基于卷积神经网络的宠物狗种类识别
|
摘要
宠物狗在人们生活中扮演着越来越重要的角色,本文利用卷积神经网络技术,建立了一个宠物狗种类识别模型。对比其他模式识别技术,卷积神经网卷积层能自动对图像进行特征提取,并且因为其参数的权值共享,可以进一步有效缩短学习时间和提升识别率。本文所构建的识别模型能够实现相对复杂宠物狗种类进行识别,可为日常生活中的宠物狗提供一种行之有效的方法,具有一定的现实意义。
Pet dogs play an increasingly important role in people's lives. In this paper, a kind of recognition model of pet dog is established by using convolution neural network technology.Compared with other pattern recognition technologies, the convolution layer of convolution neural network can automatically extract image features, and because of the weight sharing of its parameters, it can further effectively shorten the learning time and improve the recognition rate.The recognition model constructed in this paper can realize the recognition of relatively complex pet dog species. It can provide an effective method for pet dogs in daily life, and has a certain practical significance.
Pet dogs play an increasingly important role in people's lives. In this paper, a kind of recognition model of pet dog is established by using convolution neural network technology.Compared with other pattern recognition technologies, the convolution layer of convolution neural network can automatically extract image features, and because of the weight sharing of its parameters, it can further effectively shorten the learning time and improve the recognition rate.The recognition model constructed in this paper can realize the recognition of relatively complex pet dog species. It can provide an effective method for pet dogs in daily life, and has a certain practical significance.
引文
[1] Deng J, Dong W, Socher R, et al. Imagenet:A large-scale hierarchical image database[C]//Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE,2009:248-255.
[2] Huang G, Liu Z, Weinberger K Q, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, 1(2):3.
[3]卷积神经网络研究综述[J].计算机学报, 2017, 40(6):1229-1251.
[4] Girshick R. Fast R-CNN[J]. Computer Science, 2015.
[5] Trnovszky T, Kamencay P, Orjesek R, et al. Animal recognition system based onconvolutional neural network[J]. Advances in Electrical and Electronic Engineering,2017, 15(3):517.
[6] http://vision.stanford.edu/aditya86/ImageNetDogs/
[2] Huang G, Liu Z, Weinberger K Q, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, 1(2):3.
[3]卷积神经网络研究综述[J].计算机学报, 2017, 40(6):1229-1251.
[4] Girshick R. Fast R-CNN[J]. Computer Science, 2015.
[5] Trnovszky T, Kamencay P, Orjesek R, et al. Animal recognition system based onconvolutional neural network[J]. Advances in Electrical and Electronic Engineering,2017, 15(3):517.
[6] http://vision.stanford.edu/aditya86/ImageNetDogs/