Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges

TL;DR

This paper introduces realistic multi-digit writer (MDW) benchmarks for handwritten number recognition, highlighting the challenges and need for new methods beyond isolated digit classification.

Contribution

It creates new MDW datasets with task-specific metrics, emphasizing the gap between isolated digit accuracy and multi-digit recognition in real-world scenarios.

Findings

Classifiers perform well on isolated digits but poorly on multi-digit tasks.

MDW benchmarks enable development of methods leveraging task-specific knowledge.

Additional advances are necessary for effective real-world number recognition.

Abstract

Isolated digit classification has served as a motivating problem for decades of machine learning research. In real settings, numbers often occur as multiple digits, all written by the same person. Examples include ZIP Codes, handwritten check amounts, and appointment times. In this work, we leverage knowledge about the writers of NIST digit images to create more realistic benchmark multi-digit writer (MDW) data sets. As expected, we find that classifiers may perform well on isolated digits yet do poorly on multi-digit number recognition. If we want to solve real number recognition problems, additional advances are needed. The MDW benchmarks come with task-specific performance metrics that go beyond typical error calculations to more closely align with real-world impact. They also create opportunities to develop methods that can leverage task-specific knowledge to improve performance well beyond that of individual digit classification methods.