andré's profile - activity

Hello,

I'm currently working on a project where I have to compare similar histograms. These histograms are obtained from photos taken under different illumination conditions.

I know that OpenCV offers the compareHist function. However this function returns a metric of similarity and I'm looking for a method that matches corresponding peaks/valleys between similar histograms.

For instance, if we have two photos of the same subject, one underexposed and one with the "ideal" exposure, their histograms of intensity might look like this:

As shown by the arrows, the peaks in one histogram also exist in the other. Anyone has a suggestion on how to match corresponding peaks?

Thank you!

Thanks for the answer @LBerger. I'm trying to avoid downsizing the images as some information is lost in the process, which may be necessary in the folowing phases of the project for the sake of precision. I'll take a look on the phase correlation to see if it useful. Thank you!

Hello,

I'm currently working on a project where I have to correlate several similar images taken from a DSLR camera. Those images may vary on factors such as focal distance, orientation, level of exposure and noise.

My approach consists in using SIFT or SURF for keypoint detection, followed by the FLANN library for keypoint matching. However, the images may have resolutions that go as far as 18 megapixels, which makes the process of keypoint detection too slow. Both SIFT and SURF take more than 4 seconds to detect keypoints in higher resolutions. I've tried to relax the parameters of both algorithms but still the processing time is too high, which may ruin the user experience.

I've read somewhere that a possible approach would be to divide each image into a certain number of sub-images and then try to correlate respective sub-regions between different images. However, as the focal distance and orientation may vary I find this approach ineffective in the context of my project.

Anyone have a suggestion on a possible approach to make the correlation process of high resolution images more efficient?

Hello,

I have a set of similar images, focused on different areas due to depth-of-field variation.

And now I'm developing a workflow that aims to detect which image have a specific object better focused.

I'm thinking about comparing the frequency domain, of the region where the object is, of each image. The one with the highest variations shall be selected. However I'm not very experienced in image processing and I'm new to OpenCV.

So, does anyone know if my idea is possible?

Thank you

I have 8 Gb RAM and the image is 5184x3456. The error happens at the detection step, I believe. Particularly in this line: detector.detect(image, keypoints);

I'm probably running out of memory since the code works fine with smaller images. Thank you for your answer Guanta.

Hello,

I have to detect keypoints on big sized images (about 6mb). I have tried SURF and it works fine and now I'm trying to use SIFT. The code is simple:

cv::Mat image = imread("../images/IMG_3849.jpg", CV_LOAD_IMAGE_GRAYSCALE);

cv::SiftFeatureDetector detector;
std::vector<cv::KeyPoint> keypoints;
detector.detect(image, keypoints);

cv::SiftDescriptorExtractor extractor; 
cv::Mat descriptors_object;
extractor.compute( image, keypoints, descriptors_object );

However when I run this code, I get the error "OpenCV Error: Insufficient memory - Failed to allocate 286654468 bytes".

Anyone knows why this might be happening?

Thank you!

Hello,

I've downloaded OpenCv and I've been trying to run a small example with the VS 2010 Express. I set the environment variables, in the C/C++ I included the Additional Directories and in the Linker I have also included the Additional Library and the Additional Depedencies. But when I run the example I get this error:

"fatal error LNK1112: module machine type 'X86' conflicts with target machine type 'x64'"

I already changed Target Machine to MachineX64 but I still get the same error.

Anyone have any ideia on how to solve this?

Thanks a lot!