HEp-2 cell classification using rotation invariant co-occurrence among local binary patterns
作者：
Highlights：
• We propose an efficient method for HEp-2 cell classification using RIC-LBP.
• RIC-LBP can provide a high descriptive ability and robustness to local rotation.
• For global rotation, the classifier is trained with many synthesized training images.
• Experiments were performed on the MIVIA HEp-2 images dataset.
• The effectiveness was demonstrated compared with typical state-of-the-art methods.
摘要
Highlights•We propose an efficient method for HEp-2 cell classification using RIC-LBP.•RIC-LBP can provide a high descriptive ability and robustness to local rotation.•For global rotation, the classifier is trained with many synthesized training images.•Experiments were performed on the MIVIA HEp-2 images dataset.•The effectiveness was demonstrated compared with typical state-of-the-art methods.
论文关键词：Indirect immunofluorescence,HEp-2 cell classification,Local binary pattern,Rotation invariant co-occurrence
论文评审过程：Available online 1 October 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.09.018
