Showing 1–1 of 1 results for author: Yumoto, F

Handwriting Recognition with Novelty

Authors: Derek S. Prijatelj, Samuel Grieggs, Futoshi Yumoto, Eric Robertson, Walter J. Scheirer

Abstract: This paper introduces an agent-centric approach to handle novelty in the visual recognition domain of handwriting recognition (HWR). An ideal transcription agent would rival or surpass human perception, being able to recognize known and new characters in an image, and detect any stylistic changes that may occur within or across documents. A key confound is the presence of novelty, which has contin… ▽ More This paper introduces an agent-centric approach to handle novelty in the visual recognition domain of handwriting recognition (HWR). An ideal transcription agent would rival or surpass human perception, being able to recognize known and new characters in an image, and detect any stylistic changes that may occur within or across documents. A key confound is the presence of novelty, which has continued to stymie even the best machine learning-based algorithms for these tasks. In handwritten documents, novelty can be a change in writer, character attributes, writing attributes, or overall document appearance, among other things. Instead of looking at each aspect independently, we suggest that an integrated agent that can process known characters and novelties simultaneously is a better strategy. This paper formalizes the domain of handwriting recognition with novelty, describes a baseline agent, introduces an evaluation protocol with benchmark data, and provides experimentation to set the state-of-the-art. Results show feasibility for the agent-centric approach, but more work is needed to approach human-levels of reading ability, giving the HWR community a formal basis to build upon as they solve this challenging problem. △ Less

Submitted 17 May, 2021; v1 submitted 13 May, 2021; originally announced May 2021.

Comments: 16 pages, 3 Figures, 2 Tables, To be published in ICDAR 2021. Camera-ready version 1. Supplementary Material 22 pages, 4 Figures, 18 Tables. Moved novelty type examples from supp mat to main. Added brief explanation of usefulness of formalization. Added comment on joint information between transcription and style tasks in CRNN's encoding

ACM Class: I.7.5; I.5.4