Anand Deshpande - Academia.edu (original) (raw)

Papers by Anand Deshpande

Research paper thumbnail of Motion Estimation Role in the Context of 3D Video

International Journal of Multimedia Data Engineering and Management, 2021

The 3D end-to-end video system (i.e., 3D acquisition, processing, streaming, error concealment, v... more The 3D end-to-end video system (i.e., 3D acquisition, processing, streaming, error concealment, virtual/augmented reality handling, content retrieval, rendering, and displaying) still needs improvements. This paper scrutinizes the Motion Compensation/Motion Estimation (MCME)impact in the 3D Video (3DV) from the end-to-end users' point of view deeply. The concepts of Motion Vectors (MVs) and disparities are very close, and they help to ameliorate all the stages of the end-to-end 3DV system. The High-Efficiency Video Coding (HEVC) video codec standard is taken into consideration to evaluate the emergent trend towards computational treatment throughout the Cloud whenever possible. The tight bond between movement and depth affects 3D information recovery from these cues, and optimize the performance of algorithms and standards from several parts of the 3D system. Still, 3DV lacks support for engaging interactive 3DV services. Better bit allocation strategies also ameliorate all 3D p...

Research paper thumbnail of Optimal Bidding Strategy for Power Market Based on Improved World Cup Optimization Algorithm

Research paper thumbnail of Image transmission in UAV MIMO UWB-OSTBC system over Rayleigh channel using multiple description coding (MDC)

Imaging and Sensing for Unmanned Aircraft Systems: Volume 2: Deployment and Applications, 2020

Research paper thumbnail of Nondestructive Diagnosis and Analysis of Computed Microtomography Images via Texture Descriptors

Advances in Multidisciplinary Medical Technologies ─ Engineering, Modeling and Findings, 2020

X-ray computed microtomography (μCT or micro-CT) allows a nondestructive analysis of samples, whi... more X-ray computed microtomography (μCT or micro-CT) allows a nondestructive analysis of samples, which helps their reuse. The X-ray μCT equipment offers the user several configuration options that change the quality of the images obtained, thus affecting the expected result. In this study, a methodology for analyzing X-ray μCT images generated by the SkyScan 1174 Compact Micro-CT equipment was developed. The basis of this analysis methodology is texture descriptors. Three sets of images were used, and then degradations and noise were applied to the original images, generating new images. Subsequently, the following texture descriptors assisted in scrutinizing the sets: maximum probability, the moment of difference, the inverse difference moment, entropy, and uniformity. Experiments show the outcomes of some tests.

Research paper thumbnail of Introduction to Computational Intelligence and Super-Resolution

Computational Intelligence Methods for Super-Resolution in Image Processing Applications, 2021

Research paper thumbnail of Deep learning as an alternative to super-resolution imaging in UAV systems

Imaging and Sensing for Unmanned Aircraft Systems: Volume 2: Deployment and Applications, 2020

This chapter proposes a framework to super-resolve the low-resolution (LR) images captured using ... more This chapter proposes a framework to super-resolve the low-resolution (LR) images captured using the unmanned aerial vehicle. The framework used a convolution neural network to super-resolve the LR image. This framework also removes the haze present in the LR image. The proposed system is evaluated using peak signal to noise ratio, structural similarity (SSIM) and visual information fidelity (VIFP) in the pixel domain. The experimental results demonstrate the advantage of the proposed method when compared to other state-of-the-art algorithms based on qualitative and quantitative analysis. Future trends in super-resolution (SR) unmanned aerial vehicle (UAV) imaging are discussed at the end of this chapter, followed by the concluding section.

