Colour image enhancement using bright and dark stretching techniques for tissue based Tuberculosis Bacilli detection

Abstract

Tuberculosis is a serious disease caused by infection with the germ Mycobacterium tuberculosis. Sputum sample analysis is a common method for TB bacilli detection. In some cases, tissue from the suspected system is also obtained using bronchoscope or fine needle aspiration for diagnosis. The Ziehl- Neelsen stain or acid-fast stain is a special stain used to identify the TB bacilli. The preparation of Ziehl-Neelsen slides require several procedures and the slide should be analysed under microscope. There are some factors that may degrade the image quality such as exposure and staining problems. Therefore, image enhancements are necessary to produce fine images in term of contrast and intensity. This paper proposes two methods for colour image enhancement; bright stretching and dark stretching algorithms. Both methods are well known to produce good image enhancement for gray scale images. However, the current study has adapted these methods to be used for colour images. Although the adapted image processing technique is quite simple, the results indicate that these methods may have some potential to be used for improving the quality of Ziehl-Neelsen slide images. The results show that both techniques were successfully improved the image contrast and enhance the image quality.