Convolutional neural networks performance comparison for handwritten Bengali numerals recognition

Abstract

Handwritten recognition has drawn profound attention since decades ago due to its numerous potential applications in real life. Research on unconstrained handwritten recognition in some languages has achieved attractive advancement, but it lags behind for Bengali even though it is the major language spoken by about 230 million people in the Indian subcontinent, and even the first and official language of Bangladesh. Recently, the use of convolutional neural network (CNN) has been reported with high accuracy in pattern recognition and computer vision problems. The main purpose of this study is to provide an architecture of a CNN to improve the accuracy of handwritten Bengali numerals recognition (HBNR) and compare its performance with the existing ones. We proposed a new CNN architecture, VGG-11M, which improves an existing one (VGG-11). The normalized and rescaled images of each numeral were augmented by different transformation operations to increase the training samples and to add diversity in the dataset. Then, the images were used to train the proposed VGG-11M model. The recognition accuracy of the developed system was tested on both training and test sets of three publicly available handwritten Bengali numerals database at different resolutions. Finally the performance of the model was compared with four other architectures (LeNet-5, ResNet-50, VGG-11, and VGG-16). The highest accuracy 99.80%, 99.66%, and 99.25% was obtained using the proposed architecture on the test set of ISI, CMATERDB, and NUMTADB dataset, respectively, at resolution 32 × 32. The proposed VGG-11M outperformed the existing architectures of CNN on HBNR.

Real-time recognition of spraying area for UAV sprayers using a deep learning approach

“…LeNet-5 is a classical CNN model developed by Yann Le Cun et al . for optical character recognition [ 35 , 37 ]. A typical LeNet-5 architecture is illustrated in Fig 11 .…”

“…The effect of convolutional depth on accuracy in image recognition problem was studied by Simonyan and Zisserman in 2014 and led to the introduction of a new model named Visual Geometry Group (VGG) [ 36 , 37 ]. One of this group’s special architecture includes VGG- 16, which was used for recognizing handwritten Bengali characters [ 38 ].…”

A novel semi-supervised framework for UAV based crop/weed classification

“…It was essential to validate the developed technique, for which a comparison was made with well-established classification techniques such as Support Vector Machine (SVM) [45], K-Nearest Neighbor (KNN) [46], CNN [47]. SVM, working on the principle of statistical learning theory, is a machine learning method that uses nonlinear kernel functions for mapping original input data into high dimensional features seeking separate hyperplane, and the data is optimally separated into two categories by using the constructed N-dimensional hyperplane [45].…”

“…CNN is a highly accurate technique normally used to classify images [48]. CNN has (8) and thirteen (13) convolutional layers, followed by three (3) fully connected layers and a single SoftMax layer [47]. LeNet5 is a classical CNN model consisting of seven convolutional layers [47].…”

“…CNN has (8) and thirteen (13) convolutional layers, followed by three (3) fully connected layers and a single SoftMax layer [47]. LeNet5 is a classical CNN model consisting of seven convolutional layers [47]. Whereas, ResNet18 and ResNet50 comprises of 18 and 50 convolutional layers followed by batch normalization and a ReLU activation function [49].…”