硬币检测制作硬币匹配系统 [英] Coin detection to make coin matching system

问题描述

我正在使用opencv在java中开发一个匹配系统，系统接受一个带有一个硬币的对象的图像，以便确定货币的价值。

我做了什么：

1 - 将图像转换为灰度级。

2 - 在灰度图像中使用边缘检测，此步骤的输出用作下一步的输入。

3 - 使用SIFT查找特征描述符。

4 - 通过存储SIFT描述符来预测图像的值来使用SVM。

但是这个算法没有给出好的结果。

1 - 我可以做些什么来增强这个算法。

2-什么是最适合这种情况的SVM参数。

3 - 为此目的适当的边缘检测是什么。



请提出任何建议。

请注意，硬币类型的数量是五个。

I'm developing an matching system in java using opencv the system accept an image with one object which is coin in order to determine the value of the currency.
What I did :
1-Convert image to gray level.
2-Use edge detection in the gray image the output of this step is used as input to the next step.
3-Use SIFT to find the feature descriptors.
4-Use SVM by storing the SIFT descriptors to predict the value of image.
BUT this algorithm does not give good result.
1-what can I do in order to enhance this algorithm.
2- what is the best SVM params that is suitable for this case .
3-what is the appropriate edge detection for this purpose.

Any suggestion please.
Note that in the number of coins types are five.

推荐答案

硬币（或面部）识别算法的图像处理有点困难。我不是这方面的专家，但我可以参考一些有趣的链接，例如：

Dagobert - 一种新的硬币识别和分类系统 [ ^ ] - google在线图书。

设计神经网络以通过遗传识别硬币算法 [ ^ ]

三维人脸识别 [ ^ ]

iris识别如何工作 [ ^ ]

Image processing for coin (or face) recognition algorithm is bit difficult. I'm not a specialist in this matter, but i can refer few interesting links, for example:
Dagobert - a new coin recognition and sorting system[^] - google online book.
Designing a neural network for coin recognition by a genetic algorithm[^]
Three-Dimensional Face Recognition[^]
How iris recognition works[^]

这篇关于硬币检测制作硬币匹配系统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！