Christopher's profile - activity

I expect this would not be an issue, as the OCR would need to be trained to the particular font and would under no circumstances pick up common handwriting.

To answer your questions:

Matching one to one worked just fine. In fact, I tested that with find_obj.py!

But then I came upon something else. http://stackoverflow.com/questions/25781782/making-flann-matcher-editable-and-savable-to-disk ...which passed descriptors inside a list to add().

So I made a switch that no longer causes the segfault:

This:<br> flann.add([des2]) <br> instead of: <Br> flann.add(des2) <br>

It seems it needed a list of ndarrays, rather than an ndarray. Of course. The perils of using undocumented things, I guess.

Dear Internet,

I'm trying to add a number of images to a FLANN index (thousands in reality, once I have this working) and then find the closest match in the index to a query image. But it segfaults. :(

Bare essentials code:

import numpy as np
import cv2
import sys


FLANN_INDEX_LSH = 6


img1 = cv2.imread(sys.argv[1],0)


brisk = cv2.BRISK()


kp1, des1 = brisk.detectAndCompute(img1,None)


index_params= dict(algorithm = FLANN_INDEX_LSH,
                   table_number = 6, # 12
                   key_size = 12,     # 20
                   multi_probe_level = 1) #2
search_params = dict(checks=50)   # or pass empty dictionary

flann = cv2.FlannBasedMatcher(index_params,search_params)

for filename in sys.argv[2:]:
    img2 = cv2.imread(filename, 0)
    print "Detecting and computing {0}".format(filename)
    kp2, des2 = brisk.detectAndCompute(img2,None)
    print "Adding..."
    flann.add(des2)


print len(flann.getTrainDescriptors()) #verify that it actually took the descriptors in

print "Training..."
flann.train()                    

print "Matching..."
matches = flann.knnMatch(des1,k=2)

(I've tried this both with 2.4.9 and a pull of 3.0 alpha as from the day I'm posting this, both had same result.)

Problem: Here's the output where it fails:

Training...

Segmentation fault (core dumped)

So it dies at training, or at match() if I skip training.

What has me stuck:

1. I can't find this functionality in the docs as regards Python. Am I in the wrong places?
   http://docs.opencv.org/trunk/modules/flann/doc/flann_fast_approximate_nearest_neighbor_search.html
   http://docs.opencv.org/trunk/modules/features2d/doc/common_interfaces_of_descriptor_matchers.html
   

2. For lack of docs, I'm trying to emulate in Python what I see in matching_to_many_images.cpp from the samples since that's the closest thing to what I'm trying to do. I think. So that's where I'm getting what I have so far.

Now what? Kind of lost. Sorry if this is actually clearly documented and I just couldn't find it.

Thanks!

CUDA may well be it. I've become aware of that since reading more... unfortunately it is not available in the Python wrapper. :(

I'll be trying the C++ samples and what kind of times I get.

I'm getting these results with 2.4.8, 2.4.9, and 3.0.

I'm looking to find which object from a large database of images (I'll precompute and store the feature descriptions) in a video feed in realtime. I see people pulling this off in C++, like the following video I found: https://www.youtube.com/watch?v=kbYDjBa3Lyk

But my speeds in Python are way too high. I'm seeing 300-1k ms depending on the detection method with FLANN for __ONE__ object, trying all of the feature matching sample code that came with the OpenCV source. Is this just the way of things? Might I have done something wrong when compiling OpenCV?

Basically, are the speeds like in the video attainable in Python or do I need to go learn C++ to actually make my project work? Would love any ideas what I might be doing wrong if I am the problem. :)