scholarly journals Two Methods to Improve Confidence Scores for Lexicon-Free Word Spotting in Handwritten Text

Author(s):  
Alejandro Hector Toselli ◽  
Joan Puigcerver ◽  
Enrique Vidal
2013 ◽  
Author(s):  
Nikos Vasilopoulos ◽  
Ergina Kavallieratou
Keyword(s):  

2018 ◽  
Vol 22 (1) ◽  
pp. 23-32 ◽  
Author(s):  
Alejandro H. Toselli ◽  
Enrique Vidal ◽  
Joan Puigcerver ◽  
Ernesto Noya-García

2019 ◽  
Vol 9 (2) ◽  
pp. 49-65
Author(s):  
Thontadari C. ◽  
Prabhakar C. J.

In this article, the authors propose a segmentation-free word spotting in handwritten document images using a Bag of Visual Words (BoVW) framework based on the co-occurrence histogram of oriented gradient (Co-HOG) descriptor. Initially, the handwritten document is represented using visual word vectors which are obtained based on the frequency of occurrence of Co-HOG descriptor within local patches of the document. The visual word representation vector does not consider their spatial location and spatial information helps to determine a location exclusively with visual information when the different location can be perceived as the same. Hence, to add spatial distribution information of visual words into the unstructured BoVW framework, the authors adopted spatial pyramid matching (SPM) technique. The performance of the proposed method evaluated using popular datasets and it is confirmed that the authors' method outperforms existing segmentation free word spotting techniques.


Sign in / Sign up

Export Citation Format

Share Document