ABSTRACT
Grapevine (Vitis vinifera L.) currently includes thousands of cultivars. Discrimination between these varieties, historically done by ampelography, is done in recent decades mostly by genetic analysis. However, when aiming to identify archaeobotanical remains, which are mostly charred with extremely low genomic preservation, the application of the genomic approach is rarely successful. As a result, variety-level identification of most grape remains is currently prevented. Because grape pips are highly polymorphic, several attempts were made to utilize their morphological diversity as a classification tool, mostly using 2D image analysis technics. Here, we present a highly accurate varietal classification tool using an innovative and accessible 3D seed scanning approach. The suggested classification methodology is machine-learning-based, applied with the Iterative Closest Point (ICP) registration algorithm and the Linear Discriminant Analysis (LDA) technique. This methodology achieved classification results of 91% to 93% accuracy in average when trained by fresh or charred seeds to test fresh or charred seeds, respectively. We show that when classifying 8 groups, enhanced accuracy levels can be achieved using a "tournament" approach. Future development of this new methodology can lead to an effective seed classification tool, significantly improving the fields of archaeobotany, as well as general taxonomy.
ABSTRACT
Grapevine (Vitis vinifera L.) is one of the classical fruits of the Old World. Among the thousands of domesticated grapevine varieties and variable wild sylvestris populations, the range of variation in pip morphology is very wide. In this study we scanned representative samples of grape pip populations, in an attempt to probe the possibility of using the 3D tool for grape variety identification. The scanning was followed by mathematical and statistical analysis using innovative algorithms from the field of computer sciences. Using selected Fourier coefficients, a very clear separation was obtained between most of the varieties, with only very few overlaps. These results show that this method enables the separation between different Vitis vinifera varieties. Interestingly, when using the 3D approach to analyze couples of varieties, considered synonyms by the standard 22 SSR analysis approach, we found that the varieties in two of the considered synonym couples were clearly separated by the morphological analysis. This work, therefore, suggests a new systematic tool for high resolution variety discrimination.
