Non Destructive fruit quality assessment in packing house could be carried out using near infrared spectroscopy. However the prediction performance can be affected by measurement conditions ("external parameter") such as temperature or stray light variation. In this work we propose a methodology to reduce the effect of the fruit temperature on sugar content prediction. Two approaches were used to correct the temperature effect depending on wheter temperature is measurable or not. In the case of measurable temperature, three methods were tested. The first one uses a spectrum correction while the second and third ones are based on regression coefficients which vary with temperature. In case of non-measurable temperature, the studies have led to robust calibration models and to a self correcting model (where fruit temperature is estimated using spectral data). All techniques were tested with 'Golden Delicious' apples. Our study have shown that the most efficient models remove the temperature from the spectral space. These methodologies can be used to minimize of other external parameter on NIR calibration