CAJ | 학술논문

为了提高图像分割的准确度，尽可能降低分割边缘噪声对图像分割的影响，提出了一种基于降雪模型的图像分割方法，先对降雪模型及积雪表面效应做了详细分析，得出降雪模型运用于图像分割具有较强的适应性，接着在传统的随机游走图像分割算法中加入了自适应降雪模型的特性，生成新的算法，最后运用虚拟图像和真实图像进行算法性能实例仿真，结果表明，该算法的图像分割性能优于常见的NCut和传统随机游走图像分割算法，具有一定的研究价值。
위료제고도상분할적준학도，진가능강저분할변연조성대도상분할적영향，제출료일충기우강설모형적도상분할방법，선대강설모형급적설표면효응주료상세분석，득출강설모형운용우도상분할구유교강적괄응성，접착재전통적수궤유주도상분할산법중가입료자괄응강설모형적특성，생성신적산법，최후운용허의도상화진실도상진행산법성능실례방진，결과표명，해산법적도상분할성능우우상견적NCut화전통수궤유주도상분할산법，구유일정적연구개치。
In order to improve accuracy of image segmentation and reduce the effect of noise on the cutting edge of image segmentation as much as possible,a new image segmentation method based on the model of the snowfall was proposed,Firstly,snowfall model and snow surface effect were analyzed in detail, the snow model was applied to image segmentation with strong adaptability, and then mixed the traditional random walk image segmentation algorithm with adaptive snow model characteristics to generate a new algorithm,finally made performance simulation using virtual and real images algorithm,the results showed the image segmentation performance is better than the common NCut and the traditional random walk algorithm for image segmentation,and it had certain research value.