激光与光电子学进展, 2019, 56 (4): 041501, 网络出版: 2019-07-31
复杂背景下车型识别分类器 下载: 1092次
Classifier for Recognition of Fine-Grained Vehicle Models under Complex Background
机器视觉 Softmax-SVM 深度卷积神经网络 复杂背景 细粒度车型 machine vision Softmax-SVM deep convolutional neural network complex background fine-grained vehicle models
摘要
细粒度车型图像的类间特征差异小,在复杂图片背景中识别干扰因素多。为提高模型在复杂背景中对图像的特征提取能力和识别准确度,提出了基于支持向量机(SVM)和深度卷积神经网络(DCNN)的分类器集成模型Softmax-SVM。它将交叉熵代价函数与hinge损失函数相结合,代替Softmax函数层,减少了过拟合的发生。同时,设计了一个10层的DCNN提取特征,避免了手工提取特征的难题。实验数据集为复杂背景下的27类精细车型图像,尤其还包含同一汽车厂商的相近车型。实验结果表明,在不进行大量预处理的前提下,Softmax-SVM分类器识别269张测试样本能够获得97.78%的准确率,识别每张样本的时间为0.759 s,明显优于传统模式识别方法和未改进前的DCNN模型。因此,基于DCNN的Softmax-SVM分类器能够适应环境的复杂变化,兼顾识别精度与效率,为复杂背景下的细粒度车型分类提供了实际参考价值。
Abstract
The feature difference among the images of fine-grained vehicle models is small and there exist many factors disturbing recognition under complex image background. To improve the feature extraction ability and the recognition accuracy of images under complex background, a classifier named Softmax-SVM is proposed based on deep convolutional neural network (DCNN) and support vector machine(SVM), in which the cross-entropy cost function is combined with the hinge loss function to replace the Softmax function layer, so that the over-fitting is avoided. Meanwhile, a 10-layer DCNN is designed to extract features automatically and the problem of manual extraction of features is also avoided. The experimental dataset consists of the images of 27 types of fine-gained vehicle models under complex background, especially of the similar models from the same car manufacturer. The experimental results show that the Softmax-SVM classifier can be used to recognize the 269 sample images without much emphasis on the pre-processing stages, and in the identification process, the accuracy rate is 97.78% and the time to identity each image is 0.759 s. The above model performs more efficiently than the traditional recognition methods and the unimproved DCNN models. In consequence, the Softmax-SVM classifier based on DCNN can adapt to the complex changes of environment and give consideration to both the recognition accuracy and efficiency, which provides practical reference value in the classification field of fine-gained vehicle models under complex background.
张洁, 赵红东, 李宇海, 闫苗, 赵泽通. 复杂背景下车型识别分类器[J]. 激光与光电子学进展, 2019, 56(4): 041501. Jie Zhang, Hongdong Zhao, Yuhai Li, Miao Yan, Zetong Zhao. Classifier for Recognition of Fine-Grained Vehicle Models under Complex Background[J]. Laser & Optoelectronics Progress, 2019, 56(4): 041501.