This research aims to develop an artificial intelligence (AI) estimator for the coating touch panel (TP) film. The AI estimator could estimate the transmittance of touch panel (TP) with different layers coating. It also could be used for helping the technician precisely set the relevant control parameters of evaporator in advance so that the optical quality of TP film could fit the customers request. In order to catch the unknown relationship between the films transmittance and its all possible influencing factors, the neural network (NN) is taken as the AI tool. In other words, a fast and precise intelligent manufacturing mechanism for TP evaporation process is expected to be developed and this intelligent mechanism could be practically used in the real industrial applications.

In this paper, we present an improved version of CAMSHIFT algorithm applying on surveillance videos. A 2D, hue and brightness, histogram is used to describe the color feature of the target. In this way, videos with poor quality or achromatic points can be characterized better. The flooding process and contribution evaluation are executed to obtain a precise target histogram which reflects true color information and enhances discrimination ability. The proposed method is compared with existing methods and shows steady and satisfactory results.