Method for extracting titles from digital images

Abstract

A method of delineating titles within a grayscale image, in which a grayscale image is received, e.g., by scanning a document, and then is subjected to multi-level thresholding to obtain a plurality of binary images representing the original grayscale image. Each of the binary images is preferably pre-processed to filter any noise components from each of the binary images, and then all connected components within each of said binary images are identified, optionally filtered, and then clustered to identify possible title regions within each of the binary images. Next, each binary image is preferably post-processed to merge possible title regions comprising strokes and to remove non-title regions from the previously identified possible title regions in each of the images by comparing characteristics of the previously identified possible title regions to pre-determined criteria. Further, certain of the previously identified possible title regions within each of the binary images which satisfy pre-determined criteria are merged together. Still further, title regions within each of the binary images are combined after the post-processing step and the merging step. Finally, certain of the previously identified possible title regions for different layers are preferably merged to identify all possible title regions. Once the title region are located, various processing can be performed to extract the text from the title region.