Estimating landmarks on 2D images of beetle mandibles

Abstract

Studying links between phenotype/genotype and agricultural practices is one of the main topics in agronomy research. Phenotypes can be characterized by informations like age, sex of animals/plants and more and more often with the help of image analysis of their morphology. From now, getting good quality of images for numerous individuals is easy but that leads to design automatic procedures to replace manual exploration of such amount of images. Several bottlenecks have been identified to analyze automatically images. One of them is segmentation of selected area and/or shapes, and another well-known one is setting automatically morphometric landmarks. Landmarks are points on the object which can be used to identify or to classify the objects. It exists a lot of methods to experiment landmarks setting, depending on the image contents. This work has been initiated by using the article of Palaniswamy et al. "Automatic identification of landmarks in digital images"[6]. They proposed a method based on calculus of a probabilistic Hough transform coupling to a template matching algorithm. They applied their method to the Drosophilia wings. In our study, we have gotten a set of 291 beetles . For each one 2D images of 5 different parts of their anatomy have been taken: mandibles left and right, head, pronotum and elytra. The first part of the project was to test how the Palaniswamy’s method could be used to analyze them. We have implemented all the required algorithms to compute positions of mandibles landmarks and compared the obtained results to landmarks which have been manually set by biologists. We will see that even positions automatically obtained are not fully precised, if we used centroid size to characterize mandibles, the size computed from automatic landmarks is closed to this one computed from the manual ones. Future works will focus on definition of a semi-landmarks procedure which would add some features as the measure of the curve between two landmarks.