Handwritten Text Line Segmentation by Clustering with Distance Metric Learning

Separating text lines in handwritten documents remains a challenge because the text lines are often ununiformly skewed and curved. In this paper, we propose a novel text line segmentation algorithm based on Minimal Spanning Tree (MST) clustering with distance metric learning. Given a distance metric, the connected components of document image are grouped into a tree structure. Text lines are extracted by dynamically cutting the edges of the tree using a new objective function. For avoiding artificial parameters and improving the segmentation accuracy, we design the distance metric by supervised learning. Experiments on handwritten Chinese documents demonstrate the superiority of the approach.