Oral cavity CBCT superpixel generation method based on marginal probability

• Main Authors: LONG HAIXIA, WU FULI, XING SHAOHENG, WANG KAIDONG, XU XINLI, GUAN QIU
• Format: Patent
• Language: Chinese; English
• Published: 01.10.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses an oral cavity CBCT superpixel generation method based on marginal probability. The method comprises the following steps: 1) initializing a CT value; 2) conducting pixel feature mapping; 3) calculating the pixel density; 4) calculating a pixel distance and a decision value; 5) generating a superpixel; and 6) merging unreasonable areas. The oral cavity CBCT superpixel generation method provided by the invention has the advantages of strong robustness, high edge recall rate, high segmentation precision and automation, the convenience and effectiveness of CBCT image preprocessing are improved, and the loss rate of a preprocessed image is reduced. 一种基于边缘概率的口腔CBCT超像素生成方法，包括以下步骤：1)CT值初始化；2)像素特征映射；3)计算像素密度；4)计算像素距离和决策值；5)生成超像素；6)合并不合理区域。本发明提出了一种鲁棒性强、边缘召回率高、可达分割精度高且自动化的口腔CBCT超像素生成方法，提高了CBCT图像预处理的便捷性和有效性，降低了预处理的图像损失率。