Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
•Introduction of deep learning techniques to handwritten Bangla compound character recognition.•Development of a novel supervised layerwise trained Deep Convolutional Neural Network.•Augmenting with RMSProp to achieve fast convergence and higher generalization.•Establishing a benchmark on the CMATERdb 3.1.3.3 Bangla compound character dataset.•A significant reduction of error rate from 19% to 9.67% on the dataset.
[Display omitted]
In this work, a novel deep learning technique for the recognition of handwritten Bangla isolated compound character is presented and a new benchmarkof recognition accuracy on the CMATERdb 3.1.3.3 dataset is reported. Greedy layer wise training of Deep Neural Network has helped to make significant strides in various pattern recognition problems. We employ layerwise training to Deep Convolutional Neural Networks (DCNN) in a supervised fashion and augment the training process with the RMSProp algorithm to achieve faster convergence. We compare results with those obtained from standard shallow learning methods with predefined features, as well as standard DCNNs. Supervised layerwise trained DCNNs are found to outperform standard shallow learning models such as Support Vector Machines as well as regular DCNNs of similar architecture by achieving error rate of 9.67% thereby setting a new benchmark on the CMATERdb 3.1.3.3 with recognition accuracy of 90.33%, representing an improvement of nearly 10%.