Handwritten character recognition is a crucial task because of its abundant applications. The recognition task of Bangla handwritten characters is especially challenging because of the cursive nature of Bangla characters and the presence of compound characters with more than one way of writing. In this paper, a classification model based on the ensembling of several Convolutional Neural Networks (CNN), namely, BanglaNet is proposed to classify Bangla basic characters, compound characters, numerals, and modifiers. Three different models based on the idea of state-of-the-art CNN models like Inception, ResNet, and DenseNet have been trained with both augmented and non-augmented inputs. Finally, all these models are averaged or ensembled to get the finishing model. Rigorous experimentation on three benchmark Bangla handwritten characters datasets, namely, CMATERdb, BanglaLekha-Isolated, and Ekush has exhibited significant recognition accuracies compared to some recent CNN-based research. The top-1 recognition accuracies obtained are 98.40%, 97.65%, and 97.32%, and the top-3 accuracies are 99.79%, 99.74%, and 99.56% for CMATERdb, BanglaLekha-Isolated, and Ekush datasets respectively.

翻译：手写字符识别因其广泛的应用而成为一项关键任务。孟加拉手写字符的识别尤为具有挑战性，原因在于其字符的连笔特性以及存在多种书写方式的复合字符。本文提出了一种基于多个卷积神经网络（CNN）集成的分类模型，命名为BanglaNet，用于对孟加拉基本字符、复合字符、数字及修饰符进行分类。基于当前先进的CNN模型（如Inception、ResNet和DenseNet）的思想，训练了三种不同模型，分别使用增强和未增强的输入。最后，对这些模型进行平均或集成以得到最终模型。在三个基准孟加拉手写字符数据集（即CMATERdb、BanglaLekha-Isolated和Ekush）上的严格实验表明，与近期基于CNN的研究相比，所提方法取得了显著的识别准确率。在CMATERdb、BanglaLekha-Isolated和Ekush数据集上，Top-1识别准确率分别达到98.40%、97.65%和97.32%，Top-3准确率分别达到99.79%、99.74%和99.56%。