Seetharani Murugaiyan Jaisakthi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Seetharani Murugaiyan Jaisakthi has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Chandrabose Aravindan
SSN College of Engineering, Chennai, India
7 shared publications P. Mirunalini
Department of CSE, SSN College of Engineering, Chennai, India
5 shared publications- Palaniappan Mirunalini
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India
5 shared publications D. Thenmozhi
Department of CSE, SSN College of Engineering, Chennai, India
2 shared publications- Karthik Desingu
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India
2 shared publications - Mohanavalli Subramaniam
Sri Sivasubramaniya Nadar College of Engineering
2 shared publications
Latest Publications
- 27 May 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (26) , 16445-16463
Conditional adversarial segmentation and deep learning approach for skin lesion sub-typing from dermoscopic images
- 27 May 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (26) , 16445-16463
Conditional adversarial segmentation and deep learning approach for skin lesion sub-typing from dermoscopic images
- 15 June 2023
- Published by Springer Nature
- p. 71-78
Classification of Traffic Signal Images Using Deep Neural Networks
- 15 June 2023
- Published by Springer Nature
- p. 71-78
Classification of Traffic Signal Images Using Deep Neural Networks
- Top Cited Papers
- 12 October 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (10) , 15763-15778
Classification of skin cancer from dermoscopic images using deep neural network architectures
A powerful medical decision support system for classifying skin lesions from dermoscopic images is an important tool to prognosis of skin cancer. In the recent years, Deep Convolutional Neural Network (DCNN) have made a significant advancement in detecting skin cancer types from dermoscopic images, in-spite of its fine grained variability in its appearance. The main objective of this research work is to develop a DCNN based model to automatically classify skin cancer types into melanoma and non-melanoma with high accuracy. The datasets used in this work were obtained from the popular challenges ISIC-2019 and ISIC-2020, which have different image resolutions and class imbalance problems. To address these two problems and to achieve high performance in classification we have used EfficientNet architecture based on transfer learning techniques, which learns more complex and fine grained patterns from lesion images by automatically scaling depth, width and resolution of the network. We have augmented our dataset to overcome the class imbalance problem and also used metadata information to improve the classification results. Further to improve the efficiency of the EfficientNet we have used ranger optimizer which considerably reduces the hyper parameter tuning, which is required to achieve state-of-the-art results. We have conducted several experiments using different transferring models and our results proved that EfficientNet variants outperformed in the skin lesion classification tasks when compared with other architectures. The performance of the proposed system was evaluated using Area under the ROC curve (AUC - ROC) and obtained the score of 0.9681 by optimal fine tuning of EfficientNet-B6 with ranger optimizer.
- 12 October 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (10) , 15763-15778
Top Cited PapersClassification of skin cancer from dermoscopic images using deep neural network architectures
A powerful medical decision support system for classifying skin lesions from dermoscopic images is an important tool to prognosis of skin cancer. In the recent years, Deep Convolutional Neural Network (DCNN) have made a significant advancement in detecting skin cancer types from dermoscopic images, in-spite of its fine grained variability in its appearance. The main objective of this research work is to develop a DCNN based model to automatically classify skin cancer types into melanoma and non-melanoma with high accuracy. The datasets used in this work were obtained from the popular challenges ISIC-2019 and ISIC-2020, which have different image resolutions and class imbalance problems. To address these two problems and to achieve high performance in classification we have used EfficientNet architecture based on transfer learning techniques, which learns more complex and fine grained patterns from lesion images by automatically scaling depth, width and resolution of the network. We have augmented our dataset to overcome the class imbalance problem and also used metadata information to improve the classification results. Further to improve the efficiency of the EfficientNet we have used ranger optimizer which considerably reduces the hyper parameter tuning, which is required to achieve state-of-the-art results. We have conducted several experiments using different transferring models and our results proved that EfficientNet variants outperformed in the skin lesion classification tasks when compared with other architectures. The performance of the proposed system was evaluated using Area under the ROC curve (AUC - ROC) and obtained the score of 0.9681 by optimal fine tuning of EfficientNet-B6 with ranger optimizer.
