Automated Germination Classification using ORB Feature Extractor with Machine Learning Model
Keywords:Seed germination; Image processing; Computer vision; Machine learning; Germination classification.
Large-scale germination research is difficult and prone to observer error, affecting the need for automated approaches. The routine germination scoring usually depends on human observation has practically constrained the scale, accuracy, and frequency of such research. Image processing is also offered stimulating outcomes in the domain of seed detection or classifier and germination analysis. Machine learning (ML) based technique is supported to speed up the analysis of seed germination research to distinct seed cultivars. This study focuses on the development of Automated Germination Classification using ORB Feature Extractor with Machine Learning (AGCORB-ML) model. The proposed AGCORB-ML technique uses handcrafted features and ML classifiers for germination detection and seed quality assessment. In the presented AGCORB-ML technique, ORB technique is applied to produce a useful set of feature vectors from the germination images. For germination classification, two ML models are used such as support vector machine (SVM) and extreme learning machine (ELM). To demonstrate the effective germination classification performance of the AGCORB-ML technique, an extensive range of experiments were performed. The simulation values stated that the AGCORB-ML technique reaches promising performance over other ML models.