Efficient logo recognition by local feature groups

被引：3

作者：

Liu, Yujie ^{[1
]}

Wang, Jun ^{[1
]}

Li, Zongmin ^{[1
]}

Li, Hua ^{[2
]}

机构：

[1] Coll Comp & Commun Engn, Qingdao 266580, Shandong, Peoples R China

[2] Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China

来源：

MULTIMEDIA SYSTEMS | 2017年 / 23卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Logo recognition; Grouping features; Spatial information; Hough transform; SCALE;

D O I：

10.1007/s00530-016-0508-7

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a method for efficient and scalable logo recognition. Using generalized Hough transform to identify local features that are invariant across images, we can efficiently add spatial information into groups of local features and enhance the discriminative power of local feature. Our method is more flexible and efficient compared with state-of-the-art methods that merge features into groups. To fully exploit the information that different logo images provide, we employ a reference-based image representation scheme to represent training and testing images. Experiments on challenging datasets show that our method is efficient and scalable and achieves state-of-the-art performance.

引用

页码：395 / 403

页数：9