Morphology based oral CT tissue images contrast enhancement

作者：Bao Guangqing; Song Ze^*; Yang Xinhua; Wang Xiaolan

来源：Journal of Computational Information Systems, 2014, 10(20): 8653-8660.

DOI：10.12733/jcis11852

• Contrast-enhanced images
• Image resolution enhancements
• Local Contrast Enhancement
• Morphological filters
• Morphological opening
• Multi scale morphology
• Noise suppressing
• Oral Computed Tomography (CT) images

Computed Tomography (CT) images are being widely used in the diagnosis of oral diseases. One of the major issues of these types of images is their low contrast of soft tissue. In this paper, in order to improve oral image resolution, a multiscale morphology based algorithm for both local contrast enhancement and noise reduction is proposed. The proposed algorithm uses discrete wavelet transform (DWT) to decompose the input image into different subbands. Then, the low-frequency subband image which includes soft tissue information have been enhanced by sigm function, followed by combining morphological opening and closing filter to generate a new contrast-enhanced image. The proposed technique has been tested on clinical oral CT images. The quantitative analysis of histogram and entropy show the superiority of the proposed algorithm over the conventional image resolution enhancement techniques. Visual results also verify the information of soft tissue is enriched, which is helpful to dentist's examination.

• 出版日期2014