摘要
图像分割是任何图像分析过程中的首要任务,因为接下来所要做的工作(如特征提取、目标识别等)都取决于图像分割的质量。文章提出了一种改进的区域生长彩色图像分割方法iRGA(improvedRegionGrowingApproach)———基于子块色彩均值和方差的图像分割法。实验证明,该方法可以有效地减少计算复杂度和抑制噪声的干扰。
Image segmentation is an important task of any image analysis process.All the subsequent tasks,such as feature extraction and object recognition,rely heavily on the quality of the segmentation.This paper provides an improved region growing approach for color image segmentation—— — Color Image Segmentation Based on Block Mean and Variance.Experiments prove that it can decrease the complexity of computation and the mean value can make the influence of the vigorous pixels less.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第7期96-97,229,共3页
Computer Engineering and Applications
