Biological image data classification using machine learning algorithms

Machine learning is an exciting and widely used field in computational world. In this work multiclassification tasks were performed on two similar, but different tree leaf image datasets with the aim to find simple universal learning algorithm for leaf classification. K-nearest neighbourhoods, Support Vector machines and logistic regression algorithms gave the most accurate score, but PCA dimension reduction algorithm showed that data has a lot of noise therefore accuracy is not very percise. With manually created dataset the biggest challenge was image processing tasks since images were taken without professional equipment. These algorithms gave unsatisfactory results mainly because images were very noisy