Kirti Kirti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kirti Kirti has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Navin Rajpal
University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New-Delhi, India
4 shared publications - Virendra P. Vishwakarma
University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, New-Delhi, India
2 shared publications - Jyotsna Yadav
Guru Gobind Singh Indraprastha University
1 shared publication - Kalyan Kumar Mondal
ICAR-National Institute of Biotic Stress Management, Raipur, India
1 shared publication Mukta Arora
Ahir College Rewari
1 shared publicationNavin Rajpal
USICT, Guru Gobind Singh Indraprastha University
1 shared publication
Latest Publications
- Open Access
- 21 July 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-27
Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
- 21 July 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-27
Open AccessFusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
- Open Access
- 1 January 2023
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 32 (1)
Automatic adaptive weighted fusion of features-based approach for plant disease identification
With the rapid expansion in plant disease detection, there has been a progressive increase in the demand for more accurate systems. In this work, we propose a new method combining color information, edge information, and textural information to identify diseases in 14 different plants. A novel 3-branch architecture is proposed containing the color information branch, an edge information branch, and a textural information branch extracting the textural information with the help of the central difference convolution network (CDCN). ResNet-18 was chosen as the base architecture of the deep neural network (DNN). Unlike the traditional DNNs, the weights adjust automatically during the training phase and provide the best of all the ratios. The experiments were performed to determine individual and combinational features’ contribution to the classification process. Experimental results of the PlantVillage database with 38 classes show that the proposed method has higher accuracy, i.e., 99.23%, than the existing feature fusion methods for plant disease identification.
- 1 January 2023
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 32 (1)
Open AccessAutomatic adaptive weighted fusion of features-based approach for plant disease identification
With the rapid expansion in plant disease detection, there has been a progressive increase in the demand for more accurate systems. In this work, we propose a new method combining color information, edge information, and textural information to identify diseases in 14 different plants. A novel 3-branch architecture is proposed containing the color information branch, an edge information branch, and a textural information branch extracting the textural information with the help of the central difference convolution network (CDCN). ResNet-18 was chosen as the base architecture of the deep neural network (DNN). Unlike the traditional DNNs, the weights adjust automatically during the training phase and provide the best of all the ratios. The experiments were performed to determine individual and combinational features’ contribution to the classification process. Experimental results of the PlantVillage database with 38 classes show that the proposed method has higher accuracy, i.e., 99.23%, than the existing feature fusion methods for plant disease identification.
- Open Access
- 1 January 2023
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 32 (1)
A multi-crop disease identification approach based on residual attention learning
In this work, a technique is proposed to identify the diseases that occur in plants. The system is based on a combination of residual network and attention learning. The work focuses on disease identification from the images of four different plant types by analyzing leaf images of the plants. A total of four datasets are used for the work. The system incorporates attention-aware features computed by the Residual Attention Network (Res-ATTEN). The base of the network is ResNet-18 architecture. Integrating attention learning in the residual network helps improve the system's overall accuracy. Various residual attention units are combined to create a single architecture. Unlike the traditional attention network architectures, which focus only on a single type of attention, the system uses a mixed type of attention learning, i.e., a combination of spatial and channel attention. Our technique achieves state-of-the-art performance with the highest accuracy of 99%. The results show that the proposed system has performed well for both purposes and notably outperformed the traditional systems.
- 1 January 2023
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 32 (1)
Open AccessA multi-crop disease identification approach based on residual attention learning
In this work, a technique is proposed to identify the diseases that occur in plants. The system is based on a combination of residual network and attention learning. The work focuses on disease identification from the images of four different plant types by analyzing leaf images of the plants. A total of four datasets are used for the work. The system incorporates attention-aware features computed by the Residual Attention Network (Res-ATTEN). The base of the network is ResNet-18 architecture. Integrating attention learning in the residual network helps improve the system's overall accuracy. Various residual attention units are combined to create a single architecture. Unlike the traditional attention network architectures, which focus only on a single type of attention, the system uses a mixed type of attention learning, i.e., a combination of spatial and channel attention. Our technique achieves state-of-the-art performance with the highest accuracy of 99%. The results show that the proposed system has performed well for both purposes and notably outperformed the traditional systems.
- 21 December 2022
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 17 (2) , 1163-1183
Multi-resolution analysis and deep neural network architecture based hybrid feature extraction technique for plant disease identification and severity estimation
- 21 December 2022
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 17 (2) , 1163-1183
Multi-resolution analysis and deep neural network architecture based hybrid feature extraction technique for plant disease identification and severity estimation
- 12 October 2020
- Published by Springer Nature
- p. 659-670
Comparison of Texture Based Feature Extraction Techniques for Detecting Leaf Scorch in Strawberry Plant (Fragaria × Ananassa)
- 12 October 2020
- Published by Springer Nature
- p. 659-670
Comparison of Texture Based Feature Extraction Techniques for Detecting Leaf Scorch in Strawberry Plant (Fragaria × Ananassa)