Chakrabarty, Dr. AmitabhaMostakim, MoinNivrito, AKMWahed, Md. Rayed Bin2016-09-082016-09-0820168/18/2016ID 16141024ID 12201020http://hdl.handle.net/10361/6397Cataloged from PDF version of thesis report.Includes bibliographical references (page 33-35).This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2016.In the last five years or so, Machine Learning has taken the world by storm. From predictive web browsing, to E-mail classification, to autonomous cars; machine learning is at the heart of every intelligent applications that’s in service today. Image Classification and Facial Expression Recognition is another field that has benefited immensely from the emergence of this technology. In particular, an branch of Machine Learning called Deep Learning, has shown tremendous results in this regard even outperforming more conventional methods such as Image Processing. Inspired by neurons in the human brain, Artificial Neural Networks, allow us to map complex functions by stacking layers upon layers of these networks. Our goal in this paper, is to analyze Inception v-3, the best performing high resolution image classifier based on Convolutional Neural Network out there today, with other methods including one of our own to see how it performs on low resolution images detect Facial Expressions.35 pagesenBRAC University thesis are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Inception-V3Facial expressions detectionThesis