红外图像分割算法分析

The Research of the Segmentation Algorithm on the IR Image

根据红外图像的特点,提出了一种测量目标红外辐射面积的算法。采用二维otsu算法和变阈值统计平均算法的目标图像进行分割算法,采用均值算法和中值算法去除图像噪声,采用二维otsu算法初二值化去噪后图像,在以此阈值为基准变换阈值得到一组二值化后图像,统计平均二值化后的图像,设定阈值得到最终二值化结果,在结合原图像得到分割结果。最后通过与一维和二维otsu图像分割算法试验比较,验证了此算法的有效性。

An algorithm for measuring the area of IR object is proposed based on the feature of the IR image. The IR image is segmented using the 2D-Ostu and the statistical mean algorithm based on the changed threshold. The noise of the image is decreased using the mean and median filter. The denoised image is segmented according to the 2D-Otsu algorithm and the segmented threshold value is set as the primary one. A set of the segmented images can therefore be obtained using the changed thresholds based on the primary threshold. The mean image is gotten by averaging the images. The binary image is finally achieved using the set threshold. The validity of the algorithm is verified by comparing the segmented result with 2D-Otsu and 1D Otsu algorithm.