Corn Seed Defect Detection Based on Watershed Algorithm and Two-Pathway Convolutional Neural Networks
Authors:
Open Access
- 23 February 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 13, 730190
Abstract
Corn seed materials of different quality were imaged, and a method for defect detection was developed based on a watershed algorithm combined with a two-pathway convolutional neural network (CNN) model. In this study, RGB and near-infrared (NIR) images were acquired with a multispectral camera to train the model, which was proved to be effective in identifying defective seeds and defect-free seeds, with an averaged accuracy of 95.63%, an averaged recall rate of 95.29%, and an F1 (harmonic average evaluation) of 95.46%. Our proposed method was superior to the traditional method that employs a one-pathway CNN with 3-channel RGB images. At the same time, the influence of different parameter settings on the model training was studied. Finally, the application of the object detection method in corn seed defect detection, which may provide an effective tool for high-throughput quality control of corn seeds, was discussed.Keywords
This publication has 31 references indexed in Scilit:
- Current and future applications of statistical machine learning algorithms for agricultural machine vision systemsComputers and Electronics in Agriculture, 2019
- Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspectiveGigaScience, 2018
- Mutual variation of information on transfer-CNN for face recognition with degraded probe samplesNeurocomputing, 2018
- Selection for high quality pepper seeds by machine vision and classifiersJournal of Integrative Agriculture, 2018
- Non‐destructive technique for determining the viability of soybean (Glycine max) seeds using FT‐NIR spectroscopyJournal of the Science of Food and Agriculture, 2017
- Maintaining dryness during storage contributes to higher maize seed qualityJournal of Stored Products Research, 2017
- Color and texture for corn seed classification by machine vision2011
- Histograms of Oriented Gradients for Human Detection2005
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Textural Features for Image ClassificationIEEE Transactions on Systems, Man, and Cybernetics, 1973