The Segmentation and Identification of Handwriting in Noisy Document Images

In this paper we present an approach to the problem of segmenting and identifying handwritten annotations on noisy document images. In many types of documents such as correspondence, it is not uncommon for handwritten annotations to be added as part of a note, correction, clarification, or instruction, or for initials or a signature to appear as an authentication mark. It is important to be able to segment and identify such handwriting so we can 1) locate, interpret and retrieve them efficiently in large document databases, and 2) use different algorithms for printed/handwritten text or signature recognition. Our approach consists of two processes: 1) segmentation process which divides the text into regions with an appropriate level (character, word, line, or zone), and 2) classification process which identifies the segmented regions as handwritten. To determine the smallest possible region size where classification can be reliably performed, we conducted experiments at the character, word and zone level. We found that the reliable results can be achieved only at the word level with the classification accuracy of 97.3%. The identified handwritten text is further grouped into zones and verification at the zone level is used to reduce false alarms. Experiments show our approach is promising and robust.