- 19 August 2022
- Published by Springer Nature
- p. 759-770
Social Media Flood Image Classification Using Transfer Learning with EfficientNet Variants
- 19 August 2022
- Published by Springer Nature
- p. 759-770
Social Media Flood Image Classification Using Transfer Learning with EfficientNet Variants
- 12 December 2021
- Published by Springer Nature
- p. 167-174
Detection of Flooded Regions from Satellite Images Using Modified UNET
- 12 December 2021
- Published by Springer Nature
- p. 167-174
Detection of Flooded Regions from Satellite Images Using Modified UNET
- 20 December 2020
- Published by Scalable Computing: Practice and Experience in Scalable Computing: Practice and Experience
- Vol. 21 (4) , 625-635
Identification of Tomato Leaf Disease Detection using Pretrained Deep Convolutional Neural Network Models
In this paper, we proposed a plant leaf disease identification model based on a Pretrained deep convolutional neural network (Deep CNN). The Deep CNN model is trained using an open dataset with 10 different classes of tomato leaves We observed that overall architectures which can increase the best performance of the model. The proposed model was trained using different training epochs, batch sizes and dropouts. The Xception has attained maximum accuracy compare with all other approaches. After an extensive simulation, the proposed model achieves classification accuracy better. This accuracy of the proposed work is greater than the accuracy of all other Pretrained approaches. The proposed model is also tested with respect to its consistency and reliability. The set of data used for this work was collected from the plant village dataset, including sick and healthy images. Models for detection of plant disease should predict the disease quickly and accurately in the early stage itself so that a proper precautionary measures can be applied to avoid further spread of the diseases. So, to reduce the main issue about the leaf diseases, we can analyze distinct kinds of deep neural network architectures in this research. From the outcomes, Xception has a constantly improving more to enhance the accuracy by increasing the number of epochs, without any indications of overfitting and decrease in quality. And Xception also generated a fine 99.45% precision in less computing time.
- 20 December 2020
- Published by Scalable Computing: Practice and Experience in Scalable Computing: Practice and Experience
- Vol. 21 (4) , 625-635
Identification of Tomato Leaf Disease Detection using Pretrained Deep Convolutional Neural Network Models
In this paper, we proposed a plant leaf disease identification model based on a Pretrained deep convolutional neural network (Deep CNN). The Deep CNN model is trained using an open dataset with 10 different classes of tomato leaves We observed that overall architectures which can increase the best performance of the model. The proposed model was trained using different training epochs, batch sizes and dropouts. The Xception has attained maximum accuracy compare with all other approaches. After an extensive simulation, the proposed model achieves classification accuracy better. This accuracy of the proposed work is greater than the accuracy of all other Pretrained approaches. The proposed model is also tested with respect to its consistency and reliability. The set of data used for this work was collected from the plant village dataset, including sick and healthy images. Models for detection of plant disease should predict the disease quickly and accurately in the early stage itself so that a proper precautionary measures can be applied to avoid further spread of the diseases. So, to reduce the main issue about the leaf diseases, we can analyze distinct kinds of deep neural network architectures in this research. From the outcomes, Xception has a constantly improving more to enhance the accuracy by increasing the number of epochs, without any indications of overfitting and decrease in quality. And Xception also generated a fine 99.45% precision in less computing time.
