A Comparative Study of Image Segmentation Based on the Improved Meanshift Software with Edison

Image segmentation is the technique and the process to separate the image into regions which have different characteristics and extract the interested objects from the image. Meanwhile, image segmentation is a vital important issue in many fields such as image processing, pattern recognition and artificial intelligence and it has wide application in various fields. This paper performs a great deal of contrastive analysis experiments on a series of images by using improved meanshift software and Edison software. The results show that improved meanshift software is easier to segment clearly than Edison in terms of similar color; the improved meanshift software segmentation is smoother than Edison in image shadow, the segmentation results hold favorable consistency in terms of human perception; the improved meanshift software segmentation is clearer than Edison in texture segmentation such as vegetation. The improved meanshift software has a better effect on the segmentation of boundary, road, etc. Both of them can remove the noise points effectively, but improved meanshift software is more sensitive to brightness; while the Edison software has a faster speed compared to the improved meanshift software.