Correction algorithm based on fuzzy modeling for the distorted image in the digital X-ray scanner system

Abstract

The Digital X-ray Scanner System (DX-Scanner) using the Multichannel Ionization Chamber (MIC) has many advantages. On the other hand, the scanned medical image has distorted pixels because of unsuitable integration time at the nonlinear acceleration period and vibration of the AC servo motor during scanning a patient in the system.

This paper proposes a correction algorithm based on fuzzy modeling. The proposed correction algorithm can correct the distorted medical image during scanning. Fuzzy modeling uses a clustering method for the nonlinear motor velocity in the algorithm. The algorithm reconstructs the normal medical image lines by calculating the moving distance every integration time during acceleration period of AC servo motor. The algorithm analyzes by comparing the distance of the acceleration period with the distance of the uniform velocity period in every integration time. The velocity for the acceleration period is able to be compensated via this algorithm. In addition, several image processing procedures are also included in the algorithm.

When the proposed correction algorithm is applied to the test pattern for checking the image resolution, its effectiveness is verified at scanning of 3.5 cm/sec, 7 cm/sec, and 14 cm/sec. The corrected image is a better image.