2018/12/14 by Al Mehdi Saadat Chowdhury, Chowdhury, Al Mehdi Saadat, M. Shahidur Rahman +7
Computer Science · Mathematics · #Digital Media Forensic Detection #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1812.05758
arxiv created 2018/12/14 · openalex publication_date 2018/12/14 · arxiv updated 2018/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This work attempts to find the most optimal parameter setting of a deep artificial neural network (ANN) for Bengali digit dataset by pre-training it using stacked denoising autoencoder (SDA). Although SDA based recognition is hugely popular in image, speech and language processing related tasks among the researchers, it was never tried in Bengali dataset recognition. For this work, a dataset of 70000 handwritten samples were used from (Chowdhury and Rahman, 2016) and was recognized using several settings of network architecture. Among all these settings, the most optimal setting being found to be five or more deeper hidden layers with sigmoid activation and one output layer with softmax activation. We proposed the optimal number of neurons that can be used in the hidden layer is 1500 or more. The minimum validation error found from this work is 2.34% which is the lowest error rate on handwritten Bengali dataset proposed till date.