Murali Kanthi | CMR Group of institutions (original) (raw)
Papers by Murali Kanthi
2023 2nd International Conference for Innovation in Technology (INOCON)
International Journal of Intelligent Engineering and Systems, 2022
The classification of hyperspectral image (HSI) has attracted significant attention from the rese... more The classification of hyperspectral image (HSI) has attracted significant attention from the research community of remote sensing. HSI analysis suffers from overfitting due to the limited number of labelled training samples. As a result, in order to enhance the performance of the HSI classification task, a better efficient neural network architecture should be developed. To tackle this issue, this letter presents a new 3D-Inception CNN (3D-ICNN) model for dynamically extracting features by stacking inception modules in the network that can learn more representative features with fewer training samples by adopting variable spatial size convolutional filters and dynamic CNN architecture. The experimental results exhibit that the presented model can modify the network design adaptively and achieve higher classification performance. To establish the efficiency and robustness of the presented model, the experiments are conducted on the publicly available benchmark data sets and also on the new data sets. The proposed 3D-Inception CNN model obtained accuracies of 86.25% on Ahmedabad-1(AH1) dataset, 80.30% on Ahmedabad-2(AH2) dataset, 99.95% on the Pavia University (PU) dataset, 99.86% on the Salinas (SA) dataset, and 99.89% on the Indian Pines (IP) dataset.
Journal of Theoretical and Applied Information Technology, 2021
Hyperspectral imaging (HSI) is a popular subject in remote sensing data processing because of the... more Hyperspectral imaging (HSI) is a popular subject in remote sensing data processing because of the huge quantity of data included in these images, which enables for improved description and utilization of the surface of the earth by integrating abundant spectral and spatial data. However, due to the high dimensionality of HSI data and the limited number of labelled examples available, conducting HSI image classification poses significant technical and pragmatic hurdles. Approaches to HSI classification with deep learning have gained major successes in recent years as new deep learning algorithms emerge, giving unique prospects for hyperspectral image classification research and development. Initially, a quick introduction to standard deep learning (DL) models is provided, followed by a comparison of the performance of common DL based HSI approaches. Finally, the difficulties and future research prospects are explored.
International Journal of Intelligent Engineering and Systems, 2022
The classification of hyperspectral image (HSI) has attracted significant attention from the rese... more The classification of hyperspectral image (HSI) has attracted significant attention from the research community of remote sensing. HSI analysis suffers from overfitting due to the limited number of labelled training samples. As a result, in order to enhance the performance of the HSI classification task, a better efficient neural network architecture should be developed. To tackle this issue, this letter presents a new 3D-Inception CNN (3D-ICNN) model for dynamically extracting features by stacking inception modules in the network that can learn more representative features with fewer training samples by adopting variable spatial size convolutional filters and dynamic CNN architecture. The experimental results exhibit that the presented model can modify the network design adaptively and achieve higher classification performance. To establish the efficiency and robustness of the presented model, the experiments are conducted on the publicly available benchmark data sets and also on the new data sets. The proposed 3D-Inception CNN model obtained accuracies of 86.25% on Ahmedabad-1(AH1) dataset, 80.30% on Ahmedabad-2(AH2) dataset, 99.95% on the Pavia University (PU) dataset, 99.86% on the Salinas (SA) dataset, and 99.89% on the Indian Pines (IP) dataset.
Indian Journal of Computer Science and Engineering (IJCSE), 2021
Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used fo... more Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets-Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)-are compared to those from the current models. Experimental results show that the computational complexity of the proposed approach is significantly reduced and producing relatively good classification accuracy with the state-of-the-art methods.
Received Mar 5, 2021 Revised Aug 6, 2021 Accepted Aug 11, 2021 Machine learning involves the task... more Received Mar 5, 2021 Revised Aug 6, 2021 Accepted Aug 11, 2021 Machine learning involves the task of training systems to be able to make decisions without being explicitly programmed. Important among machine learning tasks is classification involving the process of training machines to make predictions from predefined labels. Classification is broadly categorized into three distinct groups: single-label (SL), multi-class, and multi-label (ML) classification. This research work presents an application of a multi-label classification (MLC) technique in automating Quranic verses labeling. MLC has been gaining attention in recent years. This is due to the increasing amount of works based on real-world classification problems of multi-label data. In traditional classification problems, patterns are associated with a single-label from a set of disjoint labels. However, in MLC, an instance of data is associated with a set of labels. In this paper, three standard MLC methods: binary relevan...
