【作者】 董明；

【导师】 叶青；

【作者基本信息】 长春理工大学 ， 计算机应用技术， 2009， 硕士

【摘要】 图像分割技术是图像识别、分析的基础,其主要应用领域包括智能移动机器人的场景理解、智能视频监控中的运动目标提取、基于内容的图像检索、基于内容的图像压缩等,本文首先对图像分割的基本理论和基于边缘的图像分割进行了详细阐述,简单介绍了一些常见的边缘检测方法和算子,给出了不同算子对同一幅图像进行分割的结果,并对结果进行了分析。在此基础上分别针对灰度图像和彩色图像的分割给出具体处理方法和实现过程。结合数学形态学、正交变换技术、运用扩展的微分算子提高算法的抗噪性,设计基于子块的区域生长方法,利用颜色信息减少彩色图像的过度分割。更多还原

【Abstract】 Image segmentation is the basic task for image recognition and interpreting. Its applications include computer vision of mobile robots, extraction of moving objects in intelligent video monitoring systems, content based image retrieval, content based image compression, and so on. In this paper, the basic theory of image segmentation and image segmentation based on the edge introduced firstly, A brief introduction of common edge detection methods and operators is completed secondly, Finally, The result of image segmentation with different operators on the same image are given, In the paper processing procedure for grayscale images and color image segmentation are given. Combination of mathematical morphology, orthogonal transformation technology, and the expansion of the differential operator to enhance the anti-noise power and design of growing methods based on sub-block and color information for reducing over-segmentation is presented in details.更多还原