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

Subhranil Kundu,Ram Sarkar,Yoon Young Moon,Samir Malakar,Pawan Kumar Singh,Zong Woo Geem

doi:10.3390/s21144648

Abstract

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 division, feature extraction, and feature matching. The pre-processing step deals with the noise found in the word images, and the skewness of the handwritings caused by the varied writing styles of the individuals. Next, the vertical zone division splits the word image into several zones. The number of vertical zones is guided by the number of letters in the query word image. To obtain this information (i.e., number of letters in a query word image) during experimentation, we use the text encoding of the query word image. The user provides the information to the system. The feature extraction process involves the use of the Hough transform. The last step is feature matching, which first compares the features extracted from the word images and then generates a similarity score. The performance of this algorithm has been tested on three publicly available datasets: IAM, QUWI, and ICDAR KWS 2015. It is noticed that the proposed method outperforms state-of-the-art learning-free KWS methods considered here for comparison while evaluated on the present datasets. We also evaluate the performance of the present KWS model using state-of-the-art deep features and it is found that the features used in the present work perform better than the deep features extracted using InceptionV3, VGG19, and DenseNet121 models.

Highlights

Automatic understanding of textual contents from handwritten document images is of great interest to researchers in the document-processing domain
This conversion helps in storing the information contained by the text in a compressed way, and assists in easy retrieval from a pool of such documents. Such efforts of obtaining the underlying machine-readable text from handwritten documents have opened up a new research domain known as handwritten text recognition (HTR)
The present work is aimed at segmentation-based, learning-free keyword searching through query by example (QBE)

Summary

Introduction

Automatic understanding of textual contents from handwritten document images is of great interest to researchers in the document-processing domain This is primarily due to the wide use of handwritten documents for communication from the ancient ages. Researchers are developing methods to convert the textual contents of handwritten document images into machine-encoded forms This conversion helps in storing the information contained by the text in a compressed way, and assists in easy retrieval from a pool of such documents. Such efforts of obtaining the underlying machine-readable text from handwritten documents have opened up a new research domain known as handwritten text recognition (HTR). Despite some notable success in HTR as found in the literature [1,2,3], many uncertain problems associated with

Methods

Results

Conclusion