计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (11): 190-193.

• 图形、图像、模式识别 • 上一篇    下一篇

基于HSI颜色空间的蔗糖结晶图像分割方法

张振升,朱名日   

  1. 桂林电子科技大学 计算机与控制学院,广西 桂林 541004
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-04-11 发布日期:2011-04-11

Image segmentation method for sucrose-crystallizing based on HSI color space

ZHANG Zhensheng,ZHU Mingri   

  1. College of Computer and Control,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-11 Published:2011-04-11

摘要: 针对煮糖过程蔗糖结晶图像的特点,采用颜色空间转换的方法,将图像从RGB颜色空间转换到HSI颜色空间,利用HSI颜色空间各分量相对独立性以及结晶颗粒和糖浆溶液的色调差异通过改进的大津法对H分量进行阈值分割,再通过数学形态学,中值滤波,孔洞填充,去除噪声颗粒,去除图像边界的非完整颗粒等方法进行后续处理,最终将结晶颗粒从复杂的图像信息中分割出来。实验证明该方法分割效果好,切实可行。

关键词: 蔗糖结晶, HSI颜色空间, 改进的大津法, 数学形态学, 孔洞填充, 噪声颗粒, 图像分割, ,

Abstract: Based on the characteristics of sucrose-crystallizing images in the sugar-boiling process,this article uses a method called color space conversion,which changes the images from RGB color space into HSI color space,and makes use of the relative independence of every components in the HSI color space and the color difference between crystal particles and syrup solution to segment the H component by the improved Otsu’s thresholding method,then many methods are used in the subsequent processing such as mathematical morphology opening operation,median filter,holes filled,noise removing process of particles,it removes non-holonomic particles which are close to the image border in the subsequent processing,eventually crystalline particles are segmented from the complexity of the image information.Experiments show that this method is effective and practical.

Key words: sucrose crystallization, HSI color space, improved Otsu method, mathematical morphology, holes filled, noise particles, image segmentation