Localization of Drosophila embryos using connected components in scale space

Localization of Drosophila embryos in images is a fundamental step in an automatic computational system for the exploration of gene-gene interaction on Drosophila. In this paper, we introduce a localization framework based on the analysis of connected components in the Gaussian scale space of an embryonic image. We propose three criteria for the selection of the optimal scale. The experiment results show the promise of the proposed methods.