2018/07/17 by Christian Tendyck, Tendyck, Christian, Andrew W. Haddad +4
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Art #Artificial intelligence #Computational photography #Computer Vision and Pattern Recognition (cs.CV) #Computer graphics (images) #Computer science #Computer vision #FOS: Computer and information sciences #Image (mathematics) #Image Enhancement Techniques #Image enhancement #Image processing #Multimedia (cs.MM) #Photography #Subject (documents) #Visual arts #World Wide Web #cs.CV #cs.MM
paper · pdf · doi:10.48550/arxiv.1807.06196
published in arXiv (Cornell University) (Cornell University)
arxiv created 2018/07/17 · openalex publication_date 2018/07/17 · arxiv updated 2018/07/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Camera display reflections are an issue in bright light situations, as they may prevent users from correctly positioning the subject in the picture. We propose a software solution to this problem, which consists in modifying the image in the viewer, in real time. In our solution, the user is seeing a posterized image which roughly represents the contour of the objects. Five enhancement methods are compared in a user study. Our results indicate that the problem considered is a valid one, as users had problems locating landmarks nearly 37% of the time under sunny conditions, and that our proposed enhancement method using contrasting colors is a practical solution to that problem.