A novel noise filter based on interesting pattern mining for bag-of-features images

作者：

Highlights：

• We first propose to utilize the cosine interesting pattern to construct the noise filter.

• We then prove that to filter noise only requires to mine the shortest cosine interesting patterns, which dramatically simplifies the mining process.

• We present an in-breadth pruning technique to further speed up the mining process.

摘要

•We first propose to utilize the cosine interesting pattern to construct the noise filter.•We then prove that to filter noise only requires to mine the shortest cosine interesting patterns, which dramatically simplifies the mining process.•We present an in-breadth pruning technique to further speed up the mining process.

论文关键词：Image data,Bag-of-Features,Noise filtering,Interesting pattern mining,Shortest cosine interesting pattern

论文评审过程：Available online 26 July 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.07.058