Venu gopala rao - Academia.edu (original) (raw)

Papers by Venu gopala rao

Ain Shams Engineering Journal, 2017

Induction motors consumes 90% of total power consumed by industries due to large scale utilisatio... more Induction motors consumes 90% of total power consumed by industries due to large scale utilisation. Even though these motors are rugged in structure, they often face unexpected failure due to long usage without maintenance. Bearing failure is a major problem among various faults, which cause catastrophic damage to machine when unnoticed at incipient stage. So the bearing faults in induction machines should be continuously monitored. Motor current signature analysis (MCSA) has become popular for detection and localisation of these faults and has attracted concentration of many researchers. In this paper stator current is monitored by means of frequency spectral subtraction using various wavelet transforms to suppress dominant components. The spectral subtraction using discrete wavelet transform (DWT), stationary wavelet transform (SWT) and wavelet packet decomposition (WPD) is performed and a comparative analysis is carried out by means of different fault indexing parameters. The proposed topology is examined using 2.2 kW induction machine test bed.

International Journal of Engineering & Technology, 2018

The image classification is a classical problem of image processing, computer vision and machine ... more The image classification is a classical problem of image processing, computer vision and machine learning fields. In this paper we study the image classification using deep learning. We use AlexNet architecture with convolutional neural networks for this purpose. Four test images are selected from the ImageNet database for the classification purpose. We cropped the images for various portion areas and conducted experiments. The results show the effectiveness of deep learning based image classification using AlexNet.

2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN), 2015

ABSTRACT Ionospheric time delay variations are highly variable and random in the low latitude Ind... more ABSTRACT Ionospheric time delay variations are highly variable and random in the low latitude Indian region. It is a key responsible parameter for the range error in Global Positioning System (GPS) ranging signals which is proportional to the total electron content (TEC). Dual frequency GPS receiver at KL University, Vaddeswaram (16.31° N, 80.37° E), India (falls under the transition zone of the Equatorial Ionization Anomaly in low latitude) is considered in the analysis. An Auto Regressive Moving Average (ARMA) model is implemented for short term forecasting of the VTEC (Vertical TEC) values. Three Geomagnetic storms occurred in the current solar maximum period (2013-2014) are considered to test the performance of ARMA model. The forecasted VTEC values are compared with original VTEC the values and IRI models. The forecasted results indicate that ARMA model would be useful to set up an early warning system of ionospheric disturbances.

Defence Science Journal, 2015

Acquisition is a most important process and a challenge task for identifying visible satellites, ... more Acquisition is a most important process and a challenge task for identifying visible satellites, coarse values of carrier frequency, and code phase of the satellite signals in designing software defined Global positioning system (GPS) receiver. This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Fourier transform (ssFFT). The proposed algorithm exploits the recently developed sparse FFT (or sparse IFFT) that computes in sub-linear time. Further it uses the property of fourier transforms (FT): Aliasing a signal in the time domain corresponds to sub-sampling it in the frequency domain, and vice versa. The ssFFT is an FFT algorithm that computes sub-sampled version of the data by an integer factor 'd', and hence, the computational complexity is proportionately reduced by a factor of 'd log d' compared to conventional FFT-based algorithms for any length of the input GPS signal. The simulation results show that the proposed ssFFT based GPS acquisition computation is 8.5571 times faster than the conventional FFT-based acquisition computation time. The implementation of this method in an FPGA provides very fast processing of incoming GPS samples that satisfies real-time positioning requirements.

Liquid Crystals Today, 2015

Transition temperatures in N-(p-n-heptyloxybenzylidene)-p-n-alkyloxy anilines, 7O.Om liquid cryst... more Transition temperatures in N-(p-n-heptyloxybenzylidene)-p-n-alkyloxy anilines, 7O.Om liquid crystalline compounds are computed from optical textures using Multispectral Correlations Technique in image processing. The statistical parameters like mean, standard deviation and entropy of textures as a function of temperature are computed from the image processing technique. These results show abrupt changes as a function of temperature, indicating the phase transition of the 7O.Om samples. The MATLAB simulation results are in good agreement with DSC results and the proposed methodology is one of the techniques in giving reliable and suitable technique to identify transition temperatures at low cost.

International Journal of Engineering & Technology, 2018

The modern signal and image processing deals with large data such as images and this data deals w... more The modern signal and image processing deals with large data such as images and this data deals with complex statistics and high dimensionality. Sparsity is one powerful tool used signal and image processing applications. The mainly used applications are compression and denoising. A dictionary contains information of the signals in the form of coefficients. Recently dictionary learning has emerged for efficient representation of signals. In this paper we study the image compression using both analytical and learned dictionaries. The results show that the effectiveness of learned dictionaries in the application of image compression.

