Improved algorithm for blob detection in document images

This paper proposes a fast algorithm for blob detection for document images. Blobs are connected components in a binary image. Blobs need to be detected and extracted in order to obtain useful information from image. Blobs may be 4-connected or 8-connected. Various algorithms are proposed for detecting blobs [5]. As it is the backbone of all fundamental operations, it needs to be fast and accurate. Proposed algorithm makes use of the fact that most document images have more background units as compared to foreground units. Processing them unit by unit is more time consuming. So, algorithm works by processing them in blocks where each block consists of 8 units. In this way, numbers of comparisons are reduced significantly. Also the paper compares the proposed algorithm with five other algorithms on the basis of image size and execution time. Reduced number of comparisons makes it nearly 1.5 times faster than algorithms discussed in paper.