candidates for solving different ill-defined problems, due to their high computational speed and the possibility of working with uncertain data. Among others, they represent an efficient tool for solving constrained optimization problems. Under appropriate assumptions, routing in packet-switched networks may be considered as an optimization problem, more precisely, as a shortest-path problem, where the Hopfield type neural network exhibits very good performance. An efficient neural network shortest-path algorithm, inspired by the Hopfield network, is suggested. The routing algorithm suggested is designed to find the shortest path but also it takes into account packet-loss avoidance. The applicability of the proposed model is demonstrated through computer simulations for different full-connected networks with both symmetrical and non-symmetrical links.

Application of multifractal analysis on microscopic images in the classification of metastatic bone disease

The paper considers the method, based on multifractal (MF) analysis, for classifying the shape of tissue cells from microscopis images, identifying the primary cancer in cases of metastasis bone disease. Diagnosis of primary cancer is of great importance, because further treatment depends on how successful and accurate that diagnosis is. This method can be applied as an additional and objective tool in primary cancer diagnosis, as well as in decreasing of the subjective factor and error probability. The method is tested over a large number (1050) of clinical cases from the Institute of Pathology, University of Belgrade. The results of computer-aided analysis of images have been presented and discussed.

Breast cancer evaluation by fluorescent dot detection using combined mathematical morphology and multifractal techniques.

BackgroundFluorescence in situ hybridization (FISH) is very accurate method for measuring HER2 gene copies, as a sign of potential breast cancer. This method requires small tissue samples, and has a high sensitivity to detect abnormalities from a histological section. By using multiple colors, this method allows the detection of multiple targets simultaneously. The target parts in the cells become visible as colored dots. The HER-2 probes are visible as orange stained spots under a fluorescent microscope while probes for centromere 17 (CEP-17), the chromosome on which the gene HER-2/neu is located, are visible as green spots.MethodsThe conventional analysis involves the scoring of the ratio of HER-2/neu over CEP 17 dots within each cell nucleus and then averaging the scores for a number of 60 cells. A ratio of 2.0 of HER-2/neu to CEP 17 copy number denotes amplification. Several methods have been proposed for the detection and automated evaluation (dot counting) of FISH signals. In this paper the combined method based on the mathematical morphology (MM) and inverse multifractal (IMF) analysis is suggested. Similar method was applied recently in detection of microcalcifications in digital mammograms, and was very successful.ResultsThe combined MM using top-hat and bottom-hat filters, and the IMF method was applied to FISH images from Molecular Biology Lab, Department of Pathology, Wielkoposka Cancer Center, Poznan. Initial results indicate that this method can be applied to FISH images for the evaluation of HER2/neu status.ConclusionsMathematical morphology and multifractal approach are used for colored dot detection and counting in FISH images. Initial results derived on clinical cases are promising. Note that the overlapping of colored dots, particularly red/orange dots, needs additional improvements in post-processing.