
Oral cancer is the sixth most common cancer globally and most reported cancer in India with fourteen deaths in an hour on a yearly basis. Oral cancers can be cured with early detection but the biggest hindrances are lack of awareness, cost of tests and the immense workload of the cyto-pathologist leading to delay and errors in the detection process. An effective, semi-automated system described in this paper has made an attempt towards mitigating the above mentioned issues by combining techniques like Papanicolaou (Pap) smear, image processing and neural networks. The primary concern and objective of the system developers is to help cure the menace of oral cancer that is plaguing India and the world. This system is perhaps one of the first successful attempts at semi-automating the process.