2018/02/03 by Mahmoud Afifi, Afifi, Mahmoud
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis #Image Processing Techniques and Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1802.01009
arxiv created 2018/02/03 · openalex publication_date 2018/02/03 · arxiv updated 2018/02/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Image posterization is converting images with a large number of tones into synthetic images with distinct flat areas and a fewer number of tones. In this technical report, we present the implementation and results of using fuzzy logic in order to generate a posterized image in a simple and fast way. The image filter is based on fuzzy logic and bilateral filtering; where, the given image is blurred to remove small details. Then, the fuzzy logic is used to classify each pixel into one of three specific categories in order to reduce the number of colors. This filter was developed during building the Specs on Face dataset in order to add a new level of difficulty to the original face images in the dataset. This filter does not hurt the human detection performance; however, it is considered a hindrance evading the face detection process. This filter can be used generally for posterizing images, especially those have a high contrast to get images with vivid colors.