Mocanu Ionela Georgiana, Yang Zhenxu, Belle Vaishak
University of Edinburgh, UK.
University of Edinburgh, UK.
Neural Netw. 2022 Oct;154:246-254. doi: 10.1016/j.neunet.2022.06.041. Epub 2022 Jul 8.
Convolutional Neural Networks have achieved state-of-the-art performance in image classification. Their lack of ability to recognise the spatial relationship between features, however, leads to misclassification of the variants of the same image. Capsule Networks were introduced to address this issue by incorporating the spatial information of image features into neural networks. In this paper, we are interested in showcasing the digit recognition task on CAPTCHA images, widely considered a challenge for computers in relation to human capabilities. Our intention is to provide a rigorous empirical regime in which we can compare the competitive performance of Capsule Networks against the Convolutional Neural Networks. Indeed since CAPTCHA distorts images, by adjusting the spatial positioning of features, we aim to demonstrate the advantages and limitations of Capsule Networks architecture. We train the Capsule Networks with Dynamic Routing version and the convolutional-neural-network-based deep-CAPTCHA baseline model to predict the digit sequences on numerical CAPTCHAs, investigate the performance results and propose two improvements to the Capsule Networks model.
卷积神经网络在图像分类方面取得了领先的性能。然而，它们缺乏识别特征之间空间关系的能力，导致对同一图像的变体进行错误分类。胶囊网络的引入是为了解决这个问题，它将图像特征的空间信息整合到神经网络中。在本文中，我们感兴趣的是展示在验证码图像上的数字识别任务，验证码图像被广泛认为是计算机相对于人类能力的一项挑战。我们的目的是提供一个严格的实证体系，在其中我们可以比较胶囊网络与卷积神经网络的竞争性能。事实上，由于验证码会扭曲图像，通过调整特征的空间定位，我们旨在展示胶囊网络架构的优点和局限性。我们使用动态路由版本的胶囊网络和基于卷积神经网络的深度验证码基线模型来训练，以预测数字验证码上的数字序列，研究性能结果，并对胶囊网络模型提出两项改进。
