Abstract
New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. The aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. In addition, we correlated the appearance of seeds to their physiological performance. Images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. The appearance of soybean seeds is strongly correlated with their physiological performance.
Highlights
New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process
We developed and compared four different models to classify soybean seeds based on relevant visible aspects using a high-performance tool
The model based on interactive machine learning showed an overall accuracy of 0.83 (Table 1)
Summary
New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. IML approaches can be effective in problems with small datasets or complex datasets when traditional machine learning methods become inefficient[6] The combination of these machine learning algorithms with computer vision has brought new and promising perspectives for analyzing the quality of agricultural products, especially seeds[7,8,9]. These tools have become prominent due to their flexibility and transparency in dealing with new technologies[10], and new possibilities of application are opening in as yet little explored areas Among these tools, Ilastik is open-source software that allows the development of models based on interactive machine learning with images; it is easy to use and ideal for users without substantial computational k nowledge[4]. This software has been used in recent studies to measure the confluence of Hep G2 cell culture in phase-contrast m icrographs[11], Scientific Reports | (2020) 10:11267
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
