In this paper, an improvement approach of Hough transform for tables detection and extraction from scanned document images is achieved as one of the main stages in document recognition to recognize between original and faked documents. The improvements fundamentally originate from the modulation of the standard Hough transform (SHT)parameter selection, peak threshold and voting scheme. Peakvalues formed by noise edges are thus lowered compared with those formed by clear edges. Experimental results show the proposed method leads to significant suppression of false peaks in Hough space and is thus effective. The parameters can be determined empirically in advance, which their advantage to use the proposed method in fully automated lines detection applications.