Research paper thumbnail of The DCT-CNN-ResNet50 architecture to classify brain tumors with super-resolution, convolutional neural network, and the ResNet50

Neuroscience Informatics, 2021

Abstract Brain tumors' diagnoses occur mainly by Magnetic resonance imaging (MRI) images. The... more Abstract Brain tumors' diagnoses occur mainly by Magnetic resonance imaging (MRI) images. The tissue analysis methods are used to define these tumors. Nevertheless, few factors like the quality of an MRI device and low image resolution may degrade the quality of MRI images. Also, the detection of tumors in low-resolution images is challenging. A super-resolution method helps overcome this caveat. This work suggests Artificial Intelligence (AI)-based classification of brain tumor using Convolution Neural Network (CNN) algorithms is proposed to classify brain tumors using open-access datasets. This paper hiders on a novel Discrete Cosine Transform-based image fusion combined with Convolution Neural Network as a super-resolution and classifier framework that can distinguish (aka, classify) tissue as tumor and no tumor using open-access datasets. The framework's performance is analyzed with and without super-resolution method and achieved 98.14% accuracy rate has been detected with super-resolution and ResNet50 architecture. The experiments performed on MRI images show that the proposed super-resolution framework relies on the Discrete Cosine Transform (DCT), CNN, and ResNet50 (aka DCT-CNN-ResNet50) and capable of improving classification accuracy.

Research paper thumbnail of Survey of Super Resolution Techniques

ICTACT Journal on Image and Video Processing, 2019

Research paper thumbnail of Segmentation and Quality Analysis of Long Range Captured Iris Image

ICTACT Journal on Image and Video Processing, 2016

Research paper thumbnail of Iterated Back Projection Based Super-Resolution for Iris Feature Extraction

Procedia Computer Science, 2015

Research paper thumbnail of Super resolution and recognition of unconstrained ear image

International Journal of Biometrics, 2020

Research paper thumbnail of Image Transmission in UAV MIMO UWB- OSTBC System over Rayleigh Channel Using Multiple Description Coding (MDC)

IET-The Institution of Engineering and Technology., 2020

Orthogonal Space-Time Block Codes (OSTBC) and multiple-input-multiple-output (MIMO) communication... more Orthogonal Space-Time Block Codes (OSTBC) and multiple-input-multiple-output (MIMO) communication system are new techniques with high performance that have many applications in wireless telecommunications. This chapter presents an image transfer technique for the unmanned aerial vehicle (UAV) in a UWB system using a hybrid structure of the MIMO-OSTBC wireless environment in multiple description coding (MDC) deals. MDC technique for image transmission is a new approach in which there is no record of it so far. This ensures that in the packet loss scenario due to channel errors, images with acceptable quality with no need for retransmission can be reconstructed. The proposed system is implemented using a different number of transmitter and receiver antennas UAV. Assuming a Rayleigh model for the communication channels, the MDC image transmission performance is compared with single description coding (SDC). Experimental results confirm that the proposed hybrid method has better performance than the SDC.

Research paper thumbnail of Vision based System for Optical Number Recognition

International Journal of Computer …, Jan 1, 2012

Vision based system for Optical Number recognition (ONR) deals with the recognition of processed ... more Vision based system for Optical Number recognition (ONR) deals with the recognition of processed numbers rather than magnetically processed ones. ONR is a process of automatic recognition of numbers by computers in images and digitized pages of text. ONR is one of the most fascinating and challenging areas of pattern recognition with various practical applications. It can contribute immensely to the advancement of an automation process and can improve the interface between man and machine in many applications. Moments and functions of moments have been extensively employed as invariant global features of images in pattern recognition. This paper shows the implementation and analysis of ONR, regardless of orientation, size and position, feature vectors are computed with the help of statistical moments.

