Raul Malutan

Speckle noise removal in ultrasound images using sparse code shrinkage

The paper proposes a method for ultrasound image denoising by using a classical signal processing method, i.e. Independent Component Analysis. The main idea is to process ultrasound images by the sparse code shrinkage algorithm based on ICA. We use the FastICA algorithm to estimate the inverse of the unknown mixing matrix and then apply the shrinkage operator for each determined independent component. The sparse code shrinkage method is compared with other speckle noise filtering algorithms and the results obtained show that sparse code shrinkage is a good method for multiplicative noise reduction in both test images and ultrasound images.

FPGA technology and parallel computing towards automatic microarray image processing

Automation, computational time and cost are open subjects in microarray image processing. The present paper proposes image processing techniques together with their implementations in order to eliminate the shortcomings of the existing software platforms for microarray image processing: user intervention, increased computational time and cost. Thus, for each step of microarray image processing, application-specific hardware architectures are designed aiming algorithms parallelization for fast processing. Computational time is estimated and compared with state of the art approaches. The proposed hardware architectures integrated inside microarray scanners deliver microarray image characteristics in an automated manner, excluding the need of an additional software platform. The FPGA technology was chosen for implementation, due to its parallel computation capabilities and ease of reconfiguration.

Two way clustering of microarray data using a hybrid approach

The Microarray technique is rather powerful, as it allows to test up thousands of genes at a time, but this produces an overwhelming set of data files containing huge amounts of data, which is quite difficult to pre-process, separate, classify and correlate for interesting conclusions to be extracted. Modern machine learning, data mining and clustering techniques based on information theory, are needed to read and interpret the information contents buried in those large data sets. Independent Component Analysis method can be used to correct the data affected by corruption processes or to filter the uncorrectable one and then clustering methods can group similar genes or classify samples. In this paper a hybrid approach is used to obtain a two way unsupervised clustering for a corrected microarray data.

Patch based descriptors for iris recognition

In recent years, local texture analysis methods have gained increasing attention in many areas of image processing and computer vision. The current paper deals with iris features extraction, based on dense descriptors. A dense descriptor captures the local details, pixel by pixel over the complete image. Three different techniques were employed: Local Binary Pattern, Local Phase Quantization and Differential Excitation in order to provide both spatial and frequency information. To evaluate the proposed system, experiments were performed on the UPOL database, by using a linear SVM classification scheme. The results show that the iris micro-texture patterns such as crypts, furrows or pigment spots can be well characterized by patched based descriptors.

Hardware implementation of microarray image segmentation

The present paper proposes an acquisition system for microarray image on an FPGA based platform, together with a hardware implementation of image segmentation for cDNA micro-array images. The hardware implementation takes advantage of parallel computation capabilities offered by FPGA technology.

Half iris biometric system based on HOG and LIOP

Automatic iris recognition is becoming increasingly important technique for identity management and hence security. In the computer vision domain and mainly in the image recognition applications, the possibility to compare affined images, which could be distinguished just through small differences, is highly important. Using local image descriptors, similar images could be identified, although they are not part of the same scene or they have a changed parameter. Implemented systems show that HOG (Histogram of Oriented Gradients) and LIOP (Local Intensity Order Pattern) descriptors are promising for human recognition based on iris texture. Experimental results are reported on two public databases: UPOL and CASIA_V1.

A multiplicative gradient-based anisotropic diffusion approach for speckle noise removal

We propose a novel directional diffusion method for speckle noise removal that uses the multiplicative gradient as an edge detector and operates on a moving orthonormal basis issued by a structure tensor based-approach and stochastic modelling. The method has good speckle removal and edge preservation properties and it can be used for filtering ultrasound, optical coherence tomography medical images or other types of images degraded by speckle, such as those acquired in Synthetic Aperture Radar (SAR) imaging systems. The effectiveness of our approach in speckle removal applications is demonstrated experimentally on computer generated and on real ultrasound images through comparisons with state-of-the-art Partial Differential Equations (PDE) and non-PDE-based methods.

Hybridization Dynamics Compensation in Microarray Experiments

The dynamics of the hybridization process in microarrays experiments is complex as thermodynamics factors influencing molecular interaction are still fields of important research and their effects are not fully taken into account in the estimation of genetic expression. In this paper an adaptive fitting is used to predict and regress microarray expression levels on a specific test probe to common thermodynamic conditions.

Oligonucleotide Microarray Probe Correction by FixedPoint ICA Algorithm

Oligonucleotide Microarrays have become powerful tools in genetics, as they serve as parallel scanning mechanisms to detect the presence of genes using test probes. The detection of each gene depends on the multichannel differential expression of perfectly matched segments against mismatched ones. This methodology posse some interesting problems under the point of view of Genomic Signal Processing, as test probes express themselves in rather different patterns, not showing proportional expression levels for most of the segment pairs, as it would be expected. The method proposed in this paper consists in isolating gene expressions showing unexpected behavior using independent component analysis.

Iris indexing based on local intensity order pattern.

In recent years, iris biometric systems have increased in popularity and have been proven that are capable of handling large-scale databases. The main advantage of these systems is accuracy and reliability. A proper iris patterns classification is expected to reduce the matching time in huge databases. This paper presents an iris indexing technique based on Local Intensity Order Pattern. The performance of the present approach is evaluated on UPOL database and is compared with other recent systems designed for iris indexing. The results illustrate the potential of the proposed method for large scale iris identification.