清华大学郭振华副研究员访问AIPL并作报告

2016年7月30号下午,清华大学深圳研究生院郭振华副研究员访问情感信息处理实验室,并作报告。

报告题目:Robust Texture Image Representation by Scale Selective Local Binary Patterns

报告摘要:Local Binary Pattern (LBP) has been successfully used in computer vision and pattern recognition applications such as texture recognition. It could effectively address gray-scale and rotation variation. However, it failed to get desirable performance for texture classification with scale transformation. In this paper, a new method based on dominant LBP in scale space is proposed to address scale variation for texture classification. First, a scale space of a texture image is derived by a Gaussian filter. Then, a histogram of pre-learned dominant LBPs is built for each image in the scale space. Finally, for each pattern, the maximal frequency among different scales is considered as scale invariant feature. Extensive experiments on four public texture databases(UIUC, CUReT, KTH-TIPS, UMD) validate the efficiency of the proposed feature extraction scheme. Coupled with the nearest subspace classifier (NSC), the proposed method could yield competitive results, which are 99.36%, 99.51%, 99.39%, 99.46% for UIUC, CUReT, KTH-TIPS and UMD respectively. Meanwhile, the proposed method inherits simple and efficient merits of LBP, for example, it could extract scale-robust feature for a 200*200 image with 0.24 seconds, which is applicable for many real time applications.

报告人简介:郭振华,清华大学深圳研究生院,副研究员,博士生导师。近年来一直从事模式识别、计算机视觉等方面的科研工作,尤其侧重于生物特征识别、纹理识别、视频监控等领域的研究工作。主持和参与国家自然科学基金、863、粤港合作等科研项目。发表论文70余篇,其中SCI收录24篇。授权专利5项,其中2项美国专利。获得教育部自然科学奖(2015)、深圳市青年科技奖(2014)、爱思唯尔中国高被引学者榜单(2014、2015)、日内瓦国际发明展金奖(2011)、深圳市海外高层次人才(B类)等奖励。

 

近期更新