Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection

TL;DR

This paper introduces a robust CNN-based edge detection method inspired by HED and Xception, capable of producing human-like thin edge maps without retraining, supported by a new annotated dataset and comprehensive evaluations.

Contribution

It presents a novel edge detection approach that works without prior training or fine-tuning and provides a new annotated dataset for benchmarking.

Findings

Improved F-measure scores on multiple benchmarks.

Generated a large, carefully annotated edge dataset.

Outperforms state-of-the-art edge detection algorithms.

Abstract

This paper proposes a Deep Learning based edge detector, which is inspired on both HED (Holistically-Nested Edge Detection) and Xception networks. The proposed approach generates thin edge-maps that are plausible for human eyes; it can be used in any edge detection task without previous training or fine tuning process. As a second contribution, a large dataset with carefully annotated edges has been generated. This dataset has been used for training the proposed approach as well the state-of-the-art algorithms for comparisons. Quantitative and qualitative evaluations have been performed on different benchmarks showing improvements with the proposed method when F-measure of ODS and OIS are considered.