Robust corner and tangent point detection for strokes with deep learning approach

Abstract

A robust corner and tangent point detection (CTPD) tool is critical for sketch-based engineering modeling. This paper proposes a robust CTPD approach for hand-drawn strokes with deep learning approach. Its robustness for users, stroke shapes and biased datasets is improved due to multiscaled point contexts and a vote scheme. Firstly, all stroke points are classified into segments by two deep learning networks, based on scaled point contexts which mimic human's perception. Then, a vote scheme is adopted to analyze the merge conditions and operations for adjacent segments. If most points agree with a stroke's type, this type is accepted. Finally, new corners and tangent points are inserted at transition points. The algorithm's performance is experimented with 1500 strokes of 20 shapes. Results show that our algorithm can achieve 95.3% for all-or-nothing accuracy and 88.6% accuracy for biased datasets, compared to 84.6% and 71% of the state-of-the-art CTPD technique, which is heuristic and empirical-based.