Hyperspectral Feature Selection for Detection of Chicken Skin Tumors

We consider a feature selection method to detect skin tumors on chicken carcasses using hyperspectral data. A chicken skin tumor is an ulcerous lesion that is surrounded by a rim of thickened skin. Detection of chicken tumors is a difficult detection problem because chicken tumors are of many sizes and shapes; some tumors appear on the side of chicken. In addition, different areas of normal chicken skins have a variety of hyperspectral response variations, some of which are very similar to the spectral responses of tumors. Similarly, different tumors have different spectral responses. Thus, proper training is needed and many false alarms are expected. Since the spectral responses on the lesion and thickened skin regions of tumors are considerably different, we train our feature selection algorithm to detect lesions and thickened skin separately; we then morphologically process the resultant images and we fuse the two detection results to reduce false alarms. Forward selection and modified branch and bound algorithms are used to select a small number of features that are useful for discrimination. Initial results show that our method has a good tumor detection rate and a low false alarm rate.