AUTOMATIC ASSESSMENT MARK ENTRY SYSTEM USING LOCAL BINARY PATTERN (LBP)

Offline handwritten recognition continues to be a fundamental research problem in document analysis and retrieval. The common method used in extracting handwritten mark from assessment forms is to assign a person to manually type in the marks into a spreadsheet. This method is found to be very time consuming, not cost effective and prone to human mistakes. In this project, a number recognition system is developed using local binary pattern (LBP) technique to extract and convert students’ identity numbers and handwritten marks on assessment forms into a spreadsheet. The template of the score sheet is designed as in Appendix 1 to collect sample of handwritten numbers. The training data contain three sets of LBP histograms for each digit. The recognition rate of handwritten digits using LBP is about 50% because LBP could not fully describe the structure of the digits. Instead, LBP is useful in term of arranging the digits ‘0 to 9’ from highest similarity score to the lowest similarity score as compared to sample using chi square distance. The recognition rate is greatly improved to about 95% by verifying the output of chi square distance with the salient structural features of digits.