Application of digital image processing in automated analysis of insect leaf mines

Automated species identification has become a popular alternative to manual classification in the past few decades, as a result of advancement in digital image processing techniques and machine learning algorithms. This project aims to devise a new approach for the detection of leaf mines and fungal spots from digital images, and to investigate the possibility of monitoring the growth of leaf mines. Leaf-mining insects primarily belong to the orders of moths (Lepidoptera), flies (Diptera) and beetles (Coleoptera); or the suborders of sawflies (Symphyta) and wasps (Apocrita). Every spring and summer the larvae of leaf-mining insects feed on leaf tissues until maturity and vacate the mines as adults. As most species of leaf miners attack garden plants or crops, they are generally regarded as pests, despite rarely causing severe long-term detrimental effect on their host plants. Increase in human activities has led to the spread of these invasive species globally in recent years, and the demand for an effective classification system to monitor their distribution is rising consistently. Samples from three species of leaf-mining insects were included in this project: horse chestnut leaf miner (Cameraria ohridella), apple leaf miner (Lyonetia clerkella), and holly leaf miner (Phytomyza ilicis). Leaves with tar spots (Rhytisma acerinum) were also introduced as variations. The proposed method uses image processing techniques such as thresholding, conversion between colour spaces, edge detection, image segmentation, and morphological operations. This project also explores the use of machine learning algorithms as analytical monitoring and predictive tools, using the growth of C. ohridella leaf mines as an example.