摘要
为推进车辆安全检查中同轴轮胎类型判别自动化的实现,提出一种基于孪生网络的轮胎花纹图像验证算法。该算法面向小样本轮胎花纹图像,在孪生网络的基础架构上,增加方向矫正的图像预处理模块,实现轮胎花纹的对齐,消除轮胎图像间明显纹理的方向特征差异;在其子网络的低层级卷积网络中使用Gabor方向滤波器,提升网络对轮胎花纹纹理特征的学习速度以及对不同质量轮胎图像识别的鲁棒性。在CIIP_TPID和WTP数据集上的实验表明,该算法的准确率分别达到0.926和0.849。
To promote the automatic realization of coaxial tire type discrimination in vehicle safety inspection,a tire pattern image verification algorithm based on siamese network was proposed.The algorithm is oriented to the tire pattern images of small data sets.On the infrastructure of the siamese network,an image preprocessing module of orientation correction is added to realize the alignment of tire patterns and eliminate the obvious orientation difference between tire images.The Gabor Orientation Filters are used in the low-level convolutional network of its subnetwork to improve the learning speed of the network on tire pattern texture features and the robustness of tire image recognition with different quality.Experimental results on CIIP_TPID and WTP datasets show that the accuracy of the proposed algorithm is 0.926and 0.849respectively.
作者
夏煜丹
刘书朋
田静
商娅娜
陈娜
Xia Yudan;Liu Shupeng;Tian Jing;Shang Yana;Chen Na(School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China;School of Electron and Computer,Southeast University Chengxian College,Nanjing 210088,China)
出处
《电子测量技术》
北大核心
2023年第16期165-171,共7页
Electronic Measurement Technology
基金
国家自然科学基金(62175142,61875118)项目资助
关键词
图像验证
孪生网络
小样本
方向矫正
Gabor方向滤波器
image verification
siamese network
small sample
correction of direction
Gabor orientation filter
