Hair Segmentation Using Heuristically-Trained Neural Networks

Abstract

We present a method for binary classification using neural networks (NNs) that performs training and classification on the same data using the help of a pretraining heuristic classifier. The heuristic classifier is initially used to segment data into three clusters of high-confidence positives, high-confidence negatives, and low-confidence sets. The high… (More)
DOI: 10.1109/TNNLS.2016.2614653

18 Figures and Tables

Topics

  • Presentations referencing similar topics