Handwritten isolated Bangla compound character recognition: A new benchmark using a novel deep learning approach

Abstract

In this work, a novel deep learning technique for the recognition of handwritten Bangla isolated compound character is presented and a new benchmark of 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%.

Handwritten Indic Character Recognition using Capsule Networks

“…Finally N P C * N class number of routing weights must be tuned using agreement of individual and combined digit capsules. With all these, capsule networks generally have quite slow iterations, Roy et al [12] 90.33 Pal et al [13] 93.12 Sarkhel et al [14] 86.64 but as evident from Fig. IV it also learns much faster as compared to LeNet and AlexNet.…”

Using dynamic routing to extract intermediate features for developing scalable capsule networks

“…Convolutional Neural Networks(CNNs) have been around for almost two decades now. Since introduction in 1998 for digit classification problem [1] it took almost 14 years to improve them for more complicated problems [2], [3]. CNNs have grown deeper and got better in the field of visual recognition [4], [5], [6] .…”

“…Dynamic routing involves a weighted summation of primary capsules where the weights are iteratively updated during the forward proportional to the similarity between the individual activations and the combined activation. In the native work the network was demonstrated to perform well for 10 class problems like MNIST 1 , CIFAR-10 2 , SVHN 3 and so on. Capsule networks have also been shown to improve upon more complex networks like AlexNet for 1 http://yann.lecun.com/exdb/mnist/ 2 https://www.cs.toronto.edu/ kriz/cifar.html 3 http://ufldl.stanford.edu/housenumbers/ Indic character recognition [8].…”

Novel Model Based on Stacked Autoencoders with Sample‐Wise Strategy for Fault Diagnosis

“…The convolutional neural network (CNN) is widely applied in image processing based on convolution calculation. Roy et al used deep CNN with layer-wise training to recognize handwritten Bangla isolated compound character [12]. In addition, RMSProp algorithm is applied to achieve faster convergence.…”