A protocol for performance evaluation of line detection algorithms
Machine Vision and Applications - Special issue on performance evaluation
Vector-Based Arc Segmentation in the Machine Drawing Understanding System Environment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Sparse Pixel Vectorization: An Algorithm and Its Performance Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Twenty Years of Document Image Analysis in PAMI
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Line Drawings Degradation Model for Performance Characterization
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Effective Multiresolution Arc Segmentation: Algorithms and Performance Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust and Accurate Vectorization of Line Drawings
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance characterization in computer vision: A guide to best practices
Computer Vision and Image Understanding
ARG Based on Arcs and Segments to Improve the Symbol Recognition by Genetic Algorithm
Graphics Recognition. Recent Advances and New Opportunities
GREC 2007 Arc Segmentation Contest: Evaluation of Four Participating Algorithms
Graphics Recognition. Recent Advances and New Opportunities
GREC'09 arc segmentation contest: performance evaluation on old documents
GREC'09 Proceedings of the 8th international conference on Graphics recognition: achievements, challenges, and evolution
Segmentation of nanocolumnar crystals from microscopic images
ICIAR'05 Proceedings of the Second international conference on Image Analysis and Recognition
Semi-automatic ground truth generation for chart image recognition
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
GREC'11 Proceedings of the 9th international conference on Graphics Recognition: new trends and challenges
| Hi-index | 0.14 |
We present an incremental arc segmentation algorithm, which recovers the vectorized arc fragments obtained by the vectorization of a piece of arc image in a stepwise fashion. Due to proper threshold selection and consistent checking of cocircularity of the assumed arc pieces, the algorithm accurately constructs arcs from the vector input. Nearly 200 synthetic arcs, ranging in radius from five to 50 pixels, in open angle from 1/8驴 to 2驴, and in thickness from one to nine pixels, are used in the experiments and evaluation. Parts of six real drawings, containing about 200 arcs, are also processed. The algorithm works well for arc segments greater than 10 pixels in radius, 驴/4 in angle, and one pixel in width.