计算机应用 ›› 2019, Vol. 39 ›› Issue (12): 3665-3672.DOI: 10.11772/j.issn.1001-9081.2019040637

• 虚拟现实与多媒体计算 • 上一篇    下一篇

基于卷积神经网络的偏色光下植物图像分割方法

张文彬1, 朱敏2, 张宁1, 董乐1   

  1. 1. 电子科技大学 计算机科学与工程学院, 成都 611731;
    2. 珠海(横琴)食品安全研究院, 广东 珠海 519000
  • 收稿日期:2019-04-16 修回日期:2019-08-07 出版日期:2019-12-10 发布日期:2019-08-26
  • 作者简介:张文彬(1997-),男,河南三门峡人,硕士研究生,主要研究方向:计算机视觉、图像处理;朱敏(1963-),男,上海人,工程师,博士,主要研究方向:食品安全、智能农业;张宁(1975-),男,江苏南京人,讲师,博士,主要研究方向:计算机视觉、系统设计;董乐(1980-),女,陕西西安人,教授,博士,主要研究方向:视频理解、机器智能、模式识别。
  • 基金资助:
    国家自然科学基金资助项目(61772114);广东省引进领军人才项目(2016LJ06S419)。

Plant image segmentation method under bias light based on convolutional neural network

ZHANG Wenbin1, ZHU Min2, ZHANG Ning1, DONG Le1   

  1. 1. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 611731, China;
    2. Zhuhai(Hengqin) Food Safety Research Institute, Zhuhai Guangdong 519000, China
  • Received:2019-04-16 Revised:2019-08-07 Online:2019-12-10 Published:2019-08-26
  • Contact: 董乐
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61772114), the Leading Talent Introduction Program of Guangdong Province (2016LJ06S419).

摘要: 为了解决传统图像分割算法在植物工厂中偏色光植物图像上分割精确度不高、泛化性能差的问题,提出了一种基于卷积神经网络,并结合深度学习技术,对人工偏色光下植物图像进行精确分割的方法。采用该方法,最终在偏色光植物图像原始测试集上达到了91.89%的分割精确度,远超全卷积网络、聚类、阈值、区域生长等分割算法。此外,在不同色光之下的植物图片上进行测试,该方法也较上述其他分割算法有着更好的分割效果和泛化性能。实验结果表明,所提方法能够显著提高偏色光下植物图像分割的精确度,可以应用于实际的植物工厂工程项目当中。

关键词: 植物工厂, 深度学习, 卷积神经网络, 偏色光植物图像, 图像分割

Abstract: To solve the problems of low precision and poor generalization performance of traditional image segmentation algorithms on the plant images under bias light in plant factory, a method based on neural network and deep learning for accurately segmenting the plant images under artificial bias light in plant factory was proposed. By using this method, the segmentation accuracy on the original test set of bias light plant images is 91.89% and is far superior to that by other segmentation algorithms such as Fully Convolutional Network (FCN), clustering, threshold and region growth. In addition, this method has better segmentation effect and generalization performance than the above methods on plant images under different color lights. The experimental results show that the proposed method can significantly improve the accuracy of plant image segmentation under bias light, and can be applied to practical plant factory projects.

Key words: plant factory, deep learning, Convolutional Neural Network (CNN), bias light plant image, image segmentation

中图分类号: