Abstract
Geometric morphometrics has become an important approach in insect morphology studies because it capitalizeson advanced quantitative methods to analyze shape. Shape could be digitized as a set of landmarks fromspecimen images. However, the existing tools mostly require manual landmark digitization, and previous workson automatic landmark detection methods do not focus on implementation for end-users. Motivated by that, wepropose a novel approach for automatic landmark detection, based on visual features of landmarks and keypointmatching techniques. While still archiving comparable accuracy to that of the state-of-the-art method, ourframework requires less initial annotated data to build prediction model and runs faster. It is lightweight also interms of implementation, in which a four-step workflow is provided with user-friendly graphical interfaces toproduce correct landmark coordinates both by model prediction and manual correction.