Colour Contrast Enhancement on Preselected Cervical Cell for ThinPrep ® Images N. Mustafa 1 N. A. Mat Isa 2 M. Y. Mashor 3 N. H. Othman 4 1,3 Electronic & Biomedical Intelligent Systems (EBItS) Research Group, School of Mechatronic Engineering, Universiti Malaysia Perlis, 02600 Jejawi, Arau, Perlis, Malaysia E-mail: nazahah@unimap.edu.my 1 , yusoff@unimap.edu.my 3 2 School of Electrical & Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia. E-mail: ashidi@eng.usm.my 4 Pathology Department, School of Medical Science, Universiti Sains Malaysia, Medical Campus, 16150 Kubang Kerian, Kelantan, Malaysia E-mail: hayati@kb.usm.my Abstract ThinPrep ® monolayer cytology was introduced to overcome the limitations of conventional Pap smear test for screening of cervical cancer. The cytological features in ThinPrep ® images could be improved if unwanted background information and poor contrast could be eliminated. This study proposes a contrast enhancement technique, which is only applied on the cervical cell of interest. The proposed technique is divided into two stages. Firstly, the cervical cells of interest will be selected using the modified seed based region growing algorithm. Then, the contrast of cervical cell of interest in the ThinPrep ® will be enhanced by using three contrast enhancement algorithms. The cervical cell of interest will be applied with linear contrast algorithm and the proposed non- linear algorithms namely non-linear bright and non- linear dark contrast to enhance the contrast of the ThinPrep ® images. The results show that the proposed technique improves the image quality. Hence, the resultant image would be rendered more useful for further analysis by pathologists. 1. Introduction Cervical cancer is the most common malignancy in women of developing countries. Cervical cancer develops over a prolonged period covering two to three decades [1]. Therefore, the mortality related to cervical cancer can be substantially reduced through early detection and treatment. ThinPrep ® monolayer cytology was introduced to overcome the limitations of the conventional Pap smear [2]. However, the cytology image of ThinPrep ® captured from the ThinPrep ® slide using standard image analyzer usually has low contrast quality due to the magnification and overexposure to the light built in the system of the image analyzer. In some cases, the ThinPrep ® images are hazy and afflicted by unwanted noises [3][4]. These problems can hide and obscure the important cervical cells morphologies, hence increasing false diagnosis rate. Contrast is one of the factors that influenced the accuracy of interpretation of diseases based on medical images by pathologists or radiologists. To date, contrast enhancement process plays an important role in enhancing the quality and contrast of medical images [5]. Several previous studies have proven that contrast enhancement techniques are capable of