Ground-truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

被引：1

作者：

Elarian, Yousef ^{[1
]}

Zidouri, Abdelmalek ^{[1
]}

Al-Khatib, Wasfi ^{[1
]}

机构：

[1] King Fahd Univ Petr & Minerals, Dhahran 31261, Saudi Arabia

来源：

2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR) | 2014年

关键词：

segmentation; entropy-based metric; Arabic handwriting; ground-truth; IMAGE SEGMENTATION;

D O I：

10.1109/ICFHR.2014.134

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a character-level ground truth for an Arabic dataset of 8,640 character-shapes along with an evaluation metric that is adapted from image segmentation. These tools together constitute a benchmark for character-segmentation. We demonstrate the use of this benchmark on some segmentation algorithms and report their quantitative results in bits. Our approach can be extended to other scripts.

引用

下载

页码：766 / 770

页数：5

共 50 条

[1] Automatic Line Segmentation and Ground-Truth Alignment of Handwritten Documents
Bluche, Theodore
Moysset, Bastien
Kermorvant, Christopher
2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 667 - 672
[2] A Ground-Truth Fusion Method for Image Segmentation Evaluation
Malladi, Sree Ramya S. P.
Ram, Sundaresh
Rodriguez, Jeffrey J.
2018 IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION (SSIAI), 2018, : 137 - 140
[3] Objective Performance Evaluation of Video Segmentation Algorithms with Ground-Truth
杨高波
张兆扬
Advances in Manufacturing, 2004, (01) : 70 - 74
[4] A Public Ground-Truth Dataset for Handwritten Circuit Diagram Images
Thoma, Felix
Bayer, Johannes
Li, Yakun
Dengel, Andreas
DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021 WORKSHOPS, PT I, 2021, 12916 : 20 - 27
[5] Offline handwritten arabic character segmentation with probabilistic model
Xiu, PP
Peng, LR
Ding, XQ
Wang, H
DOCUMENT ANALYSIS SYSTEMS VII, PROCEEDINGS, 2006, 3872 : 402 - 412
[6] Metrics for performance evaluation of video object segmentation and tracking without ground-truth
Erdem, CE
Tekalp, AM
Sankur, B
2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS, 2001, : 69 - 72
[7] Matching based ground-truth annotation for online handwritten mathematical expressions
Hirata, Nina S. T.
Julca-Aguilar, Frank D.
PATTERN RECOGNITION, 2015, 48 (03) : 837 - 848
[8] COALIA: a ground-truth for the evaluation of the EEG source connectivity
Allouch, Sahar
Hassan, Mahmoud
Yochum, Maxime
Duprez, Joan
Khalil, Mohamad
Wendling, Fabrice
Modolo, Julien
Kabbara, Aya
2021 SIXTH INTERNATIONAL CONFERENCE ON ADVANCES IN BIOMEDICAL ENGINEERING (ICABME), 2021, : 180 - 183
[9] Qualitative Tracking Performance Evaluation without Ground-Truth
Han, Bohyung
Hamm, Jihun
2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2015, : 55 - 62
[10] Normalized Joint Mutual Information Measure for Image Segmentation Evaluation with Multiple Ground-Truth Images
Bai, Xue
Zhao, Yibiao
Huang, Yaping
Luo, Siwei
COMPUTER ANALYSIS OF IMAGES AND PATTERNS: 14TH INTERNATIONAL CONFERENCE, CAIP 2011, PT I, 2011, 6854 : 110 - 117

← 1 2 3 4 5 →