问题描述
我可以输入通过MATLAB命令获得的SURF特征(detectSURFFeature)作为神经网络的输入以训练网络以对图像中的对象进行分类/检测吗?如果是的话，我该如何处理获得的多维数据通过描述符?我正在使用相同分辨率和几乎相似方向的图像集.我只使用MATLAB.
Can I input the SURF feature obtained by the MATLAB command (detectSURFFeature) as input to the neural network to train network in order to classify/detect the object in the image?.if yes how can I cop with the multidimensional data obtained by the descriptor? I am using image set of same resolution and almost similar orientation. I am using only MATLAB.
推荐答案
一种方法是使用功能包方法.离散化SURF描述符的空间，然后计算图像中描述符的直方图.这为您提供了一个向量，您可以在输入到神经网络或您选择的任何其他分类器时使用它.
One way to do this is to use the bag of features approach. You discretize the space of the SURF descriptors, and then you compute a histogram of the descriptors in your image. This gives you a single vector that you can use at input to a neural network or any other classifier of your choice.
这篇关于在MATLAB中将SURF特征输入到神经网络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！