文章摘要
李莉,冯林,吴俊,刘胜蓝.基于半圆形局部二值模式结构相关性描述子的图像检索[J].,2016,56(5):532-538
基于半圆形局部二值模式结构相关性描述子的图像检索
Image retrieval based on semicircle local binary patterns structure correlation descriptor
  
DOI:10.7511/dllgxb201605014
中文关键词: 局部二值模式  基元频率特征  颜色差分特征  图像检索
英文关键词: local binary patterns  texton frequency feature  color difference feature  image retrieval
基金项目:国家自然科学基金资助项目(61173163,61370200).
作者单位
李莉,冯林,吴俊,刘胜蓝  
摘要点击次数: 1461
全文下载次数: 845
中文摘要:
      针对传统的结构基元方法缺少对不同量化颜色层中的中心像素点与其潜在邻居的相似性信息描述问题,提出了一种半圆形局部二值模式结构相关性描述子,并将其应用在图像检索中.首先,定义了一种新的半圆形局部二值模式结构基元;其次,检测不同量化颜色层中的结构基元;最后,提取新结构基元的空间分布和对比度特征.相比传统的结构基元方法,提出的描述子检测的结构基元更加丰富,包含更多可能的结构区分性.在不同图像库上的实验结果表明了所提方法的有效性.
英文摘要:
      To solve the problem that conventional texton methods do not describe the similarity information among the surrounding neighbors for a given center pixel in different color quantization levels, a feature descriptor, called semicircle local binary patterns structure correlation descriptor (SLBPSCD) is proposed, which is applied for image retrieval. Firstly, a novel semicircle local binary patterns structure texton is defined. Secondly, the structure textons are detected in different color quantization levels. Finally, the spatial distribution and contrast features of new structure texton are extracted. The proposed descriptor gets much more discriminative structure than conventional texton-based methods by taking more structure texton into consideration. Experimental results for different image databases verify the effectiveness of the proposed method.
查看全文   查看/发表评论  下载PDF阅读器
关闭