Inverse Sigmoid-Based X-Ray Image Enhancement

Objectives: The retinex algorithm efficiently recovers image details in the dark regions. That is mainly due to the separation of illumination and reflection in images as well as the logarithm that is similar to the human vision system. However, it fails to recover details in bright regions. This paper proposes a modified approach introducing a new logarithm formula to obtain contrast improvements in both dark and bright regions. Methods/Statistical analysis: The proposed method suggests using the inverse-sigmoid function instead of the log function in the retinex processing as a tone mapping. Findings: In our experimental results on X-ray images, the comparison results clearly demonstrated that our method is superior to the conventional method in the view point of recovering bright regions. Another advantage of our method is that it can be easily extended by adopting the improved frameworks for the retinex algorithms. Improvements/Applications: The proposed method can be used for X-ray image enhancement.