HishabNet: Detection, Localization and Calculation of Handwritten Bengali Mathematical Expressions
This work addresses the challenge of automated evaluation of handwritten Bengali math expressions, which is incremental as it applies existing YOLOv3 to a new domain-specific dataset.
The authors tackled the problem of recognizing and evaluating handwritten Bengali mathematical expressions by proposing a CNN-based object detection model that detects digits and operators, constructs numbers, and performs operations, achieving a validation mAP of 98.6% and high classification accuracies on benchmark datasets.
Recently, recognition of handwritten Bengali letters and digits have captured a lot of attention among the researchers of the AI community. In this work, we propose a Convolutional Neural Network (CNN) based object detection model which can recognize and evaluate handwritten Bengali mathematical expressions. This method is able to detect multiple Bengali digits and operators and locate their positions in the image. With that information, it is able to construct numbers from series of digits and perform mathematical operations on them. For the object detection task, the state-of-the-art YOLOv3 algorithm was utilized. For training and evaluating the model, we have engineered a new dataset 'Hishab' which is the first Bengali handwritten digits dataset intended for object detection. The model achieved an overall validation mean average precision (mAP) of 98.6%. Also, the classification accuracy of the feature extractor backbone CNN used in our model was tested on two publicly available Bengali handwritten digits datasets: NumtaDB and CMATERdb. The backbone CNN achieved a test set accuracy of 99.6252% on NumtaDB and 99.0833% on CMATERdb.