Nachricht

On Tuesday, December 5, Pranav Pravin Tondgaonkar will present the results of his master's thesis with the title:

Unsupervised Deep Learning-based Shape Retrieval using Invariant Contour Features

Abstract:

The objective of this work was to develop an unsupervised deep learning-based method for shape retrieval. The developed method uses specific scale- and rotation-invariant keypoints detected along the curvature extrema of object contours, which, according to information theory, are the most informative points. Each detected keypoint is described by a feature vector and has the following geometrical information: position, scale, and orientation. The similarity in shape between contour segments enclosed by these keypoints can pose challenges in distinguishing between objects. For this purpose, graphs are used to model the spatial arrangement of keypoints using their geometric information and feature vectors. The development of the method involves the creation of training data, the implementation of Graph Neural Network architectures, and shape retrieval. The retrieval results were systematically analyzed, and it was found that the representations become less distinct when the distribution of keypoints in the shape is uneven.