Section: New Software and Platforms

ATLAS

Keywords: Image segmentation - Object detection - Photonic imaging - Image analysis - Fluorescence microscopy

Functional Description: The ATLAS software enables to detect spots in 2D fluorescence images. The spot size is automatically selected and the detection threshold adapts to the local image contrasts. ATLAS relies on the Laplacian of Gaussian (LoG) filter, which both reduces noise and enhances spots. A multiscale representation of the image is built to automatically select the optimal LoG variance. Local statistics of the LoG image are estimated in a Gaussian window, and the detection threshold is pointwise inferred from a probability of false alarm (PFA). The user only has to specify: i/ size of the Gaussian window, ii/ PFA value. The Gaussian window must be about the size of the background structures, increasing the PFA increases the number of detections.

• Participants: Patrick Bouthemy, Charles Kervrann, Jean Salamero, Jérôme Boulanger and Antoine Basset

• Partner: UMR 144 CNRS - Institut Curie

• Contact: Patrick Bouthemy

• Publication: Adaptive spot detection with optimal scale selection in fluorescence microscopy images

• URL: http://mobyle-serpico.rennes.inria.fr/cgi-bin/portal.py#forms::ATLAS