Glaucoma is a common cause of blindness amongst retinal diseases with 13% of the cases getting af... more Glaucoma is a common cause of blindness amongst retinal diseases with 13% of the cases getting affected. The changes happen in retinal structure that gradually results in loss of peripheral vision and in the end leads to blindness if it is not treated in time. No cure is present for Glaucoma, however, its earlier detection as well as treatment helps in preventing loss of vision. Because the procedure of manual diagnosis is expensive as well as error-prone, effort has been made toward automated detection of Glaucoma in its earlier stage [1]. Glaucoma refers to a set of eye diseases that are related to concurrent functional failures in visual field. Changes in structure are symptomized by a slow diminishing neuro-retinal rim denoting degeneration of axons as well as astrocytes of the Optic Nerve. Because any lost capacity of the optic nerve is not recoverable, earlier detection as well as care is crucial for patients to retain their vision. Two major kinds of Glaucoma include: 1) Primary Open Angle Glaucoma (POAG) as well as (ii) Angle Closure Glaucoma (ACG). The former progresses in a slow manner and at times without any significant loss in vision for several years. Treatment involves medication if an early diagnosis is made. The latter requires surgery as a small portion of the outer edge of the iris is to be removed. In latest studies, a lot effort has been put into automatic diagnosis of glaucoma on the basis of computer vision. The structure of glaucoma analysis systems is dependent on the types of image cue and image modality utilized. Amongst structural image cues learnt for diagnosing glaucoma, cues based on optic discs as well as cups are significant. Optic discs are situated near ganglion nerve fibres congregating in the retina. Optic cup is where the depression occurs in the optic disc from where the fibre comes out of the retina through the Optic Nerve Head (ONH). The borders of the cup and disc structures are required to be found since it helps the assessment of glaucoma cues like disc and cup asymmetry and high Cup-to-Disc Ratio (CDR), described as the ratio between vertical cup diameter to vertical disc diameter. Value of CDR is assessed by planimetry from color fundus images after outlining the optic discs and cups physically. As the process of manual annotation of cup and disc for every image involves Glaucoma is a common cause of blindness and it is increasingly becoming more severe when taking into consideration the aging population. As the dead retinal nerve fibres are not healable, earlier detection as well as prevention of glaucoma is crucial. Resilient and automatic mass-screening will assist in the extension of symptoms-free life for the patients. A new automatic appearance-based glaucoma classification system which does not rely on segmentation-based measures is suggested here. It employs image fusion, which refers to the procedure of fusing images obtained from various sources for acquiring improved situational awareness. The goal of fusion of source images is the combination of highly relevant data from sources into one composite image. Genetic Algorithm (GA) is utilized for features selection. Features extraction methods utilized are Discrete Wavelet Transform (DWT) utilized for multiresolution fusion as well as Local Binary Patterns (LBP) for texture features. Outcomes prove that the suggested model attains excellent glaucoma classification.

Received May 28, 2021 Revised Aug 31, 2021 Accepted Sep 13, 2021 In automotive vehicles, radar is... more Received May 28, 2021 Revised Aug 31, 2021 Accepted Sep 13, 2021 In automotive vehicles, radar is the one of the component for autonomous driving, used for target detection and long-range sensing. Whereas interference exists in signals, noise increases and it effects severely while detecting target objects. For these reasons, various interference mitigation techniques are implemented in this paper. By using these mitigation techniques interference and noise are reduced and original signals are reconstructed. In this paper, we proposed a method to mitigate interference in signal using deep learning. The proposed method provides the best and accurate performance in relate to the various interference conditions and gives better accuracy compared with other existing methods.

International Journal of Engineering & Technology, 2018

This paper focuses on reducing the processing time of software GPS receiver using sub-sampling te... more This paper focuses on reducing the processing time of software GPS receiver using sub-sampling techniques. As the GPS signals are wide band signals, sampling frequency is very high. Sub-sampling enables to reduce time for processing. From the simulation results, it is observed that the sampling frequency can be reduced up to 2.5 MHz without loss of tracked signal. The processing time is reduced for software GPS receiver after sub-sampling. The overall reduction in processing time is from 3.456647 sec to 2.15946 sec respectively for sampling frequency 5 MHz , 2.5 MHz. Thus time saved is 37% of the original one.

