APPLICATION AND COMPARISON OF DIFFERENT DEEP LEARNING MODELS IN RECOGNITION OF FOOD WASTE TYPES

LIU Zhi; GAO Dongming

doi:10.13205/j.hjgc.202403031

Volume 42 Issue 3

Mar. 2024

Turn off MathJax

Article Contents

Abstract

References

Article Navigation > ENVIRONMENTAL ENGINEERING > 2024 > 42(3): 254-260

LIU Zhi, GAO Dongming. APPLICATION AND COMPARISON OF DIFFERENT DEEP LEARNING MODELS IN RECOGNITION OF FOOD WASTE TYPES[J]. ENVIRONMENTAL ENGINEERING , 2024, 42(3): 254-260. doi: 10.13205/j.hjgc.202403031

Citation:

LIU Zhi, GAO Dongming. APPLICATION AND COMPARISON OF DIFFERENT DEEP LEARNING MODELS IN RECOGNITION OF FOOD WASTE TYPES[J]. ENVIRONMENTAL ENGINEERING , 2024, 42(3): 254-260. doi: 10.13205/j.hjgc.202403031

Citation:

PDF( 5140 KB)

APPLICATION AND COMPARISON OF DIFFERENT DEEP LEARNING MODELS IN RECOGNITION OF FOOD WASTE TYPES

doi: 10.13205/j.hjgc.202403031

LIU Zhi,
GAO Dongming^,

College of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China

Received Date: 2023-02-28
Available Online: 2024-05-31

Abstract

Abstract

Kitchen waste and post-meal waste vary greatly in texture, if the pre-treatment process doesn’t effectively identify the type of kitchen waste, and then take the appropriate working parameters, it often leads to poor treatment effect of the reduction treatment equipment. We collected and processed images of vegetable waste and post-meal waste in different seasons and different dietary styles, considering the differences in images between tailgate waste and post-meal waste, on this basis, ResNet18 was used as the base network, and attention mechanism was introduced to design a new deep learning model for kitchen waste recognition, which was compared with ResNet18, ECANET+ResNet18, SENET+ResNet18, and SANET+ResNet18 models. The results showed that all the above four network models had high accuracy rates. Their accuracy rates were 96.73%, 97.10%, 97.28%, and 96.92%, respectively; their loss rates were 4.35%, 4.11%, 3.76%, and 4.17%, respectively; in terms of training time, ECANET+ResNet18 had the shortest training time, which was 350 seconds faster than ResNet18. ECANET+ResNet18 network effectively improved the performance of ResNet18 network, achieved the highest accuracy rate and the smallest loss rate, and could meet the requirements of machine recognition of kitchen waste.
- food waste,
- deep learning,
- image processing,
- type identification,
- attention mechanism

FullText(HTML)

References(24)

References

[1]	周建华,陈锋.某典型餐厨垃圾综合处理项目实例[J].环境工程,2020,38(8):47-51.
[2]	高东明,马建行,周磊,等.基于PLC的餐厨垃圾破碎机控制系统设计[J].制造业自动化,2022,44(2):133-137.
[3]	刘航驿,颜蓓蓓,林法伟,等.生命周期视角下2种餐厨垃圾资源化处理方案的对比分析[J].环境工程,2021,39(9):169-175.
[4]	KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems,2012,25(2).DOI: 10.1145/3065386.
[5]	金佩薇,姚燕,梁晓瑜,等.垃圾图像识别研究进展[J].环境工程,2022,40(1):196-206.
[6]	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society,2015:1-9.
[7]	HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society,2016.
[8]	黄兴华,叶军一,熊杰.基于纹理特征融合的道路垃圾图像识别及提取[J].计算机工程与设计,2019, 40(11):3212-3218 ,3305.
[9]	段春云,李广.绿色建筑施工垃圾智能分类仿真建模研究[J].计算机仿真,2022,39(3):234-237 ,243.
[10]	王莉,何牧天,徐硕,等.基于YOLOv5s网络的垃圾分类和检测[J].包装工程,2021,42(8):50-56.
[11]	许伟,熊卫华,姚杰,等.基于改进YOLOv3算法在垃圾检测上的应用[J].光电子·激光,2020,31(9):928-938.
[12]	王一田,唐开强,留沧海,等.基于YOLO v3的地面垃圾检测与清洁度评定方法[J].传感器与微系统,2022,41(4):129-133.
[13]	王文胜,年诚旭,张超,等.基于YOLO v5模型的非住宅区自动垃圾分类箱设计[J].环境工程,2022,40(3):159-165.
[14]	魏铖磊,南新元,李成荣,等.一种具有多尺度感受视野注意力机制的生活垃圾单阶段目标检测方法[J].环境工程, 2022, 40(1):175-183.
[15]	TIAN M J, LI X L, KONG S H. A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot[J].Frontiers of Information Technology & Electronic Engineering,2022,23(8):1217-1229.
[16]	邢洁洁,谢定进,杨然兵,等.基于YOLOv5s的农田垃圾轻量化检测方法[J].农业工程学报,2022,38(19):153-161.
[17]	田有文,吴伟,林磊,等.基于深度学习与高光谱成像的蓝莓果蝇虫害无损检测[J/OL].农业机械学报,2023(1):393-401.
[18]	黄林生,罗耀武,杨小冬,等.基于注意力机制和多尺度残差网络的农作物病害识别[J].农业机械学报,2021,52(10):264-271.
[19]	赵杰,李絮,申通.基于SENet注意力机制和深度残差网络的腹部动脉分割[J].科学技术与工程,2022,22(22):9529-9536.
[20]	刘学平,李玙乾,等.嵌入SENet结构的改进YOLOV3目标识别算法[J].计算机工程,2019,45(11):243-248.
[21]	于慧伶,霍镜宇,张怡卓.融合多层特征SENet和多尺度宽残差的高光谱图像地物分类[J].实验室研究与探索,2020,39(7):28-34 ,44.
[22]	WANG Q L, WU B G, ZHU P F, et al. ECA-Net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:11534-11542.
[23]	张小敏,徐涛,张延宁,等.用于体质量估测的黄羽鸡姿态关键帧识别与分析[J].农业机械学报,2022,53(12):254-263.
[24]	王玮琦,游雄,苏明占,等. SANet:空间注意力机制下的LiDAR点云实时语义分割方法[J].测绘通报, 2022(11):32-38.