This paper presents a document image binarization tech- nique that segments text from badly illuminated document images. Based on the observations that text documents nor- mally lie over a planar or smoothly curved surface and have a uniformly colored background, badly illuminated docu- ment images are binarized by using a smoothing polynomial surface, which estimates the shading variation and com- pensates the shading degradation based on the estimated shading variation. Badly illuminated document images are accordingly binarized through the global thresholding of the compensated document images. Compared with the re- ported methods, the proposed technique is tolerant to the variations in text size and document contrast. At the same time, it is much faster and able to produce a binary text im- age with little background noise.