Liquid Crystals, 2014

ABSTRACT Textural analysis is done in the case of the thermotropic liquid crystal (LC), 4-heptylo... more ABSTRACT Textural analysis is done in the case of the thermotropic liquid crystal (LC), 4-heptyloxybenzylidene-4′-nonyloxyaniline, 7O.O9, using a polarising microscope attached with a hot stage with a high-resolution camera. Natural images are highly structured: their pixels exhibit strong dependencies and carry important information about the structure of the objects. In this article, we consider the structural similarity index measure parameter computed as a function of the temperature. The results exhibit abrupt changes with temperature showing different liquid crystalline phases. This statistical image analysis is compared with the differential scanning calorimeter data and good agreement was found. The proposed methodology is very sensitive and reliable technique to identify the LC phases.

2013 Annual IEEE India Conference (INDICON), 2013

This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Four... more This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Fourier transform (ssFFT) and thresholding. The proposed algorithm exploits the recently developed sparse FFT (or sparse IFFT) that computes in sublinear time. Further it uses the property of Fourier transforms (FT): Aliasing a signal in the time domain is equivalent to subsampling it in the frequency domain, and vice versa. The ssFFT is an FFT algorithm that computes with sub sampling factor `d', and hence the computational complexity is reduced by a factor of `d logd', compared to conventional FFT based algorithms for any length of the input GPS signal. The simulation results show that the proposed ssFFT based GPS acquisition computation time is 8.5571 times faster than that conventional FFT based acquisition computation. A clean spike is produced by thresholding the noisy signal.

2013 IEEE International Conference on Signal Processing, Computing and Control (ISPCC), 2013

ABSTRACT The development of software based GNSS receivers is being rapidly revolutionized in sate... more ABSTRACT The development of software based GNSS receivers is being rapidly revolutionized in satellite based navigation applications. In view of commencement of new satellite/ground based navigation systems such as Indian Regional Navigations Systems (IRNSS), GPS Aided Geo Augmented Navigation (GAGAN), China's COMPAS and pseduolites etc., the receiver technology is to be updated efficiently for high positional accuracy requirements under noisy environments. The main modules of software GPS receiver contain acquisition, tracking and position computations. Among them, acquisition is very important process for identifying satellites, which is based on spread spectrum technology. In this paper, Goertzel and Cooley-tukey FFT GPS acquisition algorithms are implemented for GPS L1 signals. The simulations results indicate that Cooley-tukey FFT GPS acquisition algorithm (Acquisition time: 18.32 seconds) is performed well as compared to the other algorithms.

International Journal of Computational Intelligence and Applications, 2009

In this paper, we propose a new hybrid Bivariate Complex Fourier Wavelet Regularized Deconvolutio... more In this paper, we propose a new hybrid Bivariate Complex Fourier Wavelet Regularized Deconvolution (Bi-ComForWaRD) that is an extension to the ComForWaRD algorithm, for medical imaging. This new algorithm is a two-step process, a global blur compensation using generalized Wiener filter and followed by a denoising algorithm using local adaptive Bivariate shrinkage function. It is a low-complexity denoising algorithm using the joint statistics of the wavelet coefficients and considers the statistical dependencies between the coefficients. And also, the performance of this system will be demonstrated on both the orthogonal wavelet transform and the dual-tree complex wavelet transform (DT-CWT) and some comparisons with the best available wavelet-based image denoising results will be given in order to illustrate the effectiveness of the system.

International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), 2007

The inversion of the Radon transform in the presence of noise is numerically unstable in tomograp... more The inversion of the Radon transform in the presence of noise is numerically unstable in tomographic image reconstruction and is said to be ill conditioned. We propose an efficient hybrid Co-mplex Fourier-Wavelet Regularization (ComForWaRD) model that comprises blurring operator inver-sion followed by noise suppression via scalar shrinkage in both Fourier and Wavelet domains. The Fou-rier shrinkage exploits the structure of

International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), 2007

The inversion of the Radon transform in the presence of noise is numerically unstable in tomograp... more The inversion of the Radon transform in the presence of noise is numerically unstable in tomographic image reconstruction and is said to be ill conditioned. We propose an efficient hybrid Co-mplex Fourier-Wavelet Regularization (ComForWaRD) model that comprises blurring operator inver-sion followed by noise suppression via scalar shrinkage in both Fourier and Wavelet domains. The Fou-rier shrinkage exploits the structure of

