Recognizing Clothing Colors and Visual Textures Using a Finger-Mounted Camera
Alexander J. Medeiros, Lee Stearns, Leah Findlater, Chuan Chen, Jon E. Froehlich · 2017
We investigate clothing color and visual texture recognition using images from a finger-mounted camera to support people with visual impairments. Our approach mitigates issues with distance and lighting that can impact the accuracy of existing color and texture recognizers and allows for easy touch-based interrogation to better understand clothing appearance. We classify image textures by combining two off-the-shelf techniques commonly used for object recognition achieving 99.4% accuracy on a dataset of 520 clothing images across 9 texture categories. We close with a discussion of potential applications, user evaluation plans, and open questions.