The Otsu method is one of the commonly used threshold-based image segmentation methods. The two-dimensional Otsu method uses the two-dimensional histogram composed of the grayscale value distribution of the image pixels and the average grayscale distribution of the neighborhood pixels to perform threshold segmentation on the image. Since infrared images have the characteristics of low contrast, low signal-to-noise ratio, and blurred edges, if only two-dimensional Otsu is used to segment them, the segmented image will have unclear edge information and mis-segmentation due to the influence of noise. To address this problem, this paper proposes an infrared image segmentation method that combines morphology with two-dimensional Otsu. Experiments have shown that the use of morphology can retain the basic shape of the image, make up for the details of the segmented image, and make the outline of the image smoother, achieving better infrared image segmentation effects.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore