Valli Bhasha - Academia.edu (original) (raw)
Papers by Valli Bhasha
Biometrics is a readily available metric that is playing a vital role in face recognition. There ... more Biometrics is a readily available metric that is playing a vital role in face recognition. There are many domain areas for the features extraction such as frequency measures, geometrical measures and statistical measures. In the proposed Face Recognition System (FRS)the extraction of features are done using frequency and statistics measures. The FFT,DCT, variation, standard deviation, mean, median and entropy are the five features extracted from the ORL dataset for recognition process. A local normalization technique is applied to the extracted features. The training and testing are performed with normalized features using Back PropagationNeural Network (BPNN).
In this paper, the different research papers applicable to topic of super resolution images are r... more In this paper, the different research papers applicable to topic of super resolution images are reviewed. Image super resolution is a most important subject of research in the area of image processing. The “super resolution image” refers as technique to produce the high resolution of the image from single or multiple low resolution images. Image resolution is described as information amount contained by images. The basic idea for Super-Resolution (SR) is that the fusion of a sequence of lowresolution (LR) images which are noisy and blurred that create a high resolution (HR) image. Super resolution is process of restoring and denoising of image. Keywords— Super resolution, high resolution, low resolution.
Journal of Engineering, Design and Technology, 2021
Purpose The problems of Super resolution are broadly discussed in diverse fields. Rather than the... more Purpose The problems of Super resolution are broadly discussed in diverse fields. Rather than the progression toward the super resolution models for real-time images, operating hyperspectral images still remains a challenging problem. Design/methodology/approach This paper aims to develop the enhanced image super-resolution model using “optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT), and Optimized Deep Convolutional Neural Network”. Once after converting the HR images into LR images, the NSSR images are generated by the optimized NSSR. Then the ADWT is used for generating the subbands of both NSSR and HRSB images. The residual image with this information is obtained by the optimized Deep CNN. All the improvements on the algorithms are done by the Opposition-based Barnacles Mating Optimization (O-BMO), with the objective of attaining the multi-objective function concerning the “Peak Signal-to-Noise Ratio (PSNR), and Structur...
Neurocomputing, 2012
Lossless data hiding methods usually fail to recover the hidden messages completely when the wate... more Lossless data hiding methods usually fail to recover the hidden messages completely when the watermarked images are attacked. Therefore, the robust lossless data hiding (RLDH), or the robust reversible watermarking technique, is urgently needed to effectively improve the recovery performance. To date a couple of methods have been developed; however, they have such drawbacks as poor visual quality and low capacity. To solve this problem, we develop a novel statistical quantity histogram shifting and clustering-based RLDH method or SQH-SC for short. The benefits of SQH-SC in comparison with existing typical methods include: (1) strong robustness against lossy compression and random noise due to the usage of k-means clustering; (2) good imperceptibility and reasonable performance tradeoff due to the consideration of the just noticeable distortion of images; (3) high capacity due to the flexible adjustment of the threshold; and (4) wide adaptability and good stability to different kinds of images. Extensive experimental studies based on natural images, medical images, and synthetic aperture radar (SAR) images demonstrate the effectiveness of the proposed SQH-SC.
International Journal of Image and Graphics, 2021
Diverse image super-resolution (SR) techniques have been implemented to reconstruct the high-reso... more Diverse image super-resolution (SR) techniques have been implemented to reconstruct the high-resolution (HR) images from input images through lower spatial resolutions. However, the evaluation of the perceptual quality of SR images remains an important and complex research problem. This paper proposes a new image SR model with the intention of attaining maximum Peak Signal-to-Noise Ratio (PSNR). The conversion of low-resolution (LR) images from the HR images is performed by bicubic interpolation-based downsampling and upsampling. Then, the four sub-bands of LR and HR images are generated by the novel Adaptive Wavelet Lifting approach, in which the filter modes are optimized using the proposed SA-CBO. From this technique, LR wavelet sub-bands (LRSB) for LR images and HR wavelet sub-bands (HRSB) for HR images are formed. With the help of the LRSB and HRSB images, the residual images are formed by the adoption of the optimized Activation function and optimized hidden neurons in a deep ...
International Journal of Wavelets, Multiresolution and Information Processing
The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) ha... more The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) have been producing admirable advancements. The proposed image resolution model involves the following two main analyses: (i) analysis using Adaptive Discrete Wavelet Transform (ADWT) with Deep CNN and (ii) analysis using Non-negative Structured Sparse Representation (NSSR). The technique termed as NSSR is used to recover the high-resolution (HR) images from the low-resolution (LR) images. The experimental evaluation involves two phases: Training and Testing. In the training phase, the information regarding the residual images of the dataset are trained using the optimized Deep CNN. On the other hand, the testing phase helps to generate the super resolution image using the HR wavelet subbands (HRSB) and residual images. As the main novelty, the filter coefficients of DWT are optimized by the hybrid Fire Fly-based Spotted Hyena Optimization (FF-SHO) to develop ADWT. Finally, a valuable perf...
