A crosstalk tolerated neural segmentation methodology for Brainbow images

Authors:
Tung-Yu Wu;Hung-Hui Juan;Henry Horng-Shing Lu;Ann-Shyn Chiang
Affiliations:
National Chiao Tung University, Hsinchu, Taiwan;National Chiao Tung University, Hsinchu, Taiwan;National Chiao Tung University, Hsinchu, Taiwan;National Tsing Hua University, Hsinchu, Taiwan
Venue:
Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies
Year:
2011

Citing 3
Cited 0

Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
A Closed-Form Solution to Natural Image Matting

IEEE Transactions on Pattern Analysis and Machine Intelligence
Spectral Matting

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we develop a methodology to extract the neural components from Brainbow images. Brainbow, a new genetic engineering technology, can help scientists understand the mechanism of an olfactory system. However, crosstalk among channels exists in these images. In addition, it is necessary to develop an automatic method to analyze these data. In our proposed system, we adopt Gaussian mixture model to model the phenomenon of crosstalk and reconstruct the Brainbow images. Spectral matting is applied to extract neural components from different channels. Under this system, we can extract useful information from Brainbow images efficiently and correctly.