Ain Shams Engineering Journal, 2017

Induction motors consumes 90% of total power consumed by industries due to large scale utilisatio... more Induction motors consumes 90% of total power consumed by industries due to large scale utilisation. Even though these motors are rugged in structure, they often face unexpected failure due to long usage without maintenance. Bearing failure is a major problem among various faults, which cause catastrophic damage to machine when unnoticed at incipient stage. So the bearing faults in induction machines should be continuously monitored. Motor current signature analysis (MCSA) has become popular for detection and localisation of these faults and has attracted concentration of many researchers. In this paper stator current is monitored by means of frequency spectral subtraction using various wavelet transforms to suppress dominant components. The spectral subtraction using discrete wavelet transform (DWT), stationary wavelet transform (SWT) and wavelet packet decomposition (WPD) is performed and a comparative analysis is carried out by means of different fault indexing parameters. The proposed topology is examined using 2.2 kW induction machine test bed.

International Journal of Engineering & Technology, 2018

The image classification is a classical problem of image processing, computer vision and machine ... more The image classification is a classical problem of image processing, computer vision and machine learning fields. In this paper we study the image classification using deep learning. We use AlexNet architecture with convolutional neural networks for this purpose. Four test images are selected from the ImageNet database for the classification purpose. We cropped the images for various portion areas and conducted experiments. The results show the effectiveness of deep learning based image classification using AlexNet.

2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN), 2015

ABSTRACT Ionospheric time delay variations are highly variable and random in the low latitude Ind... more ABSTRACT Ionospheric time delay variations are highly variable and random in the low latitude Indian region. It is a key responsible parameter for the range error in Global Positioning System (GPS) ranging signals which is proportional to the total electron content (TEC). Dual frequency GPS receiver at KL University, Vaddeswaram (16.31° N, 80.37° E), India (falls under the transition zone of the Equatorial Ionization Anomaly in low latitude) is considered in the analysis. An Auto Regressive Moving Average (ARMA) model is implemented for short term forecasting of the VTEC (Vertical TEC) values. Three Geomagnetic storms occurred in the current solar maximum period (2013-2014) are considered to test the performance of ARMA model. The forecasted VTEC values are compared with original VTEC the values and IRI models. The forecasted results indicate that ARMA model would be useful to set up an early warning system of ionospheric disturbances.

Defence Science Journal, 2015

Acquisition is a most important process and a challenge task for identifying visible satellites, ... more Acquisition is a most important process and a challenge task for identifying visible satellites, coarse values of carrier frequency, and code phase of the satellite signals in designing software defined Global positioning system (GPS) receiver. This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Fourier transform (ssFFT). The proposed algorithm exploits the recently developed sparse FFT (or sparse IFFT) that computes in sub-linear time. Further it uses the property of fourier transforms (FT): Aliasing a signal in the time domain corresponds to sub-sampling it in the frequency domain, and vice versa. The ssFFT is an FFT algorithm that computes sub-sampled version of the data by an integer factor 'd', and hence, the computational complexity is proportionately reduced by a factor of 'd log d' compared to conventional FFT-based algorithms for any length of the input GPS signal. The simulation results show that the proposed ssFFT based GPS acquisition computation is 8.5571 times faster than the conventional FFT-based acquisition computation time. The implementation of this method in an FPGA provides very fast processing of incoming GPS samples that satisfies real-time positioning requirements.

Liquid Crystals Today, 2015

Transition temperatures in N-(p-n-heptyloxybenzylidene)-p-n-alkyloxy anilines, 7O.Om liquid cryst... more Transition temperatures in N-(p-n-heptyloxybenzylidene)-p-n-alkyloxy anilines, 7O.Om liquid crystalline compounds are computed from optical textures using Multispectral Correlations Technique in image processing. The statistical parameters like mean, standard deviation and entropy of textures as a function of temperature are computed from the image processing technique. These results show abrupt changes as a function of temperature, indicating the phase transition of the 7O.Om samples. The MATLAB simulation results are in good agreement with DSC results and the proposed methodology is one of the techniques in giving reliable and suitable technique to identify transition temperatures at low cost.

International Journal of Engineering & Technology, 2018

The modern signal and image processing deals with large data such as images and this data deals w... more The modern signal and image processing deals with large data such as images and this data deals with complex statistics and high dimensionality. Sparsity is one powerful tool used signal and image processing applications. The mainly used applications are compression and denoising. A dictionary contains information of the signals in the form of coefficients. Recently dictionary learning has emerged for efficient representation of signals. In this paper we study the image compression using both analytical and learned dictionaries. The results show that the effectiveness of learned dictionaries in the application of image compression.

