Handwritten and Typewritten Word and Character Separation in Unconstrained Document Images

Separating handwritten and typewritten text within unconstrained paper documents can provide more accurate and efficient OCR results. This paper presents a technique developed that can isolate both the typewritten and handwritten portions of a document image. The classification between handwritten and typewritten text occurs at both the character and the word level. Characters are grouped into words using a word separation technique with an “island” grouping method. Structural features of handwritten and typewritten characters are examined. The method developed correctly identified with probability close to 100% of the total number of typewritten words in a set of 30 handwritten documents.

• Type: Conference
• Year: 2007
• Where: IPCV
• Authors: Jia Tse, Dean Curtis, John Bunch, Christopher Jones, Evangelos A. Yfantis, Aaron Thomas
• Keywords: Handwritten Portions, Image Processing, IPCV 2007, Typewritten, Typewritten Text