Electrical Engineering / Computer Science Researcher
We implemented the auto-completion system in Python, to classify sketched symbols before they are fully completed. This system is a sketch auto-completion framework which classifies the partial drawings by learning visual appearances of partial drawings through semi-supervised clustering, followed by a supervised classification step that determines object classes.
We proposed techniques which use whole pixels of a face to improve alignment in a Face Recognition Systems. These algorithms extract interior information of each face by image processing features and utilize whole pixels’ information to strengthen the alignment algorithms.
"Even if you are on the right track, you will get run over if you just set there."