Multimodal Point Distribution Model For Anthropological Landmark Detection

While current landmark detection algorithms offer a good approximation of the landmark locations, they are often unsuitable for the use in biological research. We present multimodal landmark detection approach, based on Point distribution model that detects a larger number of anthropologically relevant landmarks than the current landmark detection algorithms. At the same time we show that improving detection accuracy of initial vertices, using image information, to which the Point distribution model is fitted, increases both the overall accuracy and the stability of the detected landmarks.We show results on data from the public FIDENTIS Database, created for the anthropological research, and compare them to the state-of-the-art landmark detection algorithms that are based on statistical shape models.