This paper proposes a multi-spectral imaging system, developed using a commercial-grade camera, under two commonly used illumination. Rather than using conventional direct or diffuse light, the novelty of our method is to use a cross-polarized imaging system to eliminate glare and specular highlights. Two RGB images are captured under two different color temperature lighting conditions. An improved reflectance estimation method is developed to transform camera RGB under two illumination to spectral reflectance using a regulated model, combining the polynomial expansion of the camera signals with optimally selected feature. The method was tested using both a semi-gloss ColorChecker SG (140) and matte ColorChecker DC (240) chart. The results indicate that the proposed method significantly outperforms the traditional methods both in terms of spectra and colorimetric accuracy. This new multi-spectral imaging system is sufficiently precise to predict spectra properties and its performance within an acceptable range.