报告题目：Hierarchical Feature Extraction with Local Neural Response for Image Recognition
报告人：李红教授
报告时间：10月12日（星期五）下午3:00
报告地点：尚贤楼8楼报告厅
报告主持人：杨建伟教授
欢迎广大师生踊跃参加。
摘要：A hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, carried out on the locally linear manifold, can extract the salient feature of image patches and lead to a sparse measure matrix on which the maximum pooling is carried out. And the maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce the computational complexity and improve the discrimination ability of LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.
报告人简介：
李红,博士，华中科技大学数学与统计学院教授、博士生导师。曾于1992年和1997年作为访问学者在厦门大学、中国科学院数学研究所从事数值逼近与小波理论及其应用的合作研究。近年来多次应邀访问香港浸会大学和澳门大学进行合作研究。先后主持完成国家自然科学基金、国防预研基金等课题十余项，先后参加完成国家自然科学基金、国家863项目等十余项。目前主要研究方向为逼近与计算、机器学习与模式识别、小波分析与图像处理。
2012-10-11
报告人：李红教授
报告时间：10月12日（星期五）下午3:00
报告地点：尚贤楼8楼报告厅
报告主持人：杨建伟教授
欢迎广大师生踊跃参加。
摘要：A hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, carried out on the locally linear manifold, can extract the salient feature of image patches and lead to a sparse measure matrix on which the maximum pooling is carried out. And the maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce the computational complexity and improve the discrimination ability of LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.
报告人简介：
李红,博士，华中科技大学数学与统计学院教授、博士生导师。曾于1992年和1997年作为访问学者在厦门大学、中国科学院数学研究所从事数值逼近与小波理论及其应用的合作研究。近年来多次应邀访问香港浸会大学和澳门大学进行合作研究。先后主持完成国家自然科学基金、国防预研基金等课题十余项，先后参加完成国家自然科学基金、国家863项目等十余项。目前主要研究方向为逼近与计算、机器学习与模式识别、小波分析与图像处理。
2012-10-11
