Automated Training Data Generation for Microscopy Focus Classification
Image focus quality is of utmost importance in digital microscopes because the pathologist cannot accurately characterize the tissue state without focused images. We propose to train a classifier to measure the focus quality of microscopy scans based on an extensive set of image features. However, classifiers rely heavily on the quality and quantity of the training data, and collecting annotated data is tedious and expensive. We therefore propose a new method to automatically generate large amounts of training data using image stacks. Our experiments demonstrate that a classifier trained with the image stacks performs comparably with one trained with manually annotated data. The classifier is able to accurately detect out-of-focus regions, provide focus quality feedback to the user, and identify potential problems of the microscopy design.
Unable to display preview. Download preview PDF.
- 6.Nayar, S., Nakagawa, Y.: Shape from focus. IEEE PAMI 16(8), 824–831 (1994)Google Scholar
- 11.Padfield, D., Rittscher, J., Roysam, B.: Defocus and low CNR detection for cell tracking applications. In: MIAAB Workshop (2008)Google Scholar
- 12.Viola, P., Jones, M.: Robust real-time object detection. In: 2nd Int. Workshop on Statistical and Computational Theories of Vision Modeling, Learning, Computing and Sampling (July 2001)Google Scholar
- 17.Vollath, D.: Automatic focusing by correlative methods. J. Microsc 147, 279–288 (1987)Google Scholar
- 18.Huang, J., Mumford, D.: Statistics of Natural Images and Models. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 541–547. IEEE Computer Society, Los Alamitos (1999)Google Scholar