- 27 September 2019
- Published by Springer Nature
- p. 85-94
Overview on Security Concerns Associated in Cloud Computing
- 27 September 2019
- Published by Springer Nature
- p. 85-94
Overview on Security Concerns Associated in Cloud Computing
- 28 March 2019
- Published by Taylor & Francis in Clinical and Experimental Optometry
- Vol. 102 (5) , 485-488
Quantification of corneal transparency in post‐mortem human corneas using laser scatter image analysis
Background The cornea is a highly transparent structure covering the anterior one‐fifth of the eyeball. The suitability of post‐mortem donor corneas for keratoplasty is currently qualitatively assessed. This makes inferences prone to bias and subjective variability. This study aimed to develop a simple, feasible and cost‐effective method to quantify corneal transparency. Methods An artificial anterior chamber was modified to provide a central transparent passage and a standardised pressure segment. All corneas graded ‘fair’ were included in this study. The corneoscleral buttons were mounted on the modified artificial anterior chamber. The mounted chamber was held in a horizontal position at a fixed distance from a white projection screen. The laser source was placed in alignment with an artificial anterior chamber so that it passed through the centre of the cornea. A camera mounted on a tripod stand was placed at a prefixed distance. An image of the scattered laser spot that formed after the laser passed through the mounted cornea on the screen was captured with a single digital camera and standardised settings. Image analysis was performed using ImageJ, an open platform for scientific image analysis. The average red pixel intensity, max intensity, and full‐width half max were calculated. Results The average red intensity was 132.45 ± 6.65 SD. The mean for max intensity was 51.1 ± 3.78 SD and the full‐width half max 787.7 ± 84.7 SD. Conclusion Laser quantification is a simple and cost‐effective method of quantifying corneal transparency. The study lends proof to the principle involved.
- 28 March 2019
- Published by Taylor & Francis in Clinical and Experimental Optometry
- Vol. 102 (5) , 485-488
Quantification of corneal transparency in post‐mortem human corneas using laser scatter image analysis
Background The cornea is a highly transparent structure covering the anterior one‐fifth of the eyeball. The suitability of post‐mortem donor corneas for keratoplasty is currently qualitatively assessed. This makes inferences prone to bias and subjective variability. This study aimed to develop a simple, feasible and cost‐effective method to quantify corneal transparency. Methods An artificial anterior chamber was modified to provide a central transparent passage and a standardised pressure segment. All corneas graded ‘fair’ were included in this study. The corneoscleral buttons were mounted on the modified artificial anterior chamber. The mounted chamber was held in a horizontal position at a fixed distance from a white projection screen. The laser source was placed in alignment with an artificial anterior chamber so that it passed through the centre of the cornea. A camera mounted on a tripod stand was placed at a prefixed distance. An image of the scattered laser spot that formed after the laser passed through the mounted cornea on the screen was captured with a single digital camera and standardised settings. Image analysis was performed using ImageJ, an open platform for scientific image analysis. The average red pixel intensity, max intensity, and full‐width half max were calculated. Results The average red intensity was 132.45 ± 6.65 SD. The mean for max intensity was 51.1 ± 3.78 SD and the full‐width half max 787.7 ± 84.7 SD. Conclusion Laser quantification is a simple and cost‐effective method of quantifying corneal transparency. The study lends proof to the principle involved.
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Grape Leaf Disease Identification using Machine Learning Techniques
Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. We have proposed an automatic system for detecting the diseases in the grape vines using image processing and machine learning technique. The system segments the leaf (Region of Interest) from the background image using grab cut segmentation method. From the segmented leaf part the diseased region is fruther segmented based on two different methods such as global thresholding and using semi-supervised technique. The features are extracted from the segmented diseased part and it has been classified as healthy, rot, esca, and leaf blight using different machine learning techniques such as Support Vector Machine (SVM), adaboost and Random Forest tree. Using SVM we have obtained a better testing accuracy of 93%.
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Grape Leaf Disease Identification using Machine Learning Techniques
Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. We have proposed an automatic system for detecting the diseases in the grape vines using image processing and machine learning technique. The system segments the leaf (Region of Interest) from the background image using grab cut segmentation method. From the segmented leaf part the diseased region is fruther segmented based on two different methods such as global thresholding and using semi-supervised technique. The features are extracted from the segmented diseased part and it has been classified as healthy, rot, esca, and leaf blight using different machine learning techniques such as Support Vector Machine (SVM), adaboost and Random Forest tree. Using SVM we have obtained a better testing accuracy of 93%.