Alberto Rosales

Adaptive Vector Directional Filters to Process Multichannel Images

We present a novel algorithm that can suppress impulsive noise in video colour sequences. It uses order statistics, and directional and adaptive processing techniques.

Fuzzy 3D filter for color video sequences contaminated by impulsive noise

A novel fuzzy 3D filter designed to suppress impulsive noise in color video sequences is proposed. In contrast to other state-of-the-art algorithms, the proposed approach employs the sequence data of the three RGB channels, analyzes eight fuzzy gradient values for each of the eight directions, and processes two temporal neighboring frames concurrently. Numerous simulation results confirm that this novel 3D framework performs well in terms of objective criteria (PSNR, MAE, NCD, and SSIM) and the more subjective measure of human vision in the different color sequences. An efficiency analysis of several promising 3D algorithms was performed on a DSP; computation times for various techniques are presented.

Impulsive noise suppression and analysis in color imaging

We present the analysis and simulation results for some modifications of the vectorial color imaging procedures those use at the second stage of magnitude processing the different order statistics filters. The technique of non-parametric filtering is presented and investigated in this paper too. For unknown functional form of noise density estimated from the observations we use the gray scalar filters to provide the reference vectors needed to realize the calculations. The performances of the traditional order statistics algorithms such as, median, Vector Median, alfa-trimmed mean, Wilcoxon, other order statistics M KNN are analyzed in the paper. For comparison analysis of the color imaging we use the following criterions: MAE; PSNR; MCRE; NCD Numerous simulation results which characterize the impulsive noise suppression and fine detail preservation are presented in the paper using different test images) such as: Lena, Mandrill, Peppers, etc. (256x256, 24 bits, RGB space). The algorithms those demonstrated good performance results have been applied to process the video sequences: “Miss America”, “Flowers” and Foreman” corrupted by impulsive noise. The results of the simulations presented in the paper show differences in color imaging by mentioned filtering technique and help to choose the filter that can satisfy to several criterion at dependence on noise level value.

Order Statistics - Fuzzy Approach in Processing of Multichannel Images and Video Sequences

There exist different applications of the image processing, such as medical imaging, high definition television, virtual reality, remote sensing, ultrasound and radar imaging, etc. In these applications, it is necessary to restore an image (or frames of video sequence) and decrease a noise influence exploiting the filtering algorithms that form a part of a general image processing system. The images are corrupted by noise, in sensors employed or maybe, during signal transmission. Also, several kinds of noises are produced by natural phenomena (atmospheric, scattering, interference, etc.). Usually, real noises are described by different models, there exist impulsive, additive and multiplicative (speckle) ones. So, the image pre-processing efficient scheme should be one of important part in any vision application permitting to suppress a noise, saving the image performances, such as, edge and fine features preservation, and also the chromaticity properties for the multichannel (multispectral) images. This demands to have several efficient filtering schemes, which depend on noise type and priory information, in a pre-processing stage of image or video sequence processing system. The main objective of present chapter is to exhibit several justified approaches in restoration of the images and video sequences, which are usually affected by noise of different nature, which can be efficiently used in different applications of the multichannel (multispectral) images and sequences. Here, multispectral image is defined in such a way, where each a pixel is represented by a number of channels that carry out information about its spectral content. Multispectral images span the domain of images from conventional three-channel colour images to hyperspectral imagery with hundred of bands/channels used in remote sensing applications, medicine, spectrometry, etc. In literature, there exist a lot of algorithms that process two dimensional (2D) images (Franke et al., 2000); (Russo & Ramponi, 1996); (Schulte et al., 2006, 2007a, 2007b, 2007c); (Shaomin & Lucke, 1994); (Nie & Barner, 2006); (Morillas et al., 2005, 2006, 2008a, 2008b, 2009); (Camarena et al., 2008, 2010); (Ma et al., 2007); (Amer & Schroder, 1996); (Xu, 2009). We compare the proposed 2D fuzzy framework with recently presented 2D-INR filter based on fuzzy logic (Schulte et al., 2007b), where a noise is detected preserving the fine features and edges in an image. Also, other promising classes of 2D processing algorithms are employed as comparative ones: 2D-AMNF, 2D-AMNF2 (Adaptive Multichannel Filters)(Plataniotis & Androutsos et al., 1997); (Plataniotis & Venetsanopoulos, 2000); 2D7

