N
Niladri B. Puhan
Researcher at Indian Institute of Technology Bhubaneswar
Publications - 107
Citations - 1186
Niladri B. Puhan is an academic researcher from Indian Institute of Technology Bhubaneswar. The author has contributed to research in topics: Feature extraction & Adaptive filter. The author has an hindex of 15, co-authored 92 publications receiving 837 citations. Previous affiliations of Niladri B. Puhan include International Institute of Information Technology & Nanyang Technological University.
Papers
More filters
Journal ArticleDOI
FoodNet: Recognizing Foods Using Ensemble of Deep Networks
TL;DR: In this paper, a multilayered convolutional neural network (CNN) pipeline was developed to take advantage of the features from other deep networks and improve the efficiency of food recognition.
Journal ArticleDOI
FoodNet: Recognizing Foods Using Ensemble of Deep Networks
TL;DR: Experimental results on the largest real-world food recognition database ETH Food-101 and newly contributed Indian food image database demonstrate the effectiveness of the proposed methodology as compared to many other benchmark deep learned CNN frameworks.
Journal ArticleDOI
Iris recognition on edge maps
TL;DR: A new measure, namely local partial Hausdorff, is computed directly on the binary edge features of the normalized iris images, which indicates high recognition performance of the proposed method.
Journal ArticleDOI
Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density
TL;DR: Performance studies on a recently created iris database, called UBIRIS, containing defocused, reflection-contained and eyelid-occluded iris images in visible spectral range, show that the proposed method is much faster than the existing methods and simultaneously achieves good segmentation accuracy.
Journal ArticleDOI
Deep residual network with regularised fisher framework for detection of melanoma
TL;DR: A deep convolutional neural network-based regularised discriminant learning framework which extracts low-dimensional discriminative features for melanoma detection is proposed and minimises the whole of within-class variance information and maximises the total class variance information.