图像中的徽标识别 [英] Logo recognition in images

问题描述

有没有人知道最近在图像标识识别方面做过的学术工作？
只有当你熟悉这个特定的主题（我可以搜索Google的标识识别自己，非常感谢），才回答。
任何熟悉计算机视觉并已完成对象识别工作的人都欢迎评论。

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，工作（并已经过测试）真实世界数据，效率考虑）而不是技术方面（使用的编程语言或是否是与OpenCV ...）
工作在图像索引和基于内容的图像检索也可以帮助。

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

它应该工作，因为标志的形状通常是不变的，所以提取的特征应该匹配。

It should work because logo shape is usually constant, so extracted features shall match well.

工作流将是这样：

1. 检测角落（例如Harris角落检测器） - 对于Nike标志，它们是两个尖锐的端点。

1. 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)

在匹配阶段找到训练期间获得的数据库中的每个特征的最近邻居。最后，你有一组匹配（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输出错误的匹配。因此，您将得到描述从理想的徽标图像转换到您找到徽标的矩阵。根据设置，您可以允许不同类型的转换（只是平移;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）关于本地功能。
http://research.microsoft.com/en -us / um / people / szeliski / Book /

Szeliski's book has a chapter (4.1) on local features. http://research.microsoft.com/en-us/um/people/szeliski/Book/

PS

1. 我假设你想在照片中找到标志，例如找到所有的百事可乐广告牌，如果您需要在屏幕上找到电视频道标志（以便不旋转和缩放），您可以更容易（模式匹配或其他）。

1. 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（虽然确切的颜色取决于闪电和相机）。

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.

这篇关于图像中的徽标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！