Real-time color imaging using the vectorial order statistics filters

Color image and video sequence restoration and improvement are complicated due to presence of various kinds of random noise. Impulsive noise is introduced by acquisition or broadcasting errors into communication channels. Non linear filters can provide good performance in terms of the signal-to-noise ratio in different levels of corruption as soon as minimum error chromaticity and minimum perceptual error. This paper presents the capability and real-time processing features of several processing techniques such as “directional processing”, “non parametric approaches” and “order statistics” filters. Some of such the filters were: Median Filter (MF), Vector Median Filter (VMF), -Trimmed Mean Filter (ATMF), Generalized Vector Directional Filter (GVDF), Adaptive Multichannel Non Parametric Filter (AMNF), Median M-type K-Nearest Neighbour (MM-KNN) filter, Wilcoxon M-type K-Nearest Neighbour (WM-KNN) filter, Ansari-Bradley-Siegel-Tukey M-Type K-Nearest Neighbor (ABSTM-KNN) filter, etc. Extensive simulations in reference color RGB images “Lena”, “Mandrill”, “Peppers” and QCIF format video sequences (Miss America, Flowers and Foreman) have demonstrated that the proposed filters consistently can outperform the known nonlinear filters. The used performance criteria in color imaging were the traditional ones: PSNR, MAE and other specific for color imaging, NCD and MCRE. The real-time implementation of image filtering was realized on the DSP TMS320C6701. The processing time of proposed filters includes the duration of data acquisition, processing and store data. We simulated impulse corrupted color image QCIF sequences to demonstrate that some of the proposed and analyzing filters potentially could provide on line processing to quality video transmission of the images.

Impulse Denoising Using Fuzzy and Directional Processing on a DSP

This article presents novel fuzzy and directional techniques in denoising colour images contaminated by impulsive random noise. Novel approach has demonstrated excellent performance in image denoising and feature image preservation. Real-Time analysis is realized on a Digital Signal Processor (Texas Instruments).

LSM static signs recognition using image processing

Object recognition is a widely field in artificial vision application, because now the machines are intended to become autonomous. This article presents the methodology for recognizing objects in an image, tecniques used are: segmentation, feature extraction and classification object within the image. Fuzzy c-means algorithm was used for segmentation, which is a fuzzy classification algorithm in which a data can belong to multiple groups in different degree of membership. For feature extraction were used Hu moments as a geometrical descriptors, which are a mathematical tool that provides seven moments that identify geometric features of the objects, main characteristics of Hu moments is its invariance to rotation, scaling and translation. Finally, the geometric features that provide the seven moments are used as input to a classifier, delivering results: these moments are used to identify the signs of the alphabet of the Mexican Sign Language (LSM).

Video Colour Denoising Using Fuzzy and Directional Techniques

Different classes of filters have been proposed for removing noise from gray scale and colour images (Astola & Kuosmanen, 1997; Bovik, 2000; Kotropoulos & Pitas, 2001). They are classified into several categories depending on specific applications. Linear filters are efficient for Gaussian noise removal but often distort edges and have poor performance against impulsive noise. Nonlinear filters are designed to suppress noise of different nature, they can remove impulsive noise and guarantee detail preservation. Rank order based filters have received considerable attention due to their inherent outlier rejection and detail preservation properties (Astola & Kuosmanen, 1997; Bovik, 2000; Kotropoulos & Pitas, 2001, Plataniotis & Venetsanopoulos, 2000). In the last decade, many useful colour processing techniques based on vector processing have been investigated due to the inherent correlation that exists between the image channels compared to traditional component-wise approaches (Plataniotis & Venetsanopoulos, 2000). The fuzzy filters are designed by fuzzy rules to remove noise and to provide edge and fine detail preservation (Russo & Ramponi, 1994). The fuzzy filter depends on the fuzzy rules and the defuzzification process, which combines the effects of applied rules to produce an only output value (Russo & Ramponi, 2004, Schulte et al., 2007). The vector directional filters employ the directional processing taking pixels as vectors, and obtaining the output vector that shows a less deviation of its angles under ordering criteria in respect to the other vectors (Trahanias & Venetsanopoulos, 1996). This chapter presents the capability features of Fuzzy Directional (FD) filter to remove impulse noise from corrupted colour images (Ponomaryov, et al., 2010). The FD filter uses directional processing, where vectorial order statistics are employed, and fuzzy rules that are based on gradient values and angle deviations to determine, if the central pixel is noisy or present local movement. Simulation results in colour images and video sequences have shown that the restoration performance is better in comparison with other known filters. In Addition, we present the Median M-Type L(MML) filter for the removal of impulsive noise in gray-scale and colour image processing applications (Gallegos-Funes et al., 2008, ToledoLopez et al., 2008). The proposed scheme is based on modification of Lfilter that uses the MM (Median M-type) -estimator to calculate the robust point estimate of the pixels within the filtering window. The proposed filter uses the value of the central pixel within the filtering window to provide the preservation of fine details and the redescending M-

