Digit Recognition in Handwritten Weather Records

TL;DR

This paper presents a system for recognizing handwritten temperature digits in weather records, combining line detection, stroke-preserving line removal, and SVM-based digit classification, achieving high accuracy on multiple datasets.

Contribution

It introduces a novel approach for localizing and recognizing handwritten digits in weather records, including a new line removal method and evaluation on real weather data.

Findings

Achieved 99.36% digit accuracy on weather records

Effective line removal method improves digit recognition

System performs well on MNIST, USPS, and weather datasets

Abstract

This paper addresses the automatic recognition of handwritten temperature values in weather records. The localization of table cells is based on line detection using projection profiles. Further, a stroke-preserving line removal method which is based on gradient images is proposed. The presented digit recognition utilizes features which are extracted using a set of filters and a Support Vector Machine classifier. It was evaluated on the MNIST and the USPS dataset and our own database with about 17,000 RGB digit images. An accuracy of 99.36% per digit is achieved for the entire system using a set of 84 weather records.