CALLIGRAPHY WORD IDENTIFICATION USING RECURRENT NEURAL NETWORKS
Author(s):
HELANA A
Keywords:
Calligraphy Word identification, LSTM dataset, Recurrent Neural networks, Tensor flow
Abstract
Calligraphy Word identification is a process of pattern recognition which defines ability of a system to identify word. There are many applications of Calligraphy Word identification (CWI) system such as reading postal addresses, bank check amounts, mail sorting and many more. CWI systems transfer human written text into digital text. Plenty of research done in the field of recognizing calligraphy words but lacking in best accuracy is a challenge. In this proposed technique, offline CWI is done using Recurrent Neural networks (RNN) and Tensor flow is proposed. RNNs have connections that form directed cycles, which allow the outputs from the LSTM to be fed as inputs to the current phase. The output from the LSTM becomes an input to the current phase and can memorize previous inputs due to its internal memory. RNNs are commonly used for image captioning, time-series analysis, natural-language processing, handwriting recognition, and machine translation. we were able to recognize the calligraphy word with highest accuracy. The experiment is performed on proposed technique with accuracy of 80.5% compared to the state-of-the-art.
Article Details
Unique Paper ID: 158807
Publication Volume & Issue: Volume 9, Issue 10
Page(s): 628 - 631
Article Preview & Download
Share This Article
Conference Alert
NCSST-2021
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2021
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT