Improving RANSAC-Based Segmentation Through CNN Encapsulation

Dustin Morley, Hassan Foroosh; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6338-6347

In this work, we present a method for improving a random sample consensus (RANSAC) based image segmentation algorithm by encapsulating it within a convolutional neural network (CNN). The improvements are gained by gradient descent training on the set of pre-RANSAC filtering and thresholding operations using a novel RANSAC-based loss function, which is geared toward optimizing the strength of the correct model relative to the most convincing false model. Thus, it can be said that our loss function trains the network on metrics that directly dictate the success or failure of the final segmentation rather than metrics that are merely correlated to the success or failure. We demonstrate successful application of this method to a RANSAC method for identifying the pupil boundary in images from the CASIA-IrisV3 iris recognition data set, and we expect that this method could be successfully applied to any RANSAC-based segmentation algorithm.