cflavs's profile - activity

I'm trying to implement an object detection module which contains the following steps:

1) extract image descriptors with SURF, creating a matrix of size [x, 64], where x depends of the number of keypoints found in the image;

2) fix the descriptor size to a [k,64] format using bag of features/words approach. Where k is the number of clusters created using k-means.

3) feed a neural network using the resulting bag of words matrix as trainingSamples.

So far I've implemented steps 1 and 2 but I'm not quite sure how to format the output vector of the NN. On OpenCV CvANN_MLP, the number of rows in the output vector should have the same number of the input rows (otherwise returns an what() exception), but the number of input rows are the number of the k clusters on step 2, so I'm not understanding how to write the output matrix based on that.

I know the output matrix should have n columns corresponding to the number of classes in the output that I want (e.g. 3 classes: cat, dog and bird will result on a matrix with 3 columns), but how do I organize the rows of this matrix based on the input rows? I thought the rows were equal to the number of columns so the output would have for instance the following matrix output for cat, dog and bird:

001

010

100

But that doesn't match with the clusters so I don't know for sure how to proceed.

I'm using SURF to extract keypoints and descriptors, but I don't know which machine learning method is the best one to match the descriptors. I've followed OpenCV tutorial with FLANN and KNN approaches, but I don't know if they're the best ones, on the beggining I thought on using neural networks but then I realized the NN will need 68/128 entries so maybe isn't the best choice to follow.