Sunflower seeds classification based on sparse convolutional neural networks in multi-objective scene

Author:

Jin Xiaowei,Zhao Yuhong,Wu Hao,Sun Tingting

Abstract

AbstractGenerally, sunflower seeds are classified by machine vision-based methods in production, which include using photoelectric sensors to identify light-sensitive signals through traditional algorithms for which the equipment cost is relatively high and using neural network image recognition methods to identify images through cameras for which the computational cost is high. To address these problems, a multi-objective sunflower seed classification method based on sparse convolutional neural networks is proposed. Sunflower seeds were obtained from the video recorded using the YOLOv5 Object detection algorithm, and a ResNet-based classification model was used to classify the seeds according to differences in appearance. The ResNet has the disadvantages of having numerous parameters and high storage requirements; therefore, this study referred to the Lottery Ticket Hypothesis and used the Iterative Magnitude Pruning algorithm to compress the sunflower seed classification model, aiming to ascertain the optimal sparse sub-network from the classification model. Experiments were conducted to compare the effects on model performance before and after pruning, pruning degree, and different pruning methods. The results showed that the performance of the ResNet-based sunflower seed classification model using global pruning was the least affected by pruning, with a 92% reduction in the number of parameters, the best accuracy is 0.56% better than non-pruned and 9.17% better than layer-wise pruning. These findings demonstrate that using the Iterative Magnitude Pruning algorithm can render the sunflower seed classification model lightweight with less performance loss. The reduction in computational resources through model compression reduces the cost of sunflower seed classification, making it more applicable to practical production, and this model can be used as a cost-effective alternative to key sunflower seed classification techniques in practical production.

Funder

National Nature Science Foundation of China

Publisher

Springer Science and Business Media LLC

Subject

Multidisciplinary

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3