A robust classifier combined with an auto-associative network for completing partly occluded images

Takashi Takahashi, Takio Kurita
2005 Neural Networks  
This paper describes an approach for constructing a classifier which is unaffected by occlusions in images. We propose a method for integrating an auto-associative network into a simple classifier. As the auto-associative network can recall the original image from a partly occluded input image, we can employ it to detect occluded regions and complete the input image by replacing those regions with recalled pixels. By iterating this reconstruction process, the integrated network is able to
more » ... fy target objects with occlusions robustly. To confirm the effectiveness of this method, we performed experiments involving face image classification. It is shown that the classification performance is not decreased, even if about 30% of the face image is occluded. q Neural Networks 18 (2005) 958-966 www.elsevier.com/locate/neunet 0893-6080/$ -see front matter q
doi:10.1016/j.neunet.2005.03.011 pmid:15936926 fatcat:jebyvkxm4vhs5lon66vzfy2tse