数字图像处理与应用 Class 8. 20200520
Lecture 8 Image Segmentation (1)
The segmentation problem
Points detection 点检测
Lines detection 线检测
Edges detection 边缘检测
Segmentation
The purpose of image segmentation is to partition an image into meaningful regions with respect to a particular application
图像分割的目的是将一幅图像按照特定的应用程序分割成有意义的区域
Segmentation should stop when the objects of interest in an application have been isolated
当应用程序中感兴趣的对象被隔离时,分割应该停止
The segmentation is based on measurements taken from the image and might be grey level, colour, texture, depth or motion
分割是基于从图像得到的测量,可能是灰度,颜色,纹理,深度或运动
补充:过分割、欠分割
图像分割的应用包括
Identifying objects in a scene for object-based measurements such as size and shape
为基于对象的度量(如大小和形状)识别场景中的对象
Identifying objects in a moving scene for object-based video compression (MPEG4)
基于对象的视频压缩在移动场景中识别对象(MPEG4)
Path planning for a mobile robots 移动机器人的路径规划
Medical image segmentation
Object detection for image analysis.
Object identification in a scene.
Path planning for a mobile robots.
Medical image segmentation for auxiliary diagnosis. 医学图像分割辅助诊断。
环境可控:如工业检测应用。传感器可控:如自主目标采集,或近红外成像。算法控制。
举栗:车牌分割识别(交通违法)、硬币识别(多少钱)、医学图像
分割算法一般基于强度值的2个基本属性:
1.不连续:根据亮度的剧烈变化(如边缘)对图像进行分割。
2.相似度:根据一组预定义的标准将图像划分为相似的区域。
Detection Of Discontinuities 不连续性检测
有三