Abstract
Upon illumination of a sufficient amount of light, the chlorophyll molecules of a plant start to emit photons in the far red region of the light spectrum. This phenomenon is also known as chlorophyll fluorescence. In this thesis a classi- fier is built that serves as a benchmark for plant classification via chlorophyll a fluorescence. A data set of 2500 samples was acquired by illuminating a total of 500 leaves gathered from five different plants with seven LEDs. To achieve an optimal model, a convolutional neural network (CNN) was designed and trained on complete fluorescence spectra. The network achieved an average accuracy of 95,7% on classifying five plants. Furthermore, the networks ac- curacy on a smaller set of LEDs was tested. In the end, a low cost approach was trained and evaluated, reaching an accuracy of 68%. This approach uses simulated phototransistor data instead of full spectra acquired with a spec- trometer.