| Abstrakt: |
Seeds play an essential role in corn cultivation. Seed is one of the determining factors for plants to grow well. Corn seeds generally are diploid, with two chromosomes in one set. Besides diploid, there are haploid seeds that only have one chromosome. The haploid is only 0.1% of the total natural corn seed. Engineering technology development produced double haploid (DH). Corn seed yields can genetically improve plants. DH can shorten the period and improve breeding efficiency. In this article, we classify the image of corn seeds--public data from a rovile dataset with 1,230 haploid and 1,770 diploid images. The research steps included pre-processing, resizing, and undersampling the majority class for balanced data. Then, split 80% training and 20% testing data. The training data uses 5-fold cross-validation. Classification using a Convolutional Neural Network (CNN) with modified VGG architecture was made by adding two dropout layers 0.5 after the dense layer. The CNN architecture also uses transfer learning and fine-tuning techniques. Transfer learning improves performance, minimizes computing, and reduces training time. Fine tuning aims to taking a model that has been trained on a specific task and then piecing together the last few layers of that model to solve a new task. The model from the crossvalidation results is then used for data testing. The test results show that the performance for accuracy, precision, recall, f1-score, and AUC is 96.83%, 95.9%, 98.87%, 97.36%, and 96.39%, respectively. [ABSTRACT FROM AUTHOR] |
