Image matting is a longstanding problem in computational photography.Although, it has been studied for more than two decades, yet there is achallenge of developing an automatic matting algorithm which does not requireany human efforts. Most of the state-of-the-art matting algorithms requirehuman intervention in the form of trimap or scribbles to generate the alphamatte form the input image. In this paper, we present a simple and efficientapproach to automatically generate the trimap from the input image and make thewhole matting process free from human-in-the-loop. We use learning basedmatting method to generate the matte from the automatically generated trimap.Experimental results demonstrate that our method produces good quality trimapwhich results into accurate matte estimation. We validate our results byreplacing the automatically generated trimap by manually created trimap whileusing the same image matting algorithm.
展开▼