CALL FOR PAPERS by Anand Deshpande

Research paper thumbnail of Springer CALL FOR BOOK CHAPTERS 2020: Computational Intelligence Methods for Super- Resolution in Image Processing Applications Book Series: Biological and Medical Physics, Biomedical Engineering

Springer Call for Book Chapters, 2020

SCOPE OF THE BOOK Super-Resolution (SR) techniques can be used in general image processing, micro... more SCOPE OF THE BOOK Super-Resolution (SR) techniques can be used in general image processing, microscopy, security, biomedical imaging, automation/robotics, biometrics among other areas to handle the dimensionality conundrum posed by the conflicts caused by the necessity to balance image acquisition, image modality/resolution/representation, subspace decomposition, compressed sensing, and communications constraints. Lighter computational implementations are needed to circumvent the heavy computational burden brought in by SR image processing applications. Soft computing and, specifically, Deep Learning (DL) ascend as possible solutions to SR efficient deployment. The amount of multi-resolution and multimodal images has been augmenting the need for more efficient and intelligent analyses, for example, computer-aided diagnosis via Computational Intelligence (CI) techniques. To facilitate this to the research community working in various fields, we and Springer Nature are coming up with Book consolidating the work carried in the subject of Computational Intelligence methods for Super Resolution in Image Processing Applications. The intend of publishing the book is to serve for researchers, technology professionals, academicians and students working in the area of latest advances and upcoming technologies employing CI methods for SR in imaging processing applications. This book explores the application of deep learning techniques within a particularly difficult computational type of computer vision problem: SR. This book aspires to provide assortment of novel research works that focuses on broad challenges of CI approaches for SR in image processing applications. We invite all researchers, academicians, developers and research scholars to contribute chapters in the field of CI and SR with an emphasis on practical examples. Each article is expected to cover Computational Intelligence methods for Super Resolution in image processing applications.

BOOKS/LIVROS by Anand Deshpande

Research paper thumbnail of Imaging and Sensing for Unmanned Aircraft Systems Volume 1: Control and Performance

Volume 1 concentrates on UAS control and performance methodologies including Computer Vision and ... more Volume 1 concentrates on UAS control and performance methodologies including Computer Vision and Data Storage, Integrated Optical Flow for Detection and Avoidance Systems, Navigation and Intelligence, Modeling and Simulation, Multisensor Data Fusion, Vision in Micro-Aerial Vehicles (MAVs), Computer Vision in UAV using ROS, Security Aspects of UAV and Robot Operating System, Vision in Indoor and Outdoor Drones, Sensors and Computer Vision, and Small UAVP for Persistent Surveillance.

Research paper thumbnail of Motion Estimation Role in the Context of 3D Video

International Journal of Multimedia Data Engineering and Management, 2021

The 3D end-to-end video system (i.e., 3D acquisition, processing, streaming, error concealment, v... more The 3D end-to-end video system (i.e., 3D acquisition, processing, streaming, error concealment, virtual/augmented reality handling, content retrieval, rendering, and displaying) still needs improvements. This paper scrutinizes the Motion Compensation/Motion Estimation (MCME)impact in the 3D Video (3DV) from the end-to-end users' point of view deeply. The concepts of Motion Vectors (MVs) and disparities are very close, and they help to ameliorate all the stages of the end-to-end 3DV system. The High-Efficiency Video Coding (HEVC) video codec standard is taken into consideration to evaluate the emergent trend towards computational treatment throughout the Cloud whenever possible. The tight bond between movement and depth affects 3D information recovery from these cues, and optimize the performance of algorithms and standards from several parts of the 3D system. Still, 3DV lacks support for engaging interactive 3DV services. Better bit allocation strategies also ameliorate all 3D p...

Research paper thumbnail of Optimal Bidding Strategy for Power Market Based on Improved World Cup Optimization Algorithm

Research paper thumbnail of Image transmission in UAV MIMO UWB-OSTBC system over Rayleigh channel using multiple description coding (MDC)

Imaging and Sensing for Unmanned Aircraft Systems: Volume 2: Deployment and Applications, 2020

Research paper thumbnail of Nondestructive Diagnosis and Analysis of Computed Microtomography Images via Texture Descriptors

Advances in Multidisciplinary Medical Technologies ─ Engineering, Modeling and Findings, 2020

X-ray computed microtomography (μCT or micro-CT) allows a nondestructive analysis of samples, whi... more X-ray computed microtomography (μCT or micro-CT) allows a nondestructive analysis of samples, which helps their reuse. The X-ray μCT equipment offers the user several configuration options that change the quality of the images obtained, thus affecting the expected result. In this study, a methodology for analyzing X-ray μCT images generated by the SkyScan 1174 Compact Micro-CT equipment was developed. The basis of this analysis methodology is texture descriptors. Three sets of images were used, and then degradations and noise were applied to the original images, generating new images. Subsequently, the following texture descriptors assisted in scrutinizing the sets: maximum probability, the moment of difference, the inverse difference moment, entropy, and uniformity. Experiments show the outcomes of some tests.

