Offline MODI script character recognition using deep learning techniques

Deep learning is a multilayer neural network learning algorithm which emerged in recent years. It has brought a new wave to machine learning and making artificial intelligence and human-computer interaction spread with big strides. India is a heritage country where traditions, religions and languages are quite varied. MODI script is one of the oldest written forms of media. Most of the early written knowledge on subjects like medicine, Buddhist ideology, food habits and horoscope has been written using MODI script. MODI is one of the languages that present special challenge to OCR. The main challenge in MODI script is that it is mostly cursive and few characters look similar. The deep learning methods like InceptionV3 and RestNet on Modi script seems not experimented yet as per literature review. This motivates to apply the deep learning methods to offline handwritten character recognition using Residual and InceptionV3 framework. The handwritten Modi barakhadi dataset is prepared by collecting samples from around 25 different people. The dataset of size 7721 is experimented. The individual characters are cut and pre-processed using Otsu binarization technique. The performance evaluation of pre-processed data is done using both algorithms on the real-world handwritten character database written by different people. Processed images recognized through RestNet50 gives testing accuracy of 94.552% with precision of the model 0.86. Processed images recognized through InceptionV3 gives testing accuracy of 93.923% with precision of the model 0.843.