[1]米克热依·迪里夏提,张太红.自适应池化卷积神经网络马品种识别研究[J].计算机技术与发展,2019,29(10):105-110.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 022]
　Mikray·DILXAT,ZHANG Tai-hong.Study on Breed Identification of Horse Based on Adaptive Pooling Convolution Neural Network[J].,2019,29(10):105-110.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 022]
点击复制

自适应池化卷积神经网络马品种识别研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年10期
页码:
105-110
栏目:
应用开发研究
出版日期:
2019-10-10

文章信息/Info

Title:
Study on Breed Identification of Horse Based on Adaptive Pooling Convolution Neural Network
文章编号:
1673-629X(2019)10-0105-06
作者:
米克热依·迪里夏提; 张太红
新疆农业大学 计算机与信息工程学院,新疆 乌鲁木齐 830001
Author(s):
Mikray·DILXAT; ZHANG Tai-hong
School of Computer and Information Engineering,Xinjiang Agricultural University,Urumqi 830001,China
关键词:
马品种图像; 卷积神经网络; 混淆矩阵; 自适应池化; 数据扩增
Keywords:
horse breed images; convolutional neural network; confusion matrix; adaptive pooling; data amplification
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 10. 022
摘要:
针对经典池化方式不能提取有效特征值的问题,提出了根据池化域的大小、池化域中的元素值和网络的训练次数调整池化结果的自适应池化法,并搭建了基于自适应池化的卷积神经网络模型,实现了对哈福林格马(Haflinger)、阿克哈-塔克马(Akhal-Teke)、吉普赛马(Gypsy Venner)、伊犁马(Yili)、阿帕卢萨马(Appaloosa)、弗里西亚马(Friesian)、阿拉伯马(Arabian)、马瓦里马(Marwari)等八个品种的识别。 对于图像进行归一化、数据扩增等预处理后,从数据集中随机选取80% 的样本用作训练集,剩余的20%用作验证集和测试集。 在 Keras 深度学习框架下,对使用自适应池化前后的卷积神经网络进行全新学习,并做了三组对照实验。 实验结果表明,自适应池化算法明显提高了模型的准确率和分类性能。 使用自适应池化算法后的模型在测试集上的准确率达到了 88.24%,初步实现了基于计算机视觉的马品种识别。
Abstract:
Aiming at the problem that the effective characteristic values cannot be extracted by the traditional pooled method,an adaptive pooled method is proposed to adjust the pooled results according to the size of the pooled domain,the element values in the pooled domain and the number of training rounds of the network,and the convolutional neural network model based on adaptive pooling is set up to realize the recognition of eight species,including Haflinger,Akhal-Teke,Gypsy Venner,Yili,Appaloosa, Friesian,Arabian and Marwari. After image normalization,data amplification and other preprocessing,80% samples are randomly selected from the data set for training set,and the remaining 20% for verification set and test set. Under the Keras,a deep learning framework,the convolutional neural network before and after self-adaptive pooling is used for new learning,and three group of experiments are conducted. Experiment shows that the adaptive pooling algorithm significantly improves the accuracy and classification performance of the model. Using the adaptive pooling algorithm,the accuracy of the model can reach 88.24% on the test set,preliminarily realizing the horse breed recognition based on computer vision.

相似文献/References:

[1]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(10):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[2]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(10):31.
[3]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(10):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[4]郭子琰,舒心,刘常燕,等.基于ReLU 函数的卷积神经网络的花卉识别算法[J].计算机技术与发展,2018,28(05):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
　GUO Ziyan,SHU Xin,LIU Changyan,et al.A Recognition Algorithm of Flower Based on Convolution Neural Network with ReLU Function[J].,2018,28(10):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
[5]缪宇杰,吴智钧,宫 婧.基于3D 卷积的视频错帧筛选方法[J].计算机技术与发展,2018,28(05):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
　MIAO Yu-jie,WU Zhi-jun,GONG Jing.A Wrong Temporal-order Frames Identification Method Based on 3D Convolution[J].,2018,28(10):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
[6]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(10):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[7]李相桥,李晨,田丽华,等.卷积神经网络并行训练的优化研究[J].计算机技术与发展,2018,28(08):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
　LI Xiang-qiao,LI Chen,TIAN Li-hua,et al.Research on Optimization of Parallel Training for Convolution Neural Network[J].,2018,28(10):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
[8]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(10):11.
[9]河海大学 计算机与信息学院,江苏 南京 0098.卷积网络的无监督特征提取对人脸识别的研究[J].计算机技术与发展,2018,28(06):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
　DU Bai-sheng.Research on Unsupervised Feature Extraction Based on Convolutional Neural Network for Face Recognition[J].,2018,28(10):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
[10]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(10):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]

更新日期/Last Update: 2019-10-10