Research paper thumbnail of Introduction to Computational Intelligence and Super-Resolution

Computational Intelligence Methods for Super-Resolution in Image Processing Applications, 2021

Research paper thumbnail of Deep learning as an alternative to super-resolution imaging in UAV systems

Imaging and Sensing for Unmanned Aircraft Systems: Volume 2: Deployment and Applications, 2020

This chapter proposes a framework to super-resolve the low-resolution (LR) images captured using ... more This chapter proposes a framework to super-resolve the low-resolution (LR) images captured using the unmanned aerial vehicle. The framework used a convolution neural network to super-resolve the LR image. This framework also removes the haze present in the LR image. The proposed system is evaluated using peak signal to noise ratio, structural similarity (SSIM) and visual information fidelity (VIFP) in the pixel domain. The experimental results demonstrate the advantage of the proposed method when compared to other state-of-the-art algorithms based on qualitative and quantitative analysis. Future trends in super-resolution (SR) unmanned aerial vehicle (UAV) imaging are discussed at the end of this chapter, followed by the concluding section.

Research paper thumbnail of The DCT-CNN-ResNet50 architecture to classify brain tumors with super-resolution, convolutional neural network, and the ResNet50

Neuroscience Informatics, 2021

Abstract Brain tumors' diagnoses occur mainly by Magnetic resonance imaging (MRI) images. The... more Abstract Brain tumors' diagnoses occur mainly by Magnetic resonance imaging (MRI) images. The tissue analysis methods are used to define these tumors. Nevertheless, few factors like the quality of an MRI device and low image resolution may degrade the quality of MRI images. Also, the detection of tumors in low-resolution images is challenging. A super-resolution method helps overcome this caveat. This work suggests Artificial Intelligence (AI)-based classification of brain tumor using Convolution Neural Network (CNN) algorithms is proposed to classify brain tumors using open-access datasets. This paper hiders on a novel Discrete Cosine Transform-based image fusion combined with Convolution Neural Network as a super-resolution and classifier framework that can distinguish (aka, classify) tissue as tumor and no tumor using open-access datasets. The framework's performance is analyzed with and without super-resolution method and achieved 98.14% accuracy rate has been detected with super-resolution and ResNet50 architecture. The experiments performed on MRI images show that the proposed super-resolution framework relies on the Discrete Cosine Transform (DCT), CNN, and ResNet50 (aka DCT-CNN-ResNet50) and capable of improving classification accuracy.

Research paper thumbnail of Survey of Super Resolution Techniques

ICTACT Journal on Image and Video Processing, 2019

Research paper thumbnail of Segmentation and Quality Analysis of Long Range Captured Iris Image

ICTACT Journal on Image and Video Processing, 2016

Research paper thumbnail of Iterated Back Projection Based Super-Resolution for Iris Feature Extraction

Procedia Computer Science, 2015

Research paper thumbnail of Super resolution and recognition of unconstrained ear image

International Journal of Biometrics, 2020

Research paper thumbnail of Image Transmission in UAV MIMO UWB- OSTBC System over Rayleigh Channel Using Multiple Description Coding (MDC)

