Engineering Commons^™

Face Centered Image Analysis Using Saliency And Deep Learning Based Techniques, Rui Guo

Doctoral Dissertations

Image analysis starts with the purpose of configuring vision machines that can perceive like human to intelligently infer general principles and sense the surrounding situations from imagery. This dissertation studies the face centered image analysis as the core problem in high level computer vision research and addresses the problem by tackling three challenging subjects: Are there anything interesting in the image? If there is, what is/are that/they? If there is a person presenting, who is he/she? What kind of expression he/she is performing? Can we know his/her age? Answering these problems results in the saliency-based object detection, deep learning structured …

Improvements To Tracking Pedestrians In Video Streams Using A Pre-Trained Convolutional Neural Network, Marjan Ramin

Electronic Thesis and Dissertation Repository

Safety has been a very crucial aspect in our lives and much attention has been paid to this issue since we need to remain safe everywhere.

In 2010, about 270,000 pedestrians were killed on the roads globally, which shows the importance of investigation of different approaches to reduce traffic fatalities.

One way to decrease the number of car accidents with pedestrians is to equip vehicles with cameras that detect and track pedestrians in the road. Many applications have been presented to improve the performance of pedestrian tracking.

However, it has remained a very challenging topic over the past few decades. …

Visualization Of Deep Convolutional Neural Networks, Dingwen Li

McKelvey School of Engineering Theses & Dissertations

Deep learning has achieved great accuracy in large scale image classification and scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a classification result is achieved. The objective of this thesis is to explore several existing visualization approaches which offer intuitive visual results. The thesis focuses on three visualization approaches: (1) image masking which highlights the region of image with high influence on the classification, (2) Taylor decomposition back-propagation which generates a per pixel heat map that describes each pixel's …