2020 · 16 citations · 25 references
ComputingComputer ScienceArtificial IntelligenceComputer VisionMachine LearningDeep LearningImage ClassificationNeural NetworksObject RecognitionPattern RecognitionRepresentation LearningAccuracyConvolutional Neural NetworksDeep Image FeaturesDeep Learning-based ClassificationHandwritten Character Recognition
Handwritten Bangla digit recognition is one of the most challenging computer vision problems due to its diverse shapes and writing style. Recently deep learning based convolutional neural network known as deep CNN finds wide-spread applications in recognizing different objects due to its high accuracy. This paper investigates the performance of some state-of-the-art deep CNN techniques for the recognition of handwritten digits. It considers four deep CNN architectures, such as AlexNet, MobileNet, GoogLeNet (Inception V3), and CapsuleNet models. These four deep CNNs have been experimented on a large, unbiased and highly augmented standard dataset, NumtaDB and confirmed that the AlexNet showed the best performance on the basis of accuracy and computation time.
25
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard, Menglong Zhu, Bo Chen et al. · arXiv (Cornell University) · 2017 · 9.9K citations · Full text
Understanding of a convolutional neural network
Saad Albawi, Tareq Abed Mohammed, Saad Al-Azawi · 2017 · 4K citations
An Introduction to Convolutional Neural Networks
Keiron O’Shea, Ryan Nash · arXiv (Cornell University) · 2015 · 952 citations · Full text