Glaucoma is a common cause of blindness amongst retinal diseases with 13% of the cases getting af... more Glaucoma is a common cause of blindness amongst retinal diseases with 13% of the cases getting affected. The changes happen in retinal structure that gradually results in loss of peripheral vision and in the end leads to blindness if it is not treated in time. No cure is present for Glaucoma, however, its earlier detection as well as treatment helps in preventing loss of vision. Because the procedure of manual diagnosis is expensive as well as error-prone, effort has been made toward automated detection of Glaucoma in its earlier stage [1]. Glaucoma refers to a set of eye diseases that are related to concurrent functional failures in visual field. Changes in structure are symptomized by a slow diminishing neuro-retinal rim denoting degeneration of axons as well as astrocytes of the Optic Nerve. Because any lost capacity of the optic nerve is not recoverable, earlier detection as well as care is crucial for patients to retain their vision. Two major kinds of Glaucoma include: 1) Primary Open Angle Glaucoma (POAG) as well as (ii) Angle Closure Glaucoma (ACG). The former progresses in a slow manner and at times without any significant loss in vision for several years. Treatment involves medication if an early diagnosis is made. The latter requires surgery as a small portion of the outer edge of the iris is to be removed. In latest studies, a lot effort has been put into automatic diagnosis of glaucoma on the basis of computer vision. The structure of glaucoma analysis systems is dependent on the types of image cue and image modality utilized. Amongst structural image cues learnt for diagnosing glaucoma, cues based on optic discs as well as cups are significant. Optic discs are situated near ganglion nerve fibres congregating in the retina. Optic cup is where the depression occurs in the optic disc from where the fibre comes out of the retina through the Optic Nerve Head (ONH). The borders of the cup and disc structures are required to be found since it helps the assessment of glaucoma cues like disc and cup asymmetry and high Cup-to-Disc Ratio (CDR), described as the ratio between vertical cup diameter to vertical disc diameter. Value of CDR is assessed by planimetry from color fundus images after outlining the optic discs and cups physically. As the process of manual annotation of cup and disc for every image involves Glaucoma is a common cause of blindness and it is increasingly becoming more severe when taking into consideration the aging population. As the dead retinal nerve fibres are not healable, earlier detection as well as prevention of glaucoma is crucial. Resilient and automatic mass-screening will assist in the extension of symptoms-free life for the patients. A new automatic appearance-based glaucoma classification system which does not rely on segmentation-based measures is suggested here. It employs image fusion, which refers to the procedure of fusing images obtained from various sources for acquiring improved situational awareness. The goal of fusion of source images is the combination of highly relevant data from sources into one composite image. Genetic Algorithm (GA) is utilized for features selection. Features extraction methods utilized are Discrete Wavelet Transform (DWT) utilized for multiresolution fusion as well as Local Binary Patterns (LBP) for texture features. Outcomes prove that the suggested model attains excellent glaucoma classification.

Received May 28, 2021 Revised Aug 31, 2021 Accepted Sep 13, 2021 In automotive vehicles, radar is... more Received May 28, 2021 Revised Aug 31, 2021 Accepted Sep 13, 2021 In automotive vehicles, radar is the one of the component for autonomous driving, used for target detection and long-range sensing. Whereas interference exists in signals, noise increases and it effects severely while detecting target objects. For these reasons, various interference mitigation techniques are implemented in this paper. By using these mitigation techniques interference and noise are reduced and original signals are reconstructed. In this paper, we proposed a method to mitigate interference in signal using deep learning. The proposed method provides the best and accurate performance in relate to the various interference conditions and gives better accuracy compared with other existing methods.

International Journal of Engineering & Technology, 2018

This paper focuses on reducing the processing time of software GPS receiver using sub-sampling te... more This paper focuses on reducing the processing time of software GPS receiver using sub-sampling techniques. As the GPS signals are wide band signals, sampling frequency is very high. Sub-sampling enables to reduce time for processing. From the simulation results, it is observed that the sampling frequency can be reduced up to 2.5 MHz without loss of tracked signal. The processing time is reduced for software GPS receiver after sub-sampling. The overall reduction in processing time is from 3.456647 sec to 2.15946 sec respectively for sampling frequency 5 MHz , 2.5 MHz. Thus time saved is 37% of the original one.

Liquid Crystals, 2014

ABSTRACT Textural analysis is done in the case of the thermotropic liquid crystal (LC), 4-heptylo... more ABSTRACT Textural analysis is done in the case of the thermotropic liquid crystal (LC), 4-heptyloxybenzylidene-4′-nonyloxyaniline, 7O.O9, using a polarising microscope attached with a hot stage with a high-resolution camera. Natural images are highly structured: their pixels exhibit strong dependencies and carry important information about the structure of the objects. In this article, we consider the structural similarity index measure parameter computed as a function of the temperature. The results exhibit abrupt changes with temperature showing different liquid crystalline phases. This statistical image analysis is compared with the differential scanning calorimeter data and good agreement was found. The proposed methodology is very sensitive and reliable technique to identify the LC phases.

2013 Annual IEEE India Conference (INDICON), 2013

This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Four... more This paper presents a new, simple, efficient and faster GPS acquisition via sub-sampled fast Fourier transform (ssFFT) and thresholding. The proposed algorithm exploits the recently developed sparse FFT (or sparse IFFT) that computes in sublinear time. Further it uses the property of Fourier transforms (FT): Aliasing a signal in the time domain is equivalent to subsampling it in the frequency domain, and vice versa. The ssFFT is an FFT algorithm that computes with sub sampling factor `d', and hence the computational complexity is reduced by a factor of `d logd', compared to conventional FFT based algorithms for any length of the input GPS signal. The simulation results show that the proposed ssFFT based GPS acquisition computation time is 8.5571 times faster than that conventional FFT based acquisition computation. A clean spike is produced by thresholding the noisy signal.

2013 IEEE International Conference on Signal Processing, Computing and Control (ISPCC), 2013

ABSTRACT The development of software based GNSS receivers is being rapidly revolutionized in sate... more ABSTRACT The development of software based GNSS receivers is being rapidly revolutionized in satellite based navigation applications. In view of commencement of new satellite/ground based navigation systems such as Indian Regional Navigations Systems (IRNSS), GPS Aided Geo Augmented Navigation (GAGAN), China's COMPAS and pseduolites etc., the receiver technology is to be updated efficiently for high positional accuracy requirements under noisy environments. The main modules of software GPS receiver contain acquisition, tracking and position computations. Among them, acquisition is very important process for identifying satellites, which is based on spread spectrum technology. In this paper, Goertzel and Cooley-tukey FFT GPS acquisition algorithms are implemented for GPS L1 signals. The simulations results indicate that Cooley-tukey FFT GPS acquisition algorithm (Acquisition time: 18.32 seconds) is performed well as compared to the other algorithms.

International Journal of Computational Intelligence and Applications, 2009

In this paper, we propose a new hybrid Bivariate Complex Fourier Wavelet Regularized Deconvolutio... more In this paper, we propose a new hybrid Bivariate Complex Fourier Wavelet Regularized Deconvolution (Bi-ComForWaRD) that is an extension to the ComForWaRD algorithm, for medical imaging. This new algorithm is a two-step process, a global blur compensation using generalized Wiener filter and followed by a denoising algorithm using local adaptive Bivariate shrinkage function. It is a low-complexity denoising algorithm using the joint statistics of the wavelet coefficients and considers the statistical dependencies between the coefficients. And also, the performance of this system will be demonstrated on both the orthogonal wavelet transform and the dual-tree complex wavelet transform (DT-CWT) and some comparisons with the best available wavelet-based image denoising results will be given in order to illustrate the effectiveness of the system.

International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), 2007

The inversion of the Radon transform in the presence of noise is numerically unstable in tomograp... more The inversion of the Radon transform in the presence of noise is numerically unstable in tomographic image reconstruction and is said to be ill conditioned. We propose an efficient hybrid Co-mplex Fourier-Wavelet Regularization (ComForWaRD) model that comprises blurring operator inver-sion followed by noise suppression via scalar shrinkage in both Fourier and Wavelet domains. The Fou-rier shrinkage exploits the structure of

International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), 2007

The inversion of the Radon transform in the presence of noise is numerically unstable in tomograp... more The inversion of the Radon transform in the presence of noise is numerically unstable in tomographic image reconstruction and is said to be ill conditioned. We propose an efficient hybrid Co-mplex Fourier-Wavelet Regularization (ComForWaRD) model that comprises blurring operator inver-sion followed by noise suppression via scalar shrinkage in both Fourier and Wavelet domains. The Fou-rier shrinkage exploits the structure of