Deep-plant: Plant identification with convolutional neural networks

Convolutional neural networks (CNNs) can identify plant species by learning unique features, particularly venation patterns of different orders, without relying on manually crafted data. This approach demonstrates superiority over existing methods when combined with various classifiers. Researchers at the Royal Botanic Gardens, Kew, tested this system using 44 plant species, employing a visualization technique based on deconvolutional networks to interpret the CNN's learned features. The study highlights CNNs' potential for unsupervised feature learning in plant identification, offering a more efficient and accurate alternative to traditional techniques.

Lee, S. H., Chan, C. S., Wilkin, P., & Remagnino, P. (2015). Deep-plant: Plant identification with convolutional neural networks. 2015 IEEE International Conference on Image Processing (ICIP), 452–456. https://doi.org/10.1109/icip.2015.7350839