CAJ | 학술논문

图像分割是图像处理中的重要工作,医学图像的多样性和复杂性使其在图像分割中具有较大的难度。阈值法由于高效、简单而成为图像分割的重要方法,但对于复杂的医学图像,其效果并不很理想。Powell法是最好的直接搜索法,利用改进的Powell法可以更好地搜索目标。为此,提出了一种将Otsu法和Powell法相结合的图像分割方法,仿真实验表明,该方法可以快速有效地分割图像,鲁棒性强。
도상분할시도상처리중적중요공작,의학도상적다양성화복잡성사기재도상분할중구유교대적난도。역치법유우고효、간단이성위도상분할적중요방법,단대우복잡적의학도상,기효과병불흔이상。Powell법시최호적직접수색법,이용개진적Powell법가이경호지수색목표。위차,제출료일충장Otsu법화Powell법상결합적도상분할방법,방진실험표명,해방법가이쾌속유효지분할도상,로봉성강。
The mage segmentation is an important task in image processing.The image segmentation has great difficulty in the medical images because of the diversity and complexity of medical images.The threshold method becomes an important method of image segmentation as it＇s simple and efficient.But the threshold is not very satisfactory to the complex medical image segmentation.Powell algorithm is the best direct search method and the improved Powell method can do the targeted search better.An image segmentation method is introduced,which combines Otsu algorithm and Powell algorithm.The experiment result shows that the method can segment images fast and efficiently with robust.