AUTOMATIC PLANT PEST DETECTION AND RECOGNITION USING k-MEANS CLUSTERING ALGORITHM AND CORRESPONDENCE FILTERS

Plant pest recognition and detection is vital for f ood security, quality of life and a stable agricult ural economy. This research demonstrates the combination of the k -means clustering algorithm and the correspondence filter to achieve pest detection and recognition. The detecti on of the dataset is achieved by partitioning the d ata space into Voronoi cells, which tends to find clusters of comparable spatial extents, thereby separating the objects (pests) from the background (pest habitat). The det ection is established by extracting the variant dis tinctive attributes between the pest and its habitat (leaf, stem) and using the correspondence filter to identi fy the plant pests to obtain correlation peak values for differe nt datasets. This work further establishes that the recognition probability from the pest image is directly proport ional to the height of the output signal and invers ely proportional to the viewing angles, which further c onfirmed that the recognition of plant pests is a f unction of their position and viewing angle. It is encouraging to note that the correspondence filter can achieve rotational invariance of pests up to angles of 360 degrees, wh ich proves the effectiveness of the algorithm for t he detection and recognition of plant pests.