A
Akshaya Mishra
Researcher at University of Waterloo
Publications - 52
Citations - 1625
Akshaya Mishra is an academic researcher from University of Waterloo. The author has contributed to research in topics: Image segmentation & Active contour model. The author has an hindex of 17, co-authored 51 publications receiving 1373 citations.
Papers
More filters
Proceedings ArticleDOI
Non-local Deep Features for Salient Object Detection
TL;DR: A simplified convolutional neural network which combines local and global information through a multi-resolution 4×5 grid structure is proposed which implements a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary, enabling near real-time, high performance saliency detection.
Journal ArticleDOI
Intra-retinal layer segmentation in optical coherence tomography images
TL;DR: Experimental results show that the proposed approach provides accurate segmentation for OCT images affected by speckle noise, even in sub-optimal conditions of low image contrast and presence of irregularly shaped structural features in the OCT images.
Journal ArticleDOI
General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery
TL;DR: A novel speckle noise reduction algorithm that projects the imaging data into the logarithmic space and a general Bayesian least squares estimate of the noise-free data is found using a conditional posterior sampling approach is developed.
Journal ArticleDOI
MIO-TCD: A new benchmark dataset for vehicle classification and localization.
Zhiming Luo,Frederic B-Charron,Carl Lemaire,Janusz Konrad,Shaozi Li,Akshaya Mishra,Andrew Achkar,Justin A. Eichel,Pierre-Marc Jodoin +8 more
TL;DR: This paper introduces the “Miovision traffic camera dataset” (MIO-TCD), the largest dataset for motorized traffic analysis to date, and demonstrates the viability of deep learning methods for vehicle localization and classification from a single video frame in real-life traffic scenarios.
Journal ArticleDOI
Decoupled Active Contour (DAC) for Boundary Detection
TL;DR: A decoupled active contour (DAC) is developed which applies the two energy terms separately and is found to be faster with better or comparable segmentation accuracy.