Year: 2017
Type: article
Abstract: In biology, the morphometric analysis is widely used to analyze the inter-organisms variations. It allows to classify\nand to determine the evolution of an organism’s family. The morphometric methods consider features such as\nshape, structure, color, or size of the studied objects. In previous works [8], we have analyzed beetle mandibles\nby using the centroid as feature, in order to classify the beetles. We have shown that the Probabilistic Hough\nTransform (PHT) is an efficient unsupervised method to compute the centroid. This paper proposes a new approach\nto precisely estimate the landmark geometry, points of interest defined by biologists on the mandible contours. In\norder to automatically register the landmarks on different mandibles, we defined patches around manual landmarks\nof the reference image. Each patch is described by computing its SIFT descriptor. Considering a query image, we\napply a registration step performed by an Iterative Principal Component Analysis which identify the rotation and\ntranslation parameters. Then, the patches in the query image are identified and the SIFT descriptors computed.\nThe biologists have collected 293 beetles to provide two sets of mandible images separated into left and right side.\nThe experiments show that, depending on the position of the landmarks on the mandible contour, the performance\ncan go up to 98% of good detection. The complete workflow is implemented in the MAELab framework, freely\navailable as library on GitHub.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2745194911