Convolutional neural network-based ensemble methods to recognize Bangla handwritten character

Abstract

In this era of advancements in deep learning, an autonomous system that recognizes handwritten characters and texts can be eventually integrated with the software to provide better user experience. Like other languages, Bangla handwritten text extraction also has various applications such as post-office automation, signboard recognition, and many more. A large-scale and efficient isolated Bangla handwritten character classifier can be the first building block to create such a system. This study aims to classify the handwritten Bangla characters. The proposed methods of this study are divided into three phases. In the first phase, seven convolutional neural networks i.e., CNN-based architectures are created. After that, the best performing CNN model is identified, and it is used as a feature extractor. Classifiers are then obtained by using shallow machine learning algorithms. In the last phase, five ensemble methods have been used to achieve better performance in the classification task. To systematically assess the outcomes of this study, a comparative analysis of the performances has also been carried out. Among all the methods, the stacked generalization ensemble method has achieved better performance than the other implemented methods. It has obtained accuracy, precision, and recall of 98.68%, 98.69%, and 98.68%, respectively on the Ekush dataset. Moreover, the use of CNN architectures and ensemble methods in large-scale Bangla handwritten character recognition has also been justified by obtaining consistent results on the BanglaLekha-Isolated dataset. Such efficient systems can move the handwritten recognition to the next level so that the handwriting can easily be automated.

Handwritten Grapheme Classification in Bengali Language Using MobileNet

“…Moreover, Animesh et al has come with a new architecture to identified isolated character and digit [11]. Similarly, Mir et al demonstrated ensemble approach on CNN model [12]. Nevertheless, we observed that these works, in particular, did not address the difficult small unit.…”

An integrated spatiotemporal-based methodology for deepfake detection

“…This is followed by a global average pooling layer. After that, the densely connected layers are added where the last one being the output layer [62]. In the Xception architecture, all convolution and separable convolution layers are followed by batch normalization layer.…”

Classification of breast cancer images using new transfer learning techniques

“…After the last block, there are two separable conv followed by a global average pooling (GAP) layer. After that, the fully connected (FC) layers are added with the last being the output layer" [23]. The Architecture of Xception model is shown in Fig.…”

“…Additionally, the presence of a global average pooling layer in place of a fully connected layer in the Xception model helps in preventing the problem of overfitting . [23]. Some modifications to the Xception architecture were made in two phases:…”