Deep Active Contours

Abstract

We propose a method for interactive boundary extraction which combines a deep, patch-based representation with an active contour framework. We train a class-specific convolutional neural network which predicts a vector pointing from the respective point on the evolving contour towards the closest point on the boundary of the object of interest. These predictions form a vector field which is then used for evolving the contour by the Sobolev active contour framework proposed by Sundaramoorthi et al. The resulting interactive segmentation method is very efficient in terms of required computational resources and can even be trained on comparatively small graphics cards. We evaluate the potential of the proposed method on both medical and non-medical challenge data sets, such as the STACOM data set and the PASCAL VOC 2012 data set.

References in corpus (2)

• Learning Deconvolution Network for Semantic Segmentation
• Monocular Object Instance Segmentation and Depth Ordering with CNNs

Cited by in corpus (11)

• A Survey on Deep Learning in Medical Image Analysis
• Learning deep structured active contours end-to-end
• Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
• End to End Trainable Active Contours via Differentiable Rendering
• Simultaneous Edge Alignment and Learning
• Contour Transformer Network for One-shot Segmentation of Anatomical Structures
• Solar Potential Analysis of Rooftops Using Satellite Imagery
• Deep Active Contours Using Locally Controlled Distance Vector Flow
• DeepStrip: High Resolution Boundary Refinement
• The Deep Poincaré Map: A Novel Approach for Left Ventricle Segmentation
• Deep learning for image segmentation: veritable or overhyped?