Algorithm of measuring temperature with infrared imager based on improved neural network

According to the principles of thermal radiation and temperature measurement with infrared imager, a general computing formula was deduced for the measurement of surface temperature and the corresponding relationship between the thermal value and the true temperature of infrared images was investigated. A least squares method(LSM) and an improved neural-network method was developed to calculate the temperature to diminish the deviation of neural-network method. Both the two methods used the ratios among the three basic colors output from the infrared imager as the independent variable or input variable which can personalize the colorimetric temperature-measurement algorithm to reduce the deviation from emissivity, soot and combustion flame on the temperature result. Simulation results show that the precision of these two methods are higher than that of the traditional neural-network method. In addition, the precision of the proposed neural-network method is higher than that of the least squares method.