当前位置>主页 > 期刊在线 > 物联网 >

物联网21年13期

基于 MobileNet 的果蔬识别系统
陈怡帆
(四川大学锦城学院 计算机与软件学院,四川 成都 611731)

摘  要:我国疆域辽阔,土壤肥沃,气候温和,尤其是新疆地区,日照时间充足,盛产水果。造就了我国成为农业生产大国,每年进出口非常多的水果蔬菜。据了解,在大部分农贸市场都靠人工进行果蔬分类,工作量多且效率低下。提出一种基于MobileNet 模型的果蔬识别系统,该系统可以快速进行果蔬识别。该项目用了传统 CNN 模型和更轻量化的 MobileNet 模型对 12个不同品种的蔬果数据集进行训练,发现基于 MobileNet 模型的识别结果正确率更高。


关键词:深度学习;图像识别;卷积神经网络;MobileNet



DOI:10.19850/j.cnki.2096-4706.2021.13.040


中图分类号:TP391.4                                       文献标识码:A                                 文章编号:2096-4706(2021)13-0155-04


Fruit and Vegetable Recognition System Based on MobileNet

CHEN Yifan

(School of Computer and Software, Jincheng College of Sichuan University, Chengdu, 611731, China)

Abstract: China has a vast territory, fertile soil and mild climate. Especially in Xinjiang, it has sufficient sunshine and is rich in fruits. As a result, China has become a large agricultural production country, importing and exporting a lot of fruits and vegetables every year. It is understood that in most farmers’ markets, fruits and vegetables are classified manually, which has a large of workload and low efficiency. Therefore, this paper puts forward a fruit and vegetable recognition system based on MobileNet model, which can quickly recognize fruits and vegetables. The project uses the traditional CNN model and the lighter MobileNet model to train the data sets of 12 different kinds of fruit and vegetable. It is found that the recognition result based on MobileNet model has a higher accuracy.

Keywords: deep learning; image recognition; convolutional neural network; MobileNet


参考文献:

[1] HOWARD A G,ZHU M L,CHEN B,etal. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [J/OL].arXiv:1704.04861 [cs.CV].https: //arxiv.org/abs/1704.04861.

[2] 高淑萍,赵清源,齐小刚,等 . 改进 MobileNet 的图像分类方法研究 [J]. 智能系统学报,2021,16(1):11-20.

[3] 陆飞,沈世斌,苏晓云,等 . 基于改进 Mask R-CNN 的交通监控视频车辆检测算法 [J]. 南京师范大学学报(工程技术版), 2020,20(4):44-50.

[4] 张焯林,曹飞龙 . 基于 MobileNet 的轻量级网络构建及其超分辨率图像重建 [J]. 中国计量大学学报,2019,30(1):56- 64+103.

[5] 高洋,陈万米,林城 . 基于 SSD-MobileNet 的投篮机器人目标识别算法 [J]. 工业控制计算机,2021,34(6):51-53.

[6] 江南大学 . 基于 MobileNetV3 的实时人脸检测方法:CN110647817A [P].2020-01-03.

[7] 张陶宁, 陈恩庆, 肖文福 . 一种改进 MobileNet _YOLOv3 网络的快速目标检测方法 [J]. 小型微型计算机系统, 2021,42(5):1008-1014.

[8] 张骏,朱标,吉涛 . 基于 MobileNet-SSD 的红外人脸检测算法 [J]. 激光与红外,2021,51(1):107-113.


作者简介:陈怡帆(2000—),男,汉族,四川南充人,本科 在读,研究方向:机器学习。