Plant pest recognition and detection is vital for food security, quality of life and a stable agricultural economy. This research demonstrates the combination of the k-means clustering algorithm and the correspondence filter to achieve pest detection and recognition. The detection of the dataset is achieved by partitioning the data space into Voronoi cells, which tends to find clusters of comparable spatial extents, thereby separating the objects (pests) from the background (pest habitat). The detection is established by extracting the variant distinctive attributes between the pest and its habitat (leaf, stem) and using the correspondence filter to identify the plant pests to obtain correlation peak values for different datasets. This work further establishes that the recognition probability from the pest image is directly proportional to the height of the output signal and inversely proportional to the viewing angles, which further confirmed that the recognition of plant pests is a function 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, which proves the effectiveness of the algorithm for the detection and recognition of plant pests.
展开▼
