Bio

Manan Aggarwal is a rising sophomore at Johns Hopkins University, where he is pursuing a bachelor’s degree in computer science. His fascination with computers began at an early age with a game of tic-tac-toe that his mother had coded for him. What started merely as an interest soon developed into a growing desire to understand how a collection of simple ideas and components interact with each other to produce an entity as complex and adaptable as a computer. Since then, he has written several programs for a variety of systems ranging from web servers to medical robots. He is currently developing his understanding of machine intelligence with the hope of ultimately applying this knowledge to transform human life. When he is not busy working on new projects, he can be found playing soccer, practicing yoga or preparing for outdoor expeditions.

Computational Essay: Moiré Pattern

Project: Morphing Using ANNs and Shape Interpolation

Project Overview

We succeeded in transforming the input images into the output images. To do this, we first segmented the region of interest, then found a one-to-one mapping between corresponding segments, and finally morphed the 2D space using the thin plate spline. The proposed technique works best for images that have low density of intersection points. This is because the radial basis function interpolation used in the algorithm tears the 2D space for overlapping vectors. This method does not extract features from the images, but rather exploits the curvature of the splines. The quality of the results obtained is also guided by the accuracy of the segmentation algorithm.