Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 14; p. 4648
• Main Authors: Kundu, Subhranil, Malakar, Samir, Geem, Zong Woo, Moon, Yoon Young, Singh, Pawan Kumar, Sarkar, Ram
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 07.07.2021; MDPI
• Subjects: Datasets; Digitization; dynamic time warping; Experimentation; Handwriting; handwritten word; Hough transform; Hough transformation; keyword spotting; Keywords; Performance evaluation; Queries; query by example; Taxonomy

Handwritten keyword spotting (KWS) is of great interest to the document image research community. In this work, we propose a learning-free keyword spotting method following query by example (QBE) setting for handwritten documents. It consists of four key processes: pre-processing, vertical zone divi...