Semi-automatic feature based approach for sketch to image matching
Loading...
Date
2015
Journal Title
Journal ISSN
Volume Title
Publisher
University of Management and Technology
Abstract
A semi-automatic feature-based approach for sketch to image matching is presented which is used to achieve matching or recognition of sketch-based facial features to image-based facial features of human subjects. Loosely termed as ‘sketch to photo' matching, this problem is complicated by the wide possible variety of factors in both the sketches and the photos, some of which are angles, color, lighting and scale. Our proposed approach overcomes these difficulties by normalization of inputs and selection of some prominent and reliable features points. The basis of comparison between corresponding feature points is the ratio of Euclidean distances which makes the approach scale independent. The approach promises discernible improvements in accuracy and efficiency.
Description
Project advisor: Sir Syed Farooq Ali
Keywords
BS Thesis, Semi-automatic, Sketch to image matching