Abstract. A kind of artificial neural network (BP-ANN) was used to classify the different kinks of apples with the reflected spectrum. The spectrum (from 460nm to 720nm) of some specks on the surface of the apples was measured with the spectrometer. A kind of BP-ANN with single hidden layer was devised to identify two sorts of the apples (the scar and the rotten) by the biological surface spectrum. To get the optimized parameters of the neural network, it was studied that the performance of the ANN with the different neurons numbers of the hidden layer, the different ranges of the output, the error of network with the different MSE(Minimum Squares Error) goal.

Abstract-In order to detect the skin's disease with the spectral instrument, the reflection spectrum should be gotten to calculate the chromatic values and be analyzed compared. In this paper a kind of chromatic system with self-made fiber probe was designed to measure the spectrum to distinguish the skin normal or not in this paper. The probe was used to minimum the interference outside to the chromatic measurement in order to develop the chromatic measurement accuracy. Through the system, first we got the spectrum of different skin, the normal and the pathological from different part of the sick body, then calculating the tristimulating value and chromatic aberration, we can distinguish the normal with the pathological by the chromatic aberration and make sure if the disease is cured. Good results are achieved by the analyzing of the skin with this system, so a method to distinguish the pathological skin automatically and objectively is attained.