Neural Network Analysis for Microplastic Segmentation

Sensors

Gwanghee Lee¹  Kyoungson Jhang¹ 

[1] Department of Computer Science and Engineering, College of Engineering, Chungnam National University, Daejeon 34134, Korea;

关键词: microplastic;    neural network;    segmentation;    U-net;    MultiResUNet;    kernel weight histogram;   

DOI  :  10.3390/s21217030

来源: DOAJ

【 摘 要 】

It is necessary to locate microplastic particles mixed with beach sand to be able to separate them. This paper illustrates a kernel weight histogram-based analytical process to determine an appropriate neural network to perform tiny object segmentation on photos of sand with a few microplastic particles. U-net and MultiResUNet are explored as target networks. However, based on our observation of kernel weight histograms, visualized using TensorBoard, the initial encoder stages of U-net and MultiResUNet are useful for capturing small features, whereas the later encoder stages are not useful for capturing small features. Therefore, we derived reduced versions of U-net and MultiResUNet, such as Half U-net, Half MultiResUNet, and Quarter MultiResUNet. From the experiment, we observed that Half MultiResUNet displayed the best average recall-weighted F1 score (40%) and recall-weighted mIoU (26%) and Quarter MultiResUNet the second best average recall-weighted F1 score and recall-weighted mIoU for our microplastic dataset. They also require 1/5 or less floating point operations and 1/50 or a smaller number of parameters over U-net and MultiResUNet.

【 授权许可】

Unknown