Biometrics is a readily available metric that is playing a vital role in face recognition. There ... more Biometrics is a readily available metric that is playing a vital role in face recognition. There are many domain areas for the features extraction such as frequency measures, geometrical measures and statistical measures. In the proposed Face Recognition System (FRS)the extraction of features are done using frequency and statistics measures. The FFT,DCT, variation, standard deviation, mean, median and entropy are the five features extracted from the ORL dataset for recognition process. A local normalization technique is applied to the extracted features. The training and testing are performed with normalized features using Back PropagationNeural Network (BPNN).
In this paper, the different research papers applicable to topic of super resolution images are r... more In this paper, the different research papers applicable to topic of super resolution images are reviewed. Image super resolution is a most important subject of research in the area of image processing. The “super resolution image” refers as technique to produce the high resolution of the image from single or multiple low resolution images. Image resolution is described as information amount contained by images. The basic idea for Super-Resolution (SR) is that the fusion of a sequence of lowresolution (LR) images which are noisy and blurred that create a high resolution (HR) image. Super resolution is process of restoring and denoising of image. Keywords— Super resolution, high resolution, low resolution.
Journal of Engineering, Design and Technology, 2021
Purpose The problems of Super resolution are broadly discussed in diverse fields. Rather than the... more Purpose The problems of Super resolution are broadly discussed in diverse fields. Rather than the progression toward the super resolution models for real-time images, operating hyperspectral images still remains a challenging problem. Design/methodology/approach This paper aims to develop the enhanced image super-resolution model using “optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT), and Optimized Deep Convolutional Neural Network”. Once after converting the HR images into LR images, the NSSR images are generated by the optimized NSSR. Then the ADWT is used for generating the subbands of both NSSR and HRSB images. The residual image with this information is obtained by the optimized Deep CNN. All the improvements on the algorithms are done by the Opposition-based Barnacles Mating Optimization (O-BMO), with the objective of attaining the multi-objective function concerning the “Peak Signal-to-Noise Ratio (PSNR), and Structur...
Neurocomputing, 2012
Lossless data hiding methods usually fail to recover the hidden messages completely when the wate... more Lossless data hiding methods usually fail to recover the hidden messages completely when the watermarked images are attacked. Therefore, the robust lossless data hiding (RLDH), or the robust reversible watermarking technique, is urgently needed to effectively improve the recovery performance. To date a couple of methods have been developed; however, they have such drawbacks as poor visual quality and low capacity. To solve this problem, we develop a novel statistical quantity histogram shifting and clustering-based RLDH method or SQH-SC for short. The benefits of SQH-SC in comparison with existing typical methods include: (1) strong robustness against lossy compression and random noise due to the usage of k-means clustering; (2) good imperceptibility and reasonable performance tradeoff due to the consideration of the just noticeable distortion of images; (3) high capacity due to the flexible adjustment of the threshold; and (4) wide adaptability and good stability to different kinds of images. Extensive experimental studies based on natural images, medical images, and synthetic aperture radar (SAR) images demonstrate the effectiveness of the proposed SQH-SC.
International Journal of Image and Graphics, 2021
Diverse image super-resolution (SR) techniques have been implemented to reconstruct the high-reso... more Diverse image super-resolution (SR) techniques have been implemented to reconstruct the high-resolution (HR) images from input images through lower spatial resolutions. However, the evaluation of the perceptual quality of SR images remains an important and complex research problem. This paper proposes a new image SR model with the intention of attaining maximum Peak Signal-to-Noise Ratio (PSNR). The conversion of low-resolution (LR) images from the HR images is performed by bicubic interpolation-based downsampling and upsampling. Then, the four sub-bands of LR and HR images are generated by the novel Adaptive Wavelet Lifting approach, in which the filter modes are optimized using the proposed SA-CBO. From this technique, LR wavelet sub-bands (LRSB) for LR images and HR wavelet sub-bands (HRSB) for HR images are formed. With the help of the LRSB and HRSB images, the residual images are formed by the adoption of the optimized Activation function and optimized hidden neurons in a deep ...
International Journal of Wavelets, Multiresolution and Information Processing
The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) ha... more The image super-resolution methods with deep learning using Convolutional Neural Network (CNN) have been producing admirable advancements. The proposed image resolution model involves the following two main analyses: (i) analysis using Adaptive Discrete Wavelet Transform (ADWT) with Deep CNN and (ii) analysis using Non-negative Structured Sparse Representation (NSSR). The technique termed as NSSR is used to recover the high-resolution (HR) images from the low-resolution (LR) images. The experimental evaluation involves two phases: Training and Testing. In the training phase, the information regarding the residual images of the dataset are trained using the optimized Deep CNN. On the other hand, the testing phase helps to generate the super resolution image using the HR wavelet subbands (HRSB) and residual images. As the main novelty, the filter coefficients of DWT are optimized by the hybrid Fire Fly-based Spotted Hyena Optimization (FF-SHO) to develop ADWT. Finally, a valuable perf...