Indian Journal of Computer Science and Engineering, 2021
Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used fo... more Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)are comp...
Indonesian Journal of Electrical Engineering and Computer Science
Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) ... more Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) classification. High classification accuracy has been achieved by extracting deep features from both spatial-spectral channels. However, the efficiency of such spatial-spectral approaches depends on the spatial dimension of each patch and there is no theoretically valid approach to find the optimum spatial dimension to be considered. It is more valid to extract spatial features by considering varying neighborhood scales in spatial dimensions. In this regard, this article proposes a deep convolutional neural network (CNN) model wherein three different multi-scale spatial-spectral patches are used to extract the features in both the spatial and spectral channels. In order to extract these potential features, the proposed deep learning architecture takes three patches various scales in spatial dimension. 3D convolution is performed on each selected patch and the process runs through entire ...
2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)
Hyperspectral image consists of huge spectral and special information. Deep learning models, such... more Hyperspectral image consists of huge spectral and special information. Deep learning models, such as deep convolutional neural networks (CNNs) being widely used for HSI classification. Most of the approaches are based on 2D CNN. Whereas, the HSI classification performance depends on both spatial and spectral information. This paper proposes a new 3D-Deep Feature Extraction CNN model for the HSI classification which uses both spectral and spatial information. Here the HSI data is divided into 3D patches and fed into the proposed model for deep feature extractions. Experimental results show that the performance of HSI classification is improved significantly with the proposed model. The experimental results on the publicly available HSI datasets, viz., Indian Pines(IP), Pavia University scene(PU) and Salinas scene(SA), are compared with the contemporary models. The current results indicates that the proposed model provides comparatively better results than the state-of-the-art methods.
2023 2nd International Conference for Innovation in Technology (INOCON)
International Journal of Intelligent Engineering and Systems, 2022
The classification of hyperspectral image (HSI) has attracted significant attention from the rese... more The classification of hyperspectral image (HSI) has attracted significant attention from the research community of remote sensing. HSI analysis suffers from overfitting due to the limited number of labelled training samples. As a result, in order to enhance the performance of the HSI classification task, a better efficient neural network architecture should be developed. To tackle this issue, this letter presents a new 3D-Inception CNN (3D-ICNN) model for dynamically extracting features by stacking inception modules in the network that can learn more representative features with fewer training samples by adopting variable spatial size convolutional filters and dynamic CNN architecture. The experimental results exhibit that the presented model can modify the network design adaptively and achieve higher classification performance. To establish the efficiency and robustness of the presented model, the experiments are conducted on the publicly available benchmark data sets and also on the new data sets. The proposed 3D-Inception CNN model obtained accuracies of 86.25% on Ahmedabad-1(AH1) dataset, 80.30% on Ahmedabad-2(AH2) dataset, 99.95% on the Pavia University (PU) dataset, 99.86% on the Salinas (SA) dataset, and 99.89% on the Indian Pines (IP) dataset.
Journal of Theoretical and Applied Information Technology, 2021
Hyperspectral imaging (HSI) is a popular subject in remote sensing data processing because of the... more Hyperspectral imaging (HSI) is a popular subject in remote sensing data processing because of the huge quantity of data included in these images, which enables for improved description and utilization of the surface of the earth by integrating abundant spectral and spatial data. However, due to the high dimensionality of HSI data and the limited number of labelled examples available, conducting HSI image classification poses significant technical and pragmatic hurdles. Approaches to HSI classification with deep learning have gained major successes in recent years as new deep learning algorithms emerge, giving unique prospects for hyperspectral image classification research and development. Initially, a quick introduction to standard deep learning (DL) models is provided, followed by a comparison of the performance of common DL based HSI approaches. Finally, the difficulties and future research prospects are explored.
