Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Image Manipulation Detection Using Augmentation and Convolutional Neural Networks(Springer Science and Business Media Deutschland GmbH, 2024) Maheshwari, A.; Jain, R.; Mahapatra, R.; Palakuru, S.; Anand Kumar, M.A.Image tampering is now simpler than ever, thanks to the explosion of digital photos and the creation of easy image modification tools. As a result, if the situation is not handled properly, the major problems may arise. Many computer vision and deep learning strategies have been put out over the years to address the problem. Having said that, people can easily recognize the photographs that were used in that research. This begs the key question of how CNNs might do on more difficult samples. In this chapter, we build a complex CNN network and use various machine learning algorithms to classify the images and compare the accuracies obtained by them. Its performance is also compared on two different datasets. Additionally, we assess the impact of various hyperparameters and a data augmentation strategy on classification performance. This leads to a conclusion that performance can be considerably impacted by dataset difficulty. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item An Efficient AI-Based Classification of Semiconductor Wafer Defects using an Optimized CNN Model(Institute of Electrical and Electronics Engineers Inc., 2023) Pandey, C.; Bhat, K.G.Wafer maps used to display defect patterns in the integrated circuits industry include crucial information that quality engineers may utilize to identify the cause of a defect and increase yield. In this paper, we put forth a framework for accurately and quickly categorizing semiconductor wafer faults utilizing particularly CNN-based models. This paper seeks to provide a scalable, adaptive, and user-friendly implementation of convolutional neural networks for applications classifying semiconductor defects. In categorizing the defects found on semiconductor wafers, the suggested CNN model obtained an accuracy of 90.50% & 92.28% and losses of 0.39 & 0.29 while performing the training and validation, respectively, along with the misclassification rate of 0.0772. The suggested model also learns rapidly on the validation set at a rate of 1e-03 per second. The proposed custom CNN model architecture incorporates only two convolution layers, resulting in a greatly reduced number of parameter weights and biases. Specifically, the number of parameters is only 44000, which makes the model more compact, cost-effective, and robust against random noise. Moreover, this model can function well under low power and processing limits. © 2023 IEEE.Item Deep learning ensemble method for classification of satellite hyperspectral images(Elsevier B.V., 2021) Iyer, P.; A, S.; Lal, S.Classification of hyperspectral image(HSI) is extensively utilized for the study of remotely sensed satellite images for various real-life applications. Convolutional Neural Networks (CNNs) are a commonly used deep learning technique for image data processing. The utilization of 2D CNNs and 3D CNNs have gained popularity in recent years for classification of hyperspectral image, and a lot of architectures with the combination of two have been proposed some of which include residual network based architectures. So, far individual models have been proposed and ensembling has not been explored much. In this paper, we propose an inception inspired architecture (IIA) and ensembled it with existing architectures HybridSN and inception residual network. The proposed IIA has 3D and 2D inception blocks which enable better spectral-spatial learning features. The Experiments are conducted on three well known publicly available HSI datasets and the results are compared to the state-of-the-art techniques. Experimental results yield that proposed deep learning ensemble method provides enhanced performance as compared to the state-of-the-art techniques. The python source code of the proposed method is available at https://github.com/shyamfec/DL-Ensemble-Method. © 2021 Elsevier B.V.