Multichannel and Multispectral Image Restoration Employing Fuzzy Theory and Directional Techniques

Satellite, Radar, Medical, High Definition Television, Virtual Reality, Electron Microscopy, etc. are some of the multispectral and multichannel image processing applications that need the restoration and denoising procedures, all these applications are part of a general image processing system scheme. All these images usually are corrupted by noise due to sensors influence, during transmission of the signals, or noise produced by environmental phenomena; these types of noise can be modelled as impulse noise, Gaussian noise, multiplicative (speckle) noise, among other. As a consequence, the application of image preprocessing (denoising) efficient schemes is a principal part in any computer vision application and includes reducing image noise without degrading its quality, edge and small fine details preservation, as well as colour properties. The main objective of present work is to expose the justified novel approaches in restoration in denoising multichannel and multispectral images that can be used in mentioned applications. There exist in literature a lot of algorithms that process two dimensional (2D) images using fuzzy and vectorial techniques (Franke et al. (2000); Russo & Ramponi (1996); Schulte & De Witte & Nachtegael et al. (2007); Shaomin & Lucke (1994); Schulte & De Witte & Kerre (2007); Nie & Barner (2006); Morillas et al. (2006); Schulte & Morillas et al. (2007); Morillas et al. (2007; 2008); Camarena et al. (2008); Morillas et al. (2008; 2005); Ma et al. (2007); Amer & Schroder (1996)). The first approach presented above works in impulsive denoising scenario in 2D colour images. This filter uses fuzzy and directional robust technics to estimate noise presence in the sample to be processed in a local manner, employing fuzzy rules, the algorithm is capable to be adapted depending of quantity of noise detected agree to fuzzy-directional values computed under these fuzzy rules. We compare the proposed 2D framework (FCF – 2D) with recently presented 2D INR filter based on fuzzy logic (Schulte & Morillas et al., 2007), this algorithm detects the noise and preserves the fine details in the multichannel image. There are other 2D algorithms that are also implemented and used in this work as comparative ones: AMNF, AMNF2 (Adaptive Multichannel Filters)(Plataniotis & Androutsos et al. (1997); Plataniotis & Venetsanopoulos (2000)); AMNIF (Adaptive Multichannel Filter using Influence Functions) (Ponomaryov & Gallegos et al. (2005); Ponomaryov et al. (2005)); GVDF (Generalized Vector Directional Filter) (Trahanias & Venetsanopoulos, 1996); CWVDF (Centered Weighted Vector

Order statistics vector directional filters to process multichannel images

Novel algorithms to suppress impulsive noise in 3D color images are presented. Some of them have demonstrated effectiveness in preservation of inherent characteristics in the images, such as, edges, details and chromaticity. Robust algorithm that uses order statistics, vector directional and adaptive methods is developed applying three-dimensional video processing permitting suppressing a noise. Several algorithms are extended from 2D to 3D for video processing. The results show that proposed Video Adaptive Vector Directional filter outperforms the video versions of Median M-type K-Nearest Neighbour, Vector Median, Generalized Vector Directional, K-Nearest Neighbour, α-trimmed Mean, and Median filters. All of them evaluated during simulation using PSNR, MAE and NCD criteria.