Summary of Banglanet: Bangla Handwritten Character Recognition Using Ensembling Of Convolutional Neural Network, by Chandrika Saha et al.
BanglaNet: Bangla Handwritten Character Recognition using Ensembling of Convolutional Neural Network
by Chandrika Saha, Md Mostafijur Rahman
First submitted to arxiv on: 16 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel classification model, BanglaNet, is proposed to recognize Bangla handwritten characters, including basic characters, compound characters, numerals, and modifiers. This ensembled model combines the predictions of several Convolutional Neural Networks (CNN) inspired by state-of-the-art models like Inception, ResNet, and DenseNet. The models are trained on both augmented and non-augmented inputs, and their outputs are averaged to achieve high recognition accuracies. The proposed approach is evaluated on three benchmark datasets, CMATERdb, BanglaLekha-Isolated, and Ekush, achieving top-1 recognition accuracies of 98.40%, 97.65%, and 97.32%, respectively. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a new way to recognize handwritten Bangla characters. This is important because it can help machines understand written text in Bangla. The team used special kinds of computer programs called Convolutional Neural Networks (CNN) to make this happen. They combined the results from several different CNNs and tested them on lots of examples of handwritten Bangla characters. The results were very good, with an accuracy rate of over 97% on some datasets. |
Keywords
* Artificial intelligence * Classification * Cnn * Resnet
