在 OpenCV 中训练 SIFT 特征 [英] training SIFT features in OpenCV

问题描述

我创建了一个小型 SIFT 应用程序，它可以抓取关键点并将其保存到文本文件中.我正在使用它从徽标(例如 AT&T)中获取信息，并使用它与具有该徽标的其他图像进行比较.问题是我的许多图像都有不同的徽标，由于缩放、旋转或照明，它无法识别它.我想知道是否有可能获得一组图像，抓住它的关键点，然后通过某种训练算法运行它以增强检测.

I have created a small SIFT application that grabs the keypoints and saves it out to a text file. I am using this to grab information from a logo (say AT&T) and use that to compare against other images with that logo. The problem is many of my images have variations of the logo that, due to the scaling, rotation, or lighting it does not pick it up. I was wondering if it was possible to get a set of images, grab it's keypoints, and run it through some sort of training algorithm to enhance the detection.

我在网上搜索了训练 SIFT 关键点的方法，但它们都在某种 phd 论文中，涉及所有这些数学算法，老实说，因为我没有学过任何数学，所以这让我很反感上课了.

I've searched online for ways of training the SIFT keypoints, but they are all in some sort of phd paper that goes into all this mathematical algorithms which, to be honest, throws me off as I haven't taken any math class for awhile.

如果有人有任何建议或链接可以了解培训的工作原理或实施培训需要做什么，请告诉我.或者，如果有人在没有 SIFT 的情况下有更简单的方法，那么我将非常感谢其他形式的检测.以下是我尝试过的列表:

If anyone has any advice or links to be able to understand how training works or what needs to be done to implement one please let me know. Or if anyone has a simpler means of doing this without SIFT then I would greatly appreciate other forms of detection. Below is a list of what I've tried:

• 冲浪
  • 由于返回无效结果而失败
  • 我在 2011 年 7 月 11 日开始训练 100 个正模型和 100 个负图像时失败了，它在 2011 年 7 月 19 日仍在运行
  • 失败了，因为我必须根据无法在图片中检测到任何内容的次数来以指数方式创建徽标

  提前致谢

  推荐答案

  一个简单的起点是收集几个 AT&T 标志的 SIFT/SURF 描述符，并使用 FLANN 在他们身上.然后，拍摄一张测试图像，计算描述符并进行范围搜索并确定最近邻距离等，并尝试找出接近度"的度量.

  A simple starting point would be to collect SIFT/SURF descriptors of several AT&T logos, and use FLANN on them. Then, take a test image, compute the descriptors and do a range search and determine the nearest-neighbor distance, etc. and try to figure out a metric of "closeness".

  这篇关于在 OpenCV 中训练 SIFT 特征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！