Publications by authors named "Ramachandra Raghavendra"
Lifestyle diseases significantly contribute to the global health burden, with lifestyle factors playing a crucial role in the development of depression. The COVID-19 pandemic has intensified many determinants of depression. This study aimed to identify lifestyle and demographic factors associated with depression symptoms among Indians during the pandemic, focusing on a sample from Kolkata, India.
View Article and Find Full Text PDFSmartphone-based biometric authentication has been widely used in various applications. Among several biometric characteristics, fingerphoto biometrics captured from smartphones are gaining popularity owing to their usability, scalability across different smartphones, and reliable verification. However, fingerphoto verification systems are vulnerable to both direct and indirect attacks.
View Article and Find Full Text PDFTaming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing.
IEEE Trans Neural Netw Learn Syst
August 2024
Article Synopsis
- Biometric systems are susceptible to manipulation through presentation attacks (PAs), which can be carried out using various presentation attack instruments (PAIs).
- Despite many detection methods for these attacks, ensuring they work effectively against unknown PAIs remains a significant challenge.
- The authors introduced a self-supervised learning approach called DF-DM that enhances the generalization of PA detection by leveraging both local and global feature representations, achieving notable performance improvements in existing datasets compared to previous methods.
A Conformable Moments-Based Deep Learning System for Forged Handwriting Detection.
IEEE Trans Neural Netw Learn Syst
April 2024
Article Synopsis
- Detecting forged handwriting is crucial for various machine learning applications, but it becomes difficult with noisy and blurry images.
- This article introduces a new model combining conformable moments (CMs) and deep ensemble neural networks (DENNs) to effectively identify different types of altered handwriting.
- The proposed method has been tested on both a new dataset of character-level handwritten alterations and several standard datasets, showing superior classification rates compared to existing approaches.
The deep learning models for the Single Image Super-Resolution (SISR) task have found success in recent years. However, one of the prime limitations of existing deep learning-based SISR approaches is that they need supervised training. Specifically, the Low-Resolution (LR) images are obtained through known degradation (for instance, bicubic downsampling) from the High-Resolution (HR) images to provide supervised data as an LR-HR pair.
View Article and Find Full Text PDF