A probabilistic framework for handwritten text line segmentation

2018/05/07 by Francisco Cruz, Cruz, Francisco, Oriol Ramos Terrades +1
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1805.02536

47 pages, 23 images

arxiv created 2018/05/15 · arxiv updated 2018/05/16

Abstract

We successfully combine Expectation-Maximization algorithm and variational approaches for parameter learning and computing inference on Markov random felds. This is a general method that can be applied to many computer vision tasks. In this paper, we apply it to handwritten text line segmentation. We conduct several experiments that demonstrate that our method deal with common issues of this task, such as complex document layout or non-latin scripts. The obtained results prove that our method achieve state-of-the-art performance on different benchmark datasets without any particular fine tuning step.

Related

• Unsupervised deep learning for text line segmentation
• Text Line Segmentation for Challenging Handwritten Document Images Using Fully Convolutional Network
• LineCounter: Learning Handwritten Text Line Segmentation by Counting
• Unsupervised learning of text line segmentation by differentiating coarse patterns
• Line Segmentation from Unconstrained Handwritten Text Images using Adaptive Approach