CTC token parsing algorithm using keyword spotting for BLSTM based unconstrained handwritten recognition

Venkateswararao, Pinagadi; Murugavalli, S.

doi:10.1007/s12652-019-01458-0

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A technique that follows the former approach assumes that the document images have been already segmented into words or text lines through some page segmentation method [ 9 ]. The use of the page segmentation technique generates different inputs (i.e., text line or word) for the system, and accordingly, a segmentation-based KWS technique classified into two categories: (i) text line based technique, which locates a query word within pre-segmented text lines [ 10 , 11 ]; and (ii) word-based technique, which assumes the document image is already segmented into word images and, therefore, only focuses on matching the query word image with the target words [ 12 , 13 , 14 ]. On the other hand, methods that follow a segmentation-free approach do not require any prior page segmentation technique, i.e., these methods do not possess any knowledge about the document structure or any such similar templates [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

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

Kundu

Malakar²,

Geem

et al. 2021

Sensors

View full text Add to dashboard Cite

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.

show abstract