学术论文

      基于SLIC超像素的全局对比度显著性区域检测

      Salient Region Detection Based on Global Contrast with SLIC Superpixel

      摘要:
      提出了一种基于SLIC超像素的全局对比度的显著性区域检测算法.首先在图像的预处理阶段,为了降低计算的复杂度,采用SLIC超像素分割算法来提取给定图像的超像素.然后在CIELAB颜色空间上,同时考虑图像的全局对比度特征和LBP纹理特征,并利用MKB方法将这两个特征结合起来计算得到显著图.最后,通过滤波器进一步提高检测效果以便于优化最终的显著性图.在MSRA10 K基准数据库上与常用的几种方法进行定性和定量比较.实验结果表明,文中所提算法的性能均高于其他方法.
      Abstract:
      A salient region detection algorithm based on global contrast with SLIC superpixel is proposed .Firstly,in order to reduce the computation complexity ,the SLIC algorithm was used to extract the superpixels of a given image in the image prepro-cessing stage.Then, the characteristics of the image global contrast and LBP texture feature were taken into account in the CIELAB color space ,and the saliency map was acquired by combining the two features with the MKB algorithm .Finally,the final saliency map was optimized by a guided filter in order to further improve the detection results .A series of qualitative and quantita-tive experiments were done on a MSRA 10K dataset with ground truths ,and simulation results show that the performance of the proposed saliency algorithm is better than the prevailing current methods .
      作者: 高美凤 冯海永
      Author: GAO Mei-feng FENG Hai-yong
      作者单位: 江南大学,轻工过程先进控制教育部重点实验室,江苏无锡 214122
      刊 名: 仪表技术与传感器 ISTICPKU
      年,卷(期): 2017, (1)
      分类号: TH89
      在线出版日期: 2017年3月31日
      基金项目: 国家自然科学基金项目