Blar i NTNU Open på forfatter "De, Kanjar"
-
Effect of hue shift towards robustness of convolutional neural networks
De, Kanjar; Pedersen, Marius (Journal article; Peer reviewed, 2022) -
Efficient extraction of consistent bit locations from binarized iris features
Sadhya, Debanjan; De, Kanjar; Raman, Balasubramanian; Roy, Partha (Peer reviewed; Journal article, 2019)Biometric systems which are operationally based on human irides are considered to be an effective way of verifying individual identities. However, features extracted from iris images are sometimes characterized by a low ... -
Impact of Colour on Robustness of Deep Neural Networks
De, Kanjar; Pedersen, Marius (Journal article, 2021)Convolutional neural networks have become the most widely used tool for computer vision applications like image classification, segmentation, object localization, etc. Recent studies have shown that the quality of images ... -
Movie Recommendation System Using Sentiment Analysis from Microblogging Data
Kumar, Sudhanshu; De, Kanjar; Roy, Partha Pratim (Peer reviewed; Journal article, 2020)Recommendation systems (RSs) have garnered immense interest for applications in e-commerce and digital media. Traditional approaches in RSs include such as collaborative filtering (CF) and content-based filtering (CBF) ...