IET-The Institution of Engineering and Technology., 2020

Orthogonal Space-Time Block Codes (OSTBC) and multiple-input-multiple-output (MIMO) communication... more Orthogonal Space-Time Block Codes (OSTBC) and multiple-input-multiple-output (MIMO) communication system are new techniques with high performance that have many applications in wireless telecommunications. This chapter presents an image transfer technique for the unmanned aerial vehicle (UAV) in a UWB system using a hybrid structure of the MIMO-OSTBC wireless environment in multiple description coding (MDC) deals. MDC technique for image transmission is a new approach in which there is no record of it so far. This ensures that in the packet loss scenario due to channel errors, images with acceptable quality with no need for retransmission can be reconstructed. The proposed system is implemented using a different number of transmitter and receiver antennas UAV. Assuming a Rayleigh model for the communication channels, the MDC image transmission performance is compared with single description coding (SDC). Experimental results confirm that the proposed hybrid method has better performance than the SDC.

Research paper thumbnail of Vision based System for Optical Number Recognition

International Journal of Computer …, Jan 1, 2012

Vision based system for Optical Number recognition (ONR) deals with the recognition of processed ... more Vision based system for Optical Number recognition (ONR) deals with the recognition of processed numbers rather than magnetically processed ones. ONR is a process of automatic recognition of numbers by computers in images and digitized pages of text. ONR is one of the most fascinating and challenging areas of pattern recognition with various practical applications. It can contribute immensely to the advancement of an automation process and can improve the interface between man and machine in many applications. Moments and functions of moments have been extensively employed as invariant global features of images in pattern recognition. This paper shows the implementation and analysis of ONR, regardless of orientation, size and position, feature vectors are computed with the help of statistical moments.

Research paper thumbnail of Springer CALL FOR BOOK CHAPTERS 2020: Computational Intelligence Methods for Super- Resolution in Image Processing Applications Book Series: Biological and Medical Physics, Biomedical Engineering

Springer Call for Book Chapters, 2020

SCOPE OF THE BOOK Super-Resolution (SR) techniques can be used in general image processing, micro... more SCOPE OF THE BOOK Super-Resolution (SR) techniques can be used in general image processing, microscopy, security, biomedical imaging, automation/robotics, biometrics among other areas to handle the dimensionality conundrum posed by the conflicts caused by the necessity to balance image acquisition, image modality/resolution/representation, subspace decomposition, compressed sensing, and communications constraints. Lighter computational implementations are needed to circumvent the heavy computational burden brought in by SR image processing applications. Soft computing and, specifically, Deep Learning (DL) ascend as possible solutions to SR efficient deployment. The amount of multi-resolution and multimodal images has been augmenting the need for more efficient and intelligent analyses, for example, computer-aided diagnosis via Computational Intelligence (CI) techniques. To facilitate this to the research community working in various fields, we and Springer Nature are coming up with Book consolidating the work carried in the subject of Computational Intelligence methods for Super Resolution in Image Processing Applications. The intend of publishing the book is to serve for researchers, technology professionals, academicians and students working in the area of latest advances and upcoming technologies employing CI methods for SR in imaging processing applications. This book explores the application of deep learning techniques within a particularly difficult computational type of computer vision problem: SR. This book aspires to provide assortment of novel research works that focuses on broad challenges of CI approaches for SR in image processing applications. We invite all researchers, academicians, developers and research scholars to contribute chapters in the field of CI and SR with an emphasis on practical examples. Each article is expected to cover Computational Intelligence methods for Super Resolution in image processing applications.

Research paper thumbnail of Imaging and Sensing for Unmanned Aircraft Systems Volume 1: Control and Performance

Volume 1 concentrates on UAS control and performance methodologies including Computer Vision and ... more Volume 1 concentrates on UAS control and performance methodologies including Computer Vision and Data Storage, Integrated Optical Flow for Detection and Avoidance Systems, Navigation and Intelligence, Modeling and Simulation, Multisensor Data Fusion, Vision in Micro-Aerial Vehicles (MAVs), Computer Vision in UAV using ROS, Security Aspects of UAV and Robot Operating System, Vision in Indoor and Outdoor Drones, Sensors and Computer Vision, and Small UAVP for Persistent Surveillance.