The Hough transform is a robust tool to extract features, such as straight edges, circles, or ellipses from images and describe them parametrically. However, linear edge in real image is not an ideal line. Tiny orientation change commonly exists in linear edge obtained by edge detector. Standard Hough transform need to discrete Hough space, discreteness must lead to statistical error, which makes it difficult to extract the tiny, short and small line when detecting long line. It makes detecting failure of the tiny line or cannot contain all information of these small lines. In this paper, proposed improved Hough transform can eliminate the statistical error caused by discreteness. Consequently eliminate the bad effect of detecting short and tiny line caused by detecting long line, it make the long line and the short, tiny line can be detected precisely at the same time.