Enhancing Seed Germination Test Classification for Pole Sitao (Vigna unguiculata (L.) Walp.) Using SSD MobileNet and Faster R-CNN Models
Source abstract
Abstract
The classification of germinated pole sitao (Vigna unguiculata (L.) Walp.) seeds is important in seed germination tests. The automation of this process has been explored for different grain and legume seeds but is only limited to binary classification. This study aimed to develop a classifier system that can recognize three classes: normal, abnormal, and ungerminated. SSD MobileNet and Faster R-CNN models were trained to perform the classification. Both were trained using 1500 images of germinated seeds at fifth- and eighth-day observations. Each class had 500 images. The trained models were evaluated using 150 images per class. The SSD MobileNet model had an accuracy of 0.79 while the Faster R-CNN model had an accuracy of 0.75. The results showed that the average accuracies for the classes were significantly different from one another based on one-way ANOVA at a 95% confidence level with an F-critical value of 3.0159. The SSD MobileNet model outperformed the Faster R-CNN model in classifying pole sitao seeds, with improved precision in identifying abnormal and ungerminated seeds on the fifth day and normal and ungerminated seeds on the eighth day. The results confirm the potential of the SSD MobileNet model as a more reliable classifier in germination tests.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rice Cultivation and Yield Improvement · GABA and Rice Research · Plant Genetic and Mutation Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Municipal Agriculture Office-Local Government Unit of Binangonan, Rizal 1910, Philippines
Institute of Agricultural and Biosystems Engineering, College of Engineering and Agro-Industrial Technology, University of the Philippines Los Banos, Batong Malake, Laguna 4031, Philippines
Funding
Faculty Research Dissemination Grant of the Engineering Research and Development for Technology Scholarship Program under the Department of Science and Technology—Science Education Institute
References (25)
Show source-provided references
1. Agricultural Training Institute—Department of Agriculture (2022, March 14). Pole Sitaw, Available online: https://binangonan.gov.ph/municipal-departments-sections/.
2. SeedGerm: A Cost-Effective Phenotyping Platform for Automated Seed Imaging and Machine-Learning Based Phenotypic Analysis of Crop Seed Germination10.1111/nph.16736 ↗
3. International Seed Testing Association (ISTA) (2017). The Germination Tests. International Rules for Seed Testing, International Seed Testing Association. Chapter 5.10.15258/istarules.2017.05 ↗
4. Machine Learning Algorithms—A Review
5. Rice Seed Germination Analysis
6. Accurate Machine Learning—Based Germination Detection Prediction and Quality Assessment of Three Grain Crops10.1186/s13007-020-00699-x ↗
7. Seed Germination Test Using Image Processing
8. Image Analysis Based on Color, Shape, and Texture for Rice Seed (Oryza sativa L.) Germination Evaluation
9. Nguyen, T.T., Hoang, V.-N., Le, T.-L., Tran, T.-H., and Vu, H. (2018, January 16). A Vision Based Method for Automatic Evaluation of Germination Rate of Rice Seeds. Proceedings of the 2018 1st International Conference on Multimedia Analysis and Pattern Recognition (MAPR), Ho Chi Minh City, Vietnam.10.1109/MAPR.2018.8337511 ↗
10. Khoenkaw, P. (2016, January 23). An Image-Processing Based Algorithm for Rice Seed Germination Rate Evaluation. Proceedings of the 2016 International Computer Science and Engineering Conference (ICSEC), Chiang Mai, Thailand.10.1109/ICSEC.2016.7859890 ↗
11. Automatic Monitoring System for Seed Germination Test Based on Deep Learning
12. Utilization of Computer Vision and Multispectral Imaging Techniques for Classification of Cowpea (Vigna unguiculata) Seeds10.1186/s13007-019-0411-2 ↗
13. Using Color and Texture for Seeds Germination Analysis
14. A Machine Vision System for Seeds Germination Quality Evaluation Using Fuzzy Logic10.1016/S0168-1699(01)00150-8 ↗
15. Interactive Machine Learning for Soybean Seed and Seedling Quality Classification
16. Real Time Object Detection Using SSD and MobileNet10.22214/ijraset.2022.40755 ↗
17. Overview of Two-Stage Object Detection Algorithms10.1088/1742-6596/1544/1/012033 ↗
18. Faster R-CNN with Inception V2 for Fingertip Detection in Homogenous Background Image10.1088/1742-6596/1196/1/012017 ↗
19. Mishra, A. (2022, July 11). Metrics to Evaluate Your Machine Learning Algorithm. Medium. Available online: https://towardsdatascience.com/metrics-to-evaluate-your-machine-learning-algorithm-f10ba6e38234.
20. Gad, A. (2022, July 28). Is Learning Rate Useful in Artificial Neural Networks? Medium. Available online: https://towardsdatascience.com/is-learning-rate-useful-in-artificial-neural-networks-84ee5b6976d6.
21. Steps toward a Large-Scale Solar Image Data Analysis to Differentiate Solar Phenomena10.1007/s11207-013-0304-x ↗
22. Vallantin, L. (2022, July 11). Why You Should Not Trust Only in Accuracy to Measure Machine Learning Performance. Medium. Available online: https://medium.com/@limavallantin/why-you-should-not-trust-only-in-accuracy-to-measure-machine-learning-performance-a72cf00b4516.
23. Barkved, K. (2022, July 11). How to Know if Your Machine Learning Model Has Good Performance: Obviously AI. Data Science without Code. Available online: https://www.obviously.ai/post/machine-learning-model-performance.
24. Grandperrin, J. (2022, July 11). How to Use Confidence Scores in Machine Learning Models. Medium. Available online: https://towardsdatascience.com/how-to-use-confidence-scores-in-machine-learning-models-abe9773306fa.
25. Comparison of SSD and Faster R-CNN Algorithms to Detect the Airports with Data Set Which Obtained from Unmanned Aerial Vehicles and Satellite Images10.31590/ejosat.742789 ↗