Record Details

Approximate Nearest Neighbour Field Computation and Applications

Electronic Theses of Indian Institute of Science

View Archive Info
 
 
Field Value
 
Title Approximate Nearest Neighbour Field Computation and Applications
 
Creator Avinash Ramakanth, S
 
Subject Digital Image Processing
Computer Vision
Optic Disc Detection
Video Object Segmentation
Approximate Nearest Neighbour Field (ANNF)
Optical Flow
PatchMatch
Super Resolution Imaging
Feature Match
Computer Science
 
Description Approximate Nearest-Neighbour Field (ANNF\ maps between two related images are commonly used by computer vision and graphics community for image editing, completion, retargetting and denoising. In this work we generalize ANNF computation to unrelated image pairs. For accurate ANNF map computation we propose Feature Match, in which the low-dimensional features approximate image patches along with global colour adaptation. Unlike existing approaches, the proposed algorithm does not assume any relation between image pairs and thus generalises ANNF maps to any unrelated image pairs. This generalization enables ANNF approach to handle a wider range of vision applications more efficiently. The following is a brief description of the applications developed using the proposed Feature Match framework.
The first application addresses the problem of detecting the optic disk from retinal images. The combination of ANNF maps and salient properties of optic disks leads to an efficient optic disk detector that does not require tedious training or parameter tuning. The proposed approach is evaluated on many publicly available datasets and an average detection accuracy of 99% is achieved with computation time of 0.2s per image. The second application aims to super-resolve a given synthetic image using a single source image as dictionary, avoiding the expensive training involved in conventional approaches. In the third application, we make use of ANNF maps to accurately propagate labels across video for segmenting video objects. The proposed approach outperforms the state-of-the-art on the widely used benchmark SegTrack dataset. In the fourth application, ANNF maps obtained between two consecutive frames of video are enhanced for estimating sub-pixel accurate optical flow, a critical step in many vision applications. Finally a summary of the framework for various possible applications like image encryption, scene segmentation etc. is provided.
 
Contributor Venkatesh Babu, R
 
Date 2018-05-09T16:07:23Z
2018-05-09T16:07:23Z
2018-05-09
2014
 
Type Thesis
 
Identifier http://etd.iisc.ernet.in/2005/3503
http://etd.iisc.ernet.in/abstracts/4370/G26634-Abs.pdf
 
Language en_US
 
Relation G26634