当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术21年17期

基于计算机图像识别的垃圾智能分类
李天千,陈志鑫,黄桂鑫,温森荣,黄思琪
(广东外语外贸大学南国商学院 信息科学技术学院,广东 广州 510545)

摘  要:为提高垃圾分类效率,应对日益繁杂的垃圾分类工作,使垃圾分类智能化,高效化。运用卷积神经网络解决垃圾分类问题,对 YOLOv3 基础算法进行研究改进,并制作垃圾种类数据集,结合参数迁移学习训练垃圾分类识别模型。实验表明样本多的种类识别准确率较高,而对于样本少的种类,准确率就下降了。相较于现有常用的垃圾分类识别算法,所提出的垃圾分类识别算法,识别性能更优,更适合广泛推广应用。


关键词:垃圾检测;数据集制作;YOLOv3 算法



DOI:10.19850/j.cnki.2096-4706.2021.17.022


中图分类号:TP181                                       文献标识码:A                                        文章编号:2096-4706(2021)17-0092-04


Intelligent Garbage Classification Based on Computer Image Recognition

LI Tianqian, CHEN Zhixin, HUANG Guixin, WEN senrong, HUANG Siqi

(School of Information Science and Technology, South China Business College Guangdong University of Foreign Studies, Guangzhou 510545, China)

Abstract: In order to improve the efficiency of garbage classification, deal with the increasingly complicated garbage classification work, and make garbage classification intelligent and efficient. Use convolutional neural network to solve the garbage classification problem, research and improve the basic algorithm of YOLOv3, and make a garbage type data set, combined with parameter transfer learning to train the garbage classification and recognition model. Experiments show that the recognition accuracy of the types with a large number of samples is higher, while for the types with a small number of samples, the accuracy is reduced. Compared with the existing commonly used garbage classification and recognition algorithms, the proposed garbage classification and recognition algorithm has better recognition performance and is more suitable for wide promotion and application.

Keywords: garbage detection; data set production; YOLOv3 algorithm


参考文献:

[1] 刘智嘉,汪璇,赵金博,等 . 基于 YOLO 算法的红外图像目标检测的改进方法 [J]. 激光与红外,2020,50(12):1512-1520.

[2] 林红兵 .“十四五”时期垃圾分类的机遇与展望 [N]. 中国建设报,2020-11-16(8).

[3] 郝楠 . 基于深度学习的公路障碍物检测的研究 [D]. 成都:电子科技大学,2019.

[4] 张奇 . 基于改进 YOLO 的小目标检测算法应用研究 [D]. 长春:吉林农业大学,2020.

[5] 彭伟航,白林,商世为,等 . 基于改进 InceptionV3 模型的常见矿物智能识别 [J]. 地质通报,2019,38(12):2059-2066.

[6] 单宇翔,龙涛,楼卫东,等 . 基于深度学习的复杂场景中卷烟烟盒检测与识别方法 [J]. 中国烟草学报,2021,27(5):71- 80.


作者简介:李天千(2000—),女,汉族,陕西渭南人,本科在读,主要研究方向:深度学习、图像处理。