Deep Learning for Tomato Diseases: Classification and Symptoms Visualization

This study investigated the potential of using hyperspectral imaging for detecting different diseases on tomato leaves. One hundred and twenty healthy, one hundred and twenty early blight and seventy late blight diseased leaves were selected to obtain hyperspectral images covering spectral wavelengths from 380 to 1023 nm. An extreme learning machine (ELM) classifier model was established based on full wavelengths. Successive projections algorithm (SPA) was used to identify the most important wavelengths. Based on the five selected wavelengths (442, 508, 573, 696 and 715 nm), an ELM model was re-established. Then, eight texture features (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation) based on gray level co-occurrence matrix (GLCM) at the five effective wavelengths were extracted to establish detection models. Among the models which were established based on spectral information, all performed excellently with the overall classification accuracy ranging from 97.1% to 100% in testing sets. Among the eight texture features, dissimilarity, second moment and entropy carried most of the effective information with the classification accuracy of 71.8%, 70.9% and 69.9% in the ELM models. The results demonstrated that hyperspectral imaging has the potential as a non-invasive method to identify early blight and late blight diseases on tomato leaves.

Accurate and timely detection of plant diseases can help mitigate the worldwide losses experienced by the horticulture and agriculture industries each year. Thermal imaging provides a fast and non-destructive way of scanning plants for diseased regions and has been used by various researchers to study the effect of disease on the thermal profile of a plant. However, thermal image of a plant affected by disease has been known to be affected by environmental conditions which include leaf angles and depth of the canopy areas accessible to the thermal imaging camera. In this paper, we combine thermal and visible light image data with depth information and develop a machine learning system to remotely detect plants infected with the tomato powdery mildew fungus Oidium neolycopersici. We extract a novel feature set from the image data using local and global statistics and show that by combining these with the depth information, we can considerably improve the accuracy of detection of the diseased plants. In addition, we show that our novel feature set is capable of identifying plants which were not originally inoculated with the fungus at the start of the experiment but which subsequently developed disease through natural transmission.