17 March 2017 Abnormal cervical cell detection based on an adaptive margin-based feature selection method
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103411Y (2017) https://doi.org/10.1117/12.2268406
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Abstract
In an abnormal cervical cell detection system the discriminated abilities of different features are not same so the optimized combination method of all features is an essential component to this system. Feature selection can improve each feature utilization ratio and the performance of the classification problem. The previous efforts of cervical abnormal cell detection are mainly focused on changing feature space into a new one by using a binary weight vector. In this work, the binary weight values are extended to the multiple weight values. According to the statistical distribution situation of the data, an adaptive margin-based weighted feature selection method is proposed in this paper. This method performs best compared with the other 3 methods. The experimental result achieves 96% accuracy in a real-world cervical smear image dataset.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lili Zhao, Lili Zhao, Kuan Li, Kuan Li, Hongyun Yang, Hongyun Yang, Jianping Yin, Jianping Yin, } "Abnormal cervical cell detection based on an adaptive margin-based feature selection method", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103411Y (17 March 2017); doi: 10.1117/12.2268406; https://doi.org/10.1117/12.2268406
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

Image segmentation based on kernel PCA and shape prior
Proceedings of SPIE (July 08 2011)
Morphological theory in image feature extraction
Proceedings of SPIE (June 10 2003)
3D object parts inference from range image data
Proceedings of SPIE (January 08 1997)
Recognizing characters of ancient manuscripts
Proceedings of SPIE (February 16 2010)

Back to Top