International Journal of Intelligent Engineering and Systems, 2022
The classification of hyperspectral image (HSI) has attracted significant attention from the rese... more The classification of hyperspectral image (HSI) has attracted significant attention from the research community of remote sensing. HSI analysis suffers from overfitting due to the limited number of labelled training samples. As a result, in order to enhance the performance of the HSI classification task, a better efficient neural network architecture should be developed. To tackle this issue, this letter presents a new 3D-Inception CNN (3D-ICNN) model for dynamically extracting features by stacking inception modules in the network that can learn more representative features with fewer training samples by adopting variable spatial size convolutional filters and dynamic CNN architecture. The experimental results exhibit that the presented model can modify the network design adaptively and achieve higher classification performance. To establish the efficiency and robustness of the presented model, the experiments are conducted on the publicly available benchmark data sets and also on the new data sets. The proposed 3D-Inception CNN model obtained accuracies of 86.25% on Ahmedabad-1(AH1) dataset, 80.30% on Ahmedabad-2(AH2) dataset, 99.95% on the Pavia University (PU) dataset, 99.86% on the Salinas (SA) dataset, and 99.89% on the Indian Pines (IP) dataset.
Indian Journal of Computer Science and Engineering (IJCSE), 2021
Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used fo... more Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets-Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)-are compared to those from the current models. Experimental results show that the computational complexity of the proposed approach is significantly reduced and producing relatively good classification accuracy with the state-of-the-art methods.
Received Mar 5, 2021 Revised Aug 6, 2021 Accepted Aug 11, 2021 Machine learning involves the task... more Received Mar 5, 2021 Revised Aug 6, 2021 Accepted Aug 11, 2021 Machine learning involves the task of training systems to be able to make decisions without being explicitly programmed. Important among machine learning tasks is classification involving the process of training machines to make predictions from predefined labels. Classification is broadly categorized into three distinct groups: single-label (SL), multi-class, and multi-label (ML) classification. This research work presents an application of a multi-label classification (MLC) technique in automating Quranic verses labeling. MLC has been gaining attention in recent years. This is due to the increasing amount of works based on real-world classification problems of multi-label data. In traditional classification problems, patterns are associated with a single-label from a set of disjoint labels. However, in MLC, an instance of data is associated with a set of labels. In this paper, three standard MLC methods: binary relevan...
Indian Journal of Computer Science and Engineering, 2021
Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used fo... more Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)are comp...
Indonesian Journal of Electrical Engineering and Computer Science
Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) ... more Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) classification. High classification accuracy has been achieved by extracting deep features from both spatial-spectral channels. However, the efficiency of such spatial-spectral approaches depends on the spatial dimension of each patch and there is no theoretically valid approach to find the optimum spatial dimension to be considered. It is more valid to extract spatial features by considering varying neighborhood scales in spatial dimensions. In this regard, this article proposes a deep convolutional neural network (CNN) model wherein three different multi-scale spatial-spectral patches are used to extract the features in both the spatial and spectral channels. In order to extract these potential features, the proposed deep learning architecture takes three patches various scales in spatial dimension. 3D convolution is performed on each selected patch and the process runs through entire ...
2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)
Hyperspectral image consists of huge spectral and special information. Deep learning models, such... more Hyperspectral image consists of huge spectral and special information. Deep learning models, such as deep convolutional neural networks (CNNs) being widely used for HSI classification. Most of the approaches are based on 2D CNN. Whereas, the HSI classification performance depends on both spatial and spectral information. This paper proposes a new 3D-Deep Feature Extraction CNN model for the HSI classification which uses both spectral and spatial information. Here the HSI data is divided into 3D patches and fed into the proposed model for deep feature extractions. Experimental results show that the performance of HSI classification is improved significantly with the proposed model. The experimental results on the publicly available HSI datasets, viz., Indian Pines(IP), Pavia University scene(PU) and Salinas scene(SA), are compared with the contemporary models. The current results indicates that the proposed model provides comparatively better results than the state-of-the-art methods.