Comparison of Preprocessing Techniques for Dental Image Analysis

Abstract

Various dental disorders, such as lesions, masses, carries, etc. may affect the human dental structure. Dental radiography is a technique, which passes X-rays through dental structures and records the radiographic images. These radiographic images are used to analyze the disorders present in the human teeth. Preprocessing is a primary step to enhance the radiographic images for further segmentation and classification of images. In this work, the preprocessing techniques such as unsharp masking using high pass filter, bi-level histogram equalization and hybrid metaheuristic have been utilized for dental radiographs. The performance measures of the preprocessing techniques were analyzed. Results demonstrate that a hybrid metaheuristic algorithm for dental radiographs achieves higher performance measures when compared to other enhancement methods. An average Peak Signal-to-Noise Ratio (PSNR) value of 21.6 was observed in the case of a hybrid metaheuristic technique for dental image enhancement.