Engineering Commons^™

Video Annotation By Crowd Workers With Privacy-Preserving Local Disclosure, Apeksha Dipak Kumavat

Open Access Theses

Advancements in computer vision are still not reliable enough for detecting video content including humans and their actions. Microtask crowdsourcing on task markets such as Amazon Mechnical Turk and Upwork can bring humans into the loop. However, engaging crowd workers to annotate non-public video footage risks revealing the identities of people in the video who may have a right to anonymity.

This thesis demonstrates how we can engage untrusted crowd workers to detect behaviors and objects, while robustly concealing the identities of all faces. We developed a web-based system that presents obfuscated videos to crowd workers, and provides them with …

Image Quality Estimation: Soft-Ware For Objective Evaluation, He Liu

Open Access Theses

Digital images are widely used in our daily lives and the quality of images is important to the viewing experience. Low quality images may be blurry or contain noise or compression artifacts. Humans can easily estimate image quality, but it is not practical to use human subjects to measure image quality in real applications. Image Quality Estimators (QE) are algorithms that evaluate image qualities automatically. These QEs compute scores of any input images to represent their qualities. This thesis mainly focuses on evaluating the performance of QEs. Two approaches used in this work are objective software analysis and the subjective …