Optical Filter Design of Fluorescence Emission to Detect Poultry Skin Tumors

Abstract

The secure production of disease-free meat is crucial in the mass production environment. The fluorescence spectra of poultry have been gaining the practical use since the fluorescence response is very sensitive in detecting a particular biological substance. A hyperspectral image contains spectral information measured as a sequence of individual wavelength across broad spectral bands. This paper presents an optimal design method of emission filter in a hyperspectral fluorescence imaging system to detect skin tumors on poultry carcasses. The proposed method design the optimal emission filter using the linear discriminant analysis. It provides the optimal weighted combination of emission wavelengths in terms of discriminant power unlike band selection method which just finds a subset of significant spectral bands. The poultry skin tumor in fluorescence images is distinguishable by the pixel-wise intensity. The method can be extended to detect other biomedical abnormalities as well. In future research, we will incorporate the spatial information to determine the skin tumor more accurately.