Text Baseline Detection with Convolutional Neural Networks

Abstract

Often text lines must be localized and segmented before transcription. Detecting baselines is one way of localizing and deskewing text lines. We present a system for detecting baselines based on a Fully Convolutional Network (FCN) followed by post processing. We entered our system into the cBAD and HisDB competitions organized in conjunction with ICDAR 2017. We placed 3rd and 2nd on the simple and complex layout tracks of cBAD and 2nd on the HisDB baseline detection task.

Date
Location
Provo, Utah, USA
Links

Code to come.