Deep Learning Techniques for Grape Plant Species Identification in Natural Images

• Published in: Sensors (Basel, Switzerland) Vol. 19; no. 22; p. 4850
• Main Authors: Pereira, Carlos S, Morais, Raul, Reis, Manuel J C S
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 07-11-2019; MDPI
• Subjects: Accuracy; alexnet deep model; Artificial intelligence; Automation; Classification; Corners; Datasets; Deep learning; Discriminant analysis; Flowers & plants; Geographical locations; grape variety identification; Grapes; Grapevines; Image classification; Image processing; Image warping; independent component analysis; leaf vein extraction; Model accuracy; Morphology; natural vineyard images; Neural networks; Pesticides; Plant diseases; precision viticulture; Standard deviation; Support vector machines; transfer learning techniques; Vineyards; Wineries & vineyards; AlexNet deep model; independent component analysis; natural vineyard images; grape variety identification; precision viticulture; leaf vein extraction; transfer learning techniques
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s19224850

Frequently, the vineyards in the Douro Region present multiple grape varieties per parcel and even per row. An automatic algorithm for grape variety identification as an integrated software component was proposed that can be applied, for example, to a robotic harvesting system. However, some issues and constraints in its development were highlighted, namely, the images captured in natural environment, low volume of images, high similarity of the images among different grape varieties, leaf senescence, and significant changes on the grapevine leaf and bunch images in the harvest seasons, mainly due to adverse climatic conditions, diseases, and the presence of pesticides. In this paper, the performance of the transfer learning and fine-tuning techniques based on AlexNet architecture were evaluated when applied to the identification of grape varieties. Two natural vineyard image datasets were captured in different geographical locations and harvest seasons. To generate different datasets for training and classification, some image processing methods, including a proposed four-corners-in-one image warping algorithm, were used. The experimental results, obtained from the application of an AlexNet-based transfer learning scheme and trained on the image dataset pre-processed through the four-corners-in-one method, achieved a test accuracy score of 77.30%. Applying this classifier model, an accuracy of 89.75% on the popular Flavia leaf dataset was reached. The results obtained by the proposed approach are promising and encouraging in helping Douro wine growers in the automatic task of identifying grape varieties.