一种近红外静脉特征提取方法研究

A FEATURE EXTRACTION METHOD FOR NIR VEIN IMAGE

针对如何提高中医针灸和西医穿刺的精度问题,项目通过近红外(INR)成像设备的可视化技术,系统地研究了静脉图像特征提取模型。提出一种基于多方向Gabor滤波器的静脉图像增强与分割方法,构筑静脉信息研究模型。解决了近红外(NIR)光成像设备采集到的静脉图像出现对比度低、视觉模糊等缺陷,以及将各方向增强后的静脉图像的融合问题,并利用马尔可夫随机场分割,获得了满意的静脉信息研究模型,为完善中西医结合模式提供了可行手段,应用前景广泛。

Aiming at the problem of how to improve the accuracy of traditional Chinese medicine acupuncture and Western medicine puncture,the project systematically studied the feature extraction model of vein image through the visualization technology of near infrared(INR)imaging equipment.This paper proposed a vein image enhancement and segmentation method based on multi-directional Gabor filter,and constructed the vein information research model.It solved the problems of low contrast,blurred vision and other defects of vein images collected by NIR optical imaging equipment,as well as the fusion problem of vein images enhanced in all directions.The satisfactory vein image feature extraction model was obtained by using Markov random field segmentation,which provided a feasible means for improving the mode of integrated traditional Chinese and Western medicine,and had a wide application prospect.