ESTIMATION OF SKEW ANGLE IN TEXT-IMAGE ANALYSIS BY SLIDE - SUBSPACE-BASED LINE DETECTION

A new signal processing method is developed for estimating the skew an gle in text document images. Detection of the skew angle is an importa nt step in text processing tasks such as optical character recognition (OCR) and computerized filing. Based on a recently introduced multili ne-fitting algorithm, the proposed method reformulates the skew detect ion problem into a special parameter-estimation framework such that a signal structure similar to the one in the field of sensor array proce ssing is obtained. In this framework, straight lines in an image are m odeled as wavefronts of propagating planar waves. Certain measurements are defined in this virtual propagation environment such that the lar ge amount of coherency that exists between the locations of the pixels on parallel lines is exploited to enhance a subspace in the space spa nned by the measurements. The well-studied techniques of sensor array processing (e.g., the ESPRIT algorithm) are then exploited to produce a closed form and high-resolution estimate for the skew angle.