A simple method for improving local binary patterns by considering non-uniform patterns

详细信息	查看全文 | 推荐本文 |

• 作者：Loris Nanni^a ; ^{loris.nanni@unipd.it}  ; [Author Vitae] ; Sheryl Brahnam^b ; ^{sbrahnam@missouristate.edu}  ; [Author Vitae] ; Alessandra Lumini^c ; ^{alessandra.lumini@unibo.it}  ; [Author Vitae]
• 关键词：Texture descriptors ; Local binary patterns ; Local ternary patterns ; Non-uniform patterns ; Support vector machines
• 刊名：Pattern Recognition
• 出版年：2012
• 期刊代码：100_00313203
• 类别：cp
• 出版时间：October, 2012
• 卷：45
• 期：10
• 页码：3844-3852
• 文件大小：582 K

摘要

The basic idea behind LBP is that an image is composed of micropatterns. A histogram of these micropatterns contains information about the local features in an image. These micropatterns can be divided into two types: uniform and non-uniform. In standard applications using LBP, only the uniform patterns are used. The non-uniform patterns are considered in only a single bin of the histogram that is used to extract features in the classification stage. Non-uniform patterns have undesirable characteristics: they are of a high dimension, partially correlated, and introduce unwanted noise. To offset these disadvantages, we explore using random subspace, well-known to work well with noise and correlated features, to train features based also on non-uniform patterns. We find that a stand-alone support vector machine performs best with the uniform patterns and random subspace with histograms of 50 bins performs best with the non-uniform patterns. Superior results are obtained when the two are combined. Based on extensive experiments conducted in several domains using several benchmark databases, it is our conclusion that non-uniform patterns improve classifier performance.