Abstract:

The various embodiments of the present invention provide an image of an insect is captured. The image is read for prediction of the insect species by converting the captured image into a grayscale. The captured image is further segmented into a plurality of images based on a number of insect in the captured image to derive interested features or points of interest in each image. Then, a pixel value of each point of interest is derived. An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest. The surface area data is fed in to a random forest model to calculate to a confidence score. The confidence score is used to predict the insect species.