2021/05/24 by Deng Li, Yue Wu, Li, Deng +3
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Infrastructure Maintenance and Monitoring #Vehicle License Plate Recognition
paper · pdf · doi:10.48550/arxiv.2105.11307
openalex publication_date 2021/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Handwritten Text Line Segmentation (HTLS) is a low-level but important task for many higher-level document processing tasks like handwritten text recognition. It is often formulated in terms of semantic segmentation or object detection in deep learning. However, both formulations have serious shortcomings. The former requires heavy post-processing of splitting/merging adjacent segments, while the latter may fail on dense or curved texts. In this paper, we propose a novel Line Counting formulation for HTLS -- that involves counting the number of text lines from the top at every pixel location. This formulation helps learn an end-to-end HTLS solution that directly predicts per-pixel line number for a given document image. Furthermore, we propose a deep neural network (DNN) model LineCounter to perform HTLS through the Line Counting formulation. Our extensive experiments on the three public datasets (ICDAR2013-HSC, HIT-MW, and VML-AHTE) demonstrate that LineCounter outperforms state-of-the-art HTLS approaches. Source code is available at https://github.com/Leedeng/Line-Counter.