烟草异物剔除系统中实时低照度图像增强算法-烟草科技.PDFVIP

2015 年 1 月 烟草科技 Jan. 2015 第48 卷第 1 期 Tobacco Science Technology Vol. 48 No. 1 烟草异物剔除系统中实时低照度图像增强算法 张绍堂 ，宁德琼 ，王 磊1 1 2 1. 曲靖师范学院计算机科学与工程学院，云南省曲靖市麒麟区三江大道 655011 2. 红云红河（烟草）集团曲靖卷烟厂，云南省曲靖市大坡寺 655000 摘要：为解决烟草异物剔除系统随照度衰减后系统剔除性能下降问题，采用优化的高斯同态滤 波算法在系统中增设了图像增强功能。先将低照度烟叶图像从RGB （Red-Green-Blue ）空间快 速转换到HSV （Hue-Saturation-Value ）空间，实现色彩与亮度的分离，采用实时性较高的空域 同态滤波方法对亮度分量V进行增强，引入自适应系数对亮度进行拉伸，最后将HSV 转换到 RGB 模式。结果表明，该方法能有效校正低照度图像的颜色、对比度和亮度，对光照不均有很 好的均衡作用，具有较好的自适应性；能够较好地保持系统剔除性能，增强系统的可维护性、易 操作性；与其他图像增强算法相比，本方法运算速度更快，能较好地满足实时增强彩色图像的 需求。 关键词：烟草；异物剔除；低照度；图像增强；同态滤波；实时性 中图分类号：TS431 文献标志码：A 文章编号：1002-0861（2015 ）01-0096-05 DOI: 10.16135/j.issn 1002-0861 Real-time Image Intensification in Tobacco Sorting System Under Low Illumination 1 1 2 ZHANG Shaotang , NING Deqiong , and WANG Lei 1. School of Computer Science and Engineering, Qujing Normal University, Qujing 655011, Yunnan, China 2. Qujing Cigarette Factory, HongyunHonghe Tobacco (Group) Co., Ltd., Qujing 655000, Yunnan, China Abstract: The foreign matter rejecting performance of a tobacco sorting system decreases with the attenuation of illumination, therefore the function of image intensification was incorporated on the basis of optimized Gauss homomorphic filtering algorithm. The image of tobacco leaf under low illumination was converted swiftly from its RGB (Red-Green-Blue) space into an HSV (Hue-Saturation-Value) space in order to separate color from luminance, and the luminance component V was intensified by a real-time spatial homomorphic filter, then stretched by an introduced adaptive coefficient, finally HSV was converted into RGB. The results showed that this method could effective