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

2017/03/07 by Saikat Roy, Nibaran Das, Mahantapas Kundu +1 · 128 citations
Computer Science · Engineering · Mathematics · #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Bengali #Character (mathematics) #Computer science #Convolutional neural network #Deep learning #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Machine learning #Mathematics #Pattern recognition (psychology) #Vehicle License Plate Recognition #cs.CV

paper · pdf · doi:10.1016/j.patrec.2017.03.004

published in Pattern Recognition Letters 90, 15-21 (Elsevier BV)

openalex publication_date 2017/03/07 · arxiv created 2018/02/02 · arxiv updated 2018/02/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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%.

Citations

• Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Equilibrated adaptive learning rates for non-convex optimization
• Gradient-based learning applied to document recognition
• Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
• Backpropagation Applied to Handwritten Zip Code Recognition
• Distinctive Image Features from Scale-Invariant Keypoints
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
• ImageNet classification with deep convolutional neural networks
• Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification