Hyper-parameters optimisation of deep CNN architecture for vehicle logo recognition
Hyper-parameters optimisation of deep CNN architecture for vehicle logo recognition
复制标题
DOI：
10.1049/iet-its.2018.5127
复制
发表时间：
2018-10-01
影响因子：
2.7
通讯作者：
Kanesan, Jeevan
中科院分区：
文献类型：
--
作者：
Soon, Foo Chong;Khaw, Hui Ying;Kanesan, Jeevan
用于分类目的的深度卷积神经网络（CNN）的训练很大程度上取决于超参数调整的专业知识。本研究旨在通过自动搜索和优化 CNN 架构来最小化训练 CNN 时的用户变异性，特别是在车辆标志识别系统领域。为此，根据粒子群优化随机方法在训练-测试数据上的实现来选择 CNN 的架构和超参数。获得优化的超参数后，对CNN进行微调和训练，以确保更好的网络收敛和分类性能。在本研究中，总共14,950张车辆标志图像被分为两个独立的训练集和测试集。此外，这些图像被粗分割，因此在这项工作中消除了精确标志分割的要求。 CNN 学习到的特征具有足够的辨别力，可以使用多类 Softmax 分类器进行分类。通过使用图形处理单元（GPU）实现，所提出的方法的计算时间对于实时应用来说是可以接受的。实验结果明确证明，作者的方法优于大多数最先进的方法，在 13 家汽车制造商中实现了 99.1% 的准确率。
The training of deep convolutional neural network (CNN) for classification purposes is critically dependent on the expertise of hyper-parameters tuning. This study aims to minimise the user variability in training CNN by automatically searching and optimising the CNN architecture, particularly in the field of vehicle logo recognition system. For this purpose, the architecture and hyper-parameters of CNN were selected according to the implementation of the stochastic method of particle swarm optimisation on the training-testing data. After obtaining the optimised hyper-parameters, the CNN is fine-tuned and trained to ensure better network convergence and classification performance. In this study, a total of 14,950 vehicle logo images are divided into two independent training and testing sets. In addition, these images are segmented coarsely, thus the requirement of precise logo segmentation is obviated in this work. The learned features of the CNN were sufficiently discriminative to be classified using multiclass Softmax classifier. With implementation using a graphics processing unit (GPU), the computation time of the proposed method is acceptable for real-time application. The experimental results explicitly prove that the authors' approach outperforms most of the state-of-the-art methods, achieving an accuracy of 99.1% over 13 vehicle manufacturers.