图像中的标志识别 [英] Logo recognition in images
问题描述
有谁知道最近在图像标识识别方面所做的学术工作?请仅在您熟悉此特定主题的情况下回答(我自己可以在Google上搜索标识识别"，非常感谢).任何熟悉计算机视觉并在对象识别方面做过工作的人也欢迎发表评论.
Does anyone know of recent academic work which has been done on logo recognition in images? Please answer only if you are familiar with this specific subject (I can search Google for "logo recognition" myself, thank you very much). Anyone who is knowledgeable in computer vision and has done work on object recognition is welcome to comment as well.
更新:请参考算法方面(您认为合适的方法、该领域的论文、它是否应该适用(并已被测试)用于现实世界数据、效率考虑)而不是技术方面(使用的编程语言或它是否适用)是用 OpenCV ...)在图像索引和基于内容的图像检索方面的工作也会有所帮助.
Update: Please refer to the algorithmic aspects (what approach you think is appropriate, papers in the field, whether it should work(and has been tested) for real world data, efficiency considerations) and not the technical sides (the programming language used or whether it was with OpenCV...) Work on image indexing and content based image retrieval can also help.
推荐答案
您可以尝试在此处使用 SIFT 等本地功能:http://en.wikipedia.org/wiki/Scale-invariant_feature_transform
You could try to use local features like SIFT here: http://en.wikipedia.org/wiki/Scale-invariant_feature_transform
它应该可以工作，因为标志形状通常是恒定的，所以提取的特征应该匹配得很好.
It should work because logo shape is usually constant, so extracted features shall match well.
工作流程如下:
检测角点(例如 Harris 角点检测器)- 对于耐克标志，它们是两个尖头.
Detect corners (e.g. Harris corner detector) - for Nike logo they are two sharp ends.
计算描述符(如 SIFT - 128D 整数向量)
Compute descriptors (like SIFT - 128D integer vector)
在训练阶段记住他们；在匹配阶段为训练期间获得的数据库中的每个特征找到最近的邻居.最后，您有一组匹配项(其中一些可能是错误的).
On training stage remember them; on matching stage find nearest neighbours for every feature in the database obtained during training. Finally, you have a set of matches (some of them are probably wrong).
使用 RANSAC 剔除错误的匹配项.因此，您将获得描述从理想徽标图像到您找到徽标的位置的变换的矩阵.根据设置，您可以允许不同类型的变换(仅平移；平移和旋转；仿射变换).
Seed out wrong matches using RANSAC. Thus you'll get the matrix that describes transform from ideal logo image to one where you find the logo. Depending on the settings, you could allow different kinds of transforms (just translation; translation and rotation; affine transform).
Szeliski 的书有一章 (4.1) 是关于局部特征的.http://research.microsoft.com/en-us/um/人/szeliski/书/
Szeliski's book has a chapter (4.1) on local features. http://research.microsoft.com/en-us/um/people/szeliski/Book/
附言
我假设您想在照片中找到徽标，例如找到所有百事可乐广告牌，这样它们可能会被扭曲.如果您需要在屏幕上找到电视频道徽标(以免旋转和缩放)，您可以更轻松地完成(模式匹配或其他操作).
I assumed you wanna find logos in photos, for example find all Pepsi billboards, so they could be distorted. If you need to find a TV channel logo on the screen (so that it is not rotated and scaled), you could do it easier (pattern matching or something).
传统的 SIFT 不考虑颜色信息.由于徽标通常具有恒定的颜色(尽管确切的颜色取决于闪电和相机)，因此您可能需要以某种方式考虑颜色信息.
Conventional SIFT does not consider color information. Since logos usually have constant colors (though the exact color depends on lightning and camera) you might want to consider color information somehow.
这篇关于图像中的标志识别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
