A Comparison of Machine Learning Methods on Hyperspectral Plant Disease Assessments Yu-Hui F. Yeh*. Wei-Chang Chung*. Jui-Yu Liao**. Chia-Lin Chung**. Yan-Fu Kuo*. Ta-Te Lin* * Department of Bio-Industrial Mechatronics Engineering, National Taiwan University, Taipei, Taiwan, R.O.C. (Tel: 886-2-3366-5331; e-mail: m456@ ntu.edu.tw). ** Department of Plant Pathology and Microbiology, National Taiwan University, Taipei, Taiwan, R.O.C. (e-mail: clchung@ntu.edu.tw) Abstract: As plant diseases could cause agricultural production and economic loses, there is a need of fast and effective plant disease detection and assessment methods. Non-destructive methods have gained popularity among these methods as they do not affect plant growth while examining plant health conditions. Not only plant diseases can be detected but also production can be improved with proper quality controls. Hyperspectral imaging is one of the non-destructive examination techniques which have been widely applied in agriculture. Hyperspectral image analysis has been applied to different problems including plant disease detection and assessments. It provides not only spatial image but also spectral information of the observed object. This research has aimed to compare two hyperspectral image analysis methods: stepwise discriminant analysis (SDA) and spectral angle mapper (SAM) and the proposed Simple Slope Measure (SSM) method in strawberry foliage Anthracnose assessment. Anthracnose is one of the most devastating diseases for strawberries. Anthracnose disease can affect the whole plant and may result in 100 percent fruit loss from crown and fruit rot. Hence, an early detection of the Anthracnose disease will be beneficial to ensure production and quality of strawberries. This research has shown that the three different Anthracnose infection status (healthy, incubation and symptomatic) could be separated by the methods examined. The performance of these disease assessment models were evaluated and compared. The examination outcomes prove the feasibility to assess strawberry foliage Anthracnose nondestructively and as early as the symptoms not visible to naked eyes. As soon as early detections of the Anthracnose disease are achievable in the strawberry field, the damage to strawberry production due to the spread of Anthracnose disease could be reduced. Keywords: Hyperspectral Imaging, Plant Diseases, Machine Learning Algorithms. 1. INTRODUCTION The agricultural production and economic loses across the world can be affected critically by both physiological and infectious plant diseases. In particular, plant diseases in grains and crops may cause food insecurity and famines. Common sources of infection include insects and microorganisms like bacteria, funguses and viruses. Hence, plant disease predetermination and prevention has raised great interests in research, especially in real-time and non- destructive techniques. Hyperspectral image analysis has been widely applied to geology and mining applications and other problems such as food safety control and surveillance. Plant disease detections and assessments are also popular research domains in hyperspectral image application field (Coops et al., 2003; Mahlein et al., 2012; Qin et al., 2012). Hyperspectral images provide both spatial image and spectral information of the observed object. These information is much resourceful than other imaging techniques or spectral examination methods. Anthracnose is one of the most devastating diseases for strawberries. Anthracnose is an all-year-round fungal disease spreading through air and rain-splash. This disease may result 100 percent fruit loss from crown and fruit rot (Curry et al., 2002; Ellis and Erincik, 2008). The strawberry diseases were diagnosed through destructive procedures such as DNA extraction and fluorescence imaging (Sreenivasaprasad et al., 1996; Vargas et al., 2004). If non-destructive strawberry Anthracnose detection methods are available, strawberry production and quality can be ensured. This research aims to assess strawberry foliage Anthracnose disease by hyperspectral imaging. Two hyperspectral image analysis methods, spectral angle mapper (SAM), stepwise discriminant analysis (SDA) and a simple slope measure (SSM) method were applied to evaluate the hyperspectral imaging assessment accuracy and efficiency. The results show the feasibility of hyperspectral imaging not only in strawberry foliage Anthracnose diagnosis but also early detection.