copy text to be scanned more accurately into a soft copy. He had collaborated on the project with Dr Lu Shijian from A*STAR’s Institute for Infocomm Research (I2R). Their joint work was submitted to the 2009 Document Image Binarization Contest (DIBCO 2009), where it beat 35 research groups worldwide to win the top spot.

DIBCO 2009 was organised by the National Center for Scientific Research “Demokritos”, in Athens, Greece, and it was held in conjunction with the 10th International Conference on Document Analysis and Recognition (ICDAR 2009) in Barcelona, Spain, July 2009, an important international forum for the document analysis research community.

Commenting on the win, SoC Dean Professor Ooi Beng Chin said: "SoC is glad to share the sense of achievement chalked up by our colleague, Professor Tan Chew Lim at DIBCO. The win at the international event is testament to the cutting-edge research that Prof Tan has been performing in the area of image and text recognition. Our School celebrates with Prof Tan his pursuit of excellence."

Prof Tan and Dr Lu’s algorithm had competed against 43 others from research organisations in Europe, US, Australia and Asia. It produced the best detection performance, winning it the coveted top spot. The algorithms were applied on a testing dataset which consisted of five machine printed and five handwritten images resulting in a total of 10 images for which the associated human-segmented (text) images were built for the evaluation.

Human-segmented images act as the benchmark to evaluate the accuracy of the designed computer algorithms.The selection of the images in the dataset was made so that it contains representative degradations as in the real world that appears frequently (e.g., variable background intensity, shadows, smear, smudge, low contrast, bleed-through and show-through).

DIBCO 2009 is the first international document image binarisation contest organized in conjunction with the 10th International Conference on Document Analysis and Recognition (ICDAR 2009). The general objective of the contest is to identify current advances in document image binarisation using established evaluation performance measures. Document image binarisation is an important step in the document image analysis and recognition, a technology often used in Optical Character Recognition software used to drive scanning software.