Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, New Delhi 110058, India.
Department of Computer Science, Maharaja Surajmal Institute, New Delhi 110058, India.
Sensors (Basel). 2020 Jun 12;20(12):3344. doi: 10.3390/s20123344.
Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network's recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.
传统的手写识别系统依赖于手工制作的特征和大量的先验知识。基于这些前提条件训练光学字符识别 (OCR) 系统是一项具有挑战性的任务。手写识别领域的研究集中在深度学习技术上，并在过去几年中取得了突破性的性能。尽管如此，手写数据量的快速增长和大量处理能力的可用性要求提高识别精度，并值得进一步研究。卷积神经网络 (CNN) 在感知手写字符/单词的结构方面非常有效，有助于自动提取独特的特征，使 CNN 成为解决手写识别问题的最适合方法。我们在拟议工作中的目标是探索各种设计选项，例如基于 CNN 的手写数字识别的层数、步幅大小、感受野、核大小、填充和稀释。此外，我们旨在评估各种 SGD 优化算法在提高手写数字识别性能方面的作用。通过集成架构，网络的识别准确性会提高。在这里，我们的目标是通过使用没有集成架构的纯 CNN 架构来实现可比的准确性，因为集成架构会增加计算成本和高测试复杂性。因此，为了实现比集成架构更好的准确性，同时降低操作复杂性和成本，提出了一种 CNN 架构。此外，我们还在设计 CNN 时提出了适当的学习参数组合，使我们在分类 MNIST 手写数字方面达到了新的绝对记录。我们进行了广泛的实验，在 MNIST 数据集上实现了 99.87%的识别准确率。
