Inicio  /  Future Internet  /  Vol: 13 Par: 9 (2021)  /  Artículo
ARTÍCULO
TITULO

A Fusion-Based Hybrid-Feature Approach for Recognition of Unconstrained Offline Handwritten Hindi Characters

Danveer Rajpal    
Akhil Ranjan Garg    
Om Prakash Mahela    
Hassan Haes Alhelou and Pierluigi Siano    

Resumen

Hindi is the official language of India and used by a large population for several public services like postal, bank, judiciary, and public surveys. Efficient management of these services needs language-based automation. The proposed model addresses the problem of handwritten Hindi character recognition using a machine learning approach. The pre-trained DCNN models namely; InceptionV3-Net, VGG19-Net, and ResNet50 were used for the extraction of salient features from the characters? images. A novel approach of fusion is adopted in the proposed work; the DCNN-based features are fused with the handcrafted features received from Bi-orthogonal discrete wavelet transform. The feature size was reduced by the Principal Component Analysis method. The hybrid features were examined with popular classifiers namely; Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). The recognition cost was reduced by 84.37%. The model achieved significant scores of precision, recall, and F1-measure?98.78%, 98.67%, and 98.69%?with overall recognition accuracy of 98.73%.

Palabras claves

 Artículos similares

       
 
Merve Keskin, Vassilios Krassanakis and Arzu Çöltekin    
This study investigates how expert and novice map users? attention is influenced by the map design characteristics of 2D web maps by building and sharing a framework to analyze large volumes of eye tracking data. Our goal is to respond to the following r... ver más

 
Manar M. F. Donia, Wessam H. El-Behaidy and Aliaa A. A. Youssif    
The study of human behaviors aims to gain a deeper perception of stimuli that control decision making. To describe, explain, predict, and control behavior, human behavior can be classified as either non-aggressive or anomalous behavior. Anomalous behavio... ver más

 
Tahir Mehmood, Ivan Serina, Alberto Lavelli, Luca Putelli and Alfonso Gerevini    
Biomedical named entity recognition (BioNER) is a preliminary task for many other tasks, e.g., relation extraction and semantic search. Extracting the text of interest from biomedical documents becomes more demanding as the availability of online data is... ver más
Revista: Future Internet

 
Minghui Sha, Dewu Wang, Fei Meng, Wenyan Wang and Yu Han    
With the increasing complexity of radar jamming threats, accurate and automatic jamming recognition is essential but remains challenging. Conventional algorithms often suffer from sharply decreased recognition accuracy under low jamming-to-noise ratios (... ver más
Revista: Future Internet

 
Omar Adel, Karma M. Fathalla and Ahmed Abo ElFarag    
Emotion recognition is crucial in artificial intelligence, particularly in the domain of human?computer interaction. The ability to accurately discern and interpret emotions plays a critical role in helping machines to effectively decipher users? underly... ver más