Ask Your Question

kbarni's profile - activity

2019-07-23 10:25:58 -0500 commented answer Generalizing the size for Detecting Horizontal and Vertical Lines

...and did you try so solve it? Or you are just waiting for us to give you the solution? (it won't happen)

2019-07-22 08:51:58 -0500 commented answer Generalizing the size for Detecting Horizontal and Vertical Lines

@Dronzer You need to detect the local maxima in the image, to eliminate multiple detections. There are several ways to

2019-07-19 06:54:28 -0500 commented answer Generalizing the size for Detecting Horizontal and Vertical Lines

I have to name each corner as a coordinate... Just detect the maxima of the image given by the Harris corner detect

2019-07-19 05:32:15 -0500 answered a question Generalizing the size for Detecting Horizontal and Vertical Lines

To get only the intersections, just use the Harris corner detector. It will have maximum values in the middle, no matter

2019-07-17 10:55:44 -0500 answered a question selectROI does not close the window after 'enter' pressed?

Because it's not supposed to. According to the documentation: SelectROI() Selects ROI on the given image. Func

2019-07-16 10:31:11 -0500 commented question information extraction from drug packaging

Even if you manage to recognize the text, it's quite difficult to "understand" its meaning - especially as it's far from

2019-07-02 18:43:47 -0500 received badge  Nice Answer (source)
2019-07-02 07:56:58 -0500 answered a question Does OpenCV-OpenVINO version supports Yolo v3 network?

OpenCV is a generic image processing library (with DNN support), OpenVINO is a kind of DNN compiler for Intel VPUs. "Op

2019-07-02 05:27:24 -0500 answered a question GTK or QT when build OpenCV

I recommend to use the QT library which is much more efficient. The GTK window is very basic, it displays only a windo

2019-06-27 16:40:46 -0500 answered a question How to classify jersey color in a basketball game using opencv c++

Ok, here's an idea. Work in the HSV or Lab color space to reduce the dependency on the luminosity. 1 Automatic unsuperv

2019-06-26 16:02:57 -0500 commented answer How can I effectively remove the scratch from the image?

That's described in my answer.

2019-06-24 04:18:35 -0500 answered a question How can correct a problem color

Having a real image could help to give a good answer. Here are some ideas: If you worry about the luminosity, use a lu

2019-06-24 03:07:42 -0500 answered a question How can I effectively remove the scratch from the image?

First you need to identify the scratches. There are several methods to do this, maybe the simples is to check the anisot

2019-06-21 05:35:14 -0500 commented question HikVision Machine Vision Camera with OpenCV

Although it's possible to capture images from industrial cameras using OpenCV, I strongly recommend using the SDK provid

2019-06-21 05:26:55 -0500 commented question How to classify jersey color in a basketball game using opencv c++

You can try a histogram analysis in the ROI, checking values around the expected jersey colors.

2019-06-20 04:26:27 -0500 commented question Cross compile opencv build fails for aarch64 targets

Cross compiling can be annoying. I prefer to compile OpenCV on the platform I'll use it. It's quite fast on ARM processo

2019-06-20 03:20:58 -0500 commented question Tennis ball's within radius of a circle?

Note through that a tennis ball travels easily at 30-40m/s. At 5m distance with 25-30fps acquisition rate you will have

2019-06-19 04:16:20 -0500 received badge  Popular Question (source)
2019-06-17 07:19:12 -0500 commented question how to detect waterdroplet in given images

Use an accumulator image. Get the gradients (gx,gy), calculate its magnitude and directions (cartToPolar), then for eac

2019-06-17 03:04:39 -0500 commented answer changing the fps of a video?

As the name says, CAP_PROP_FPS sets the frame rate of CAPturing. This is in fact a parameter of the camera. Resolution,

2019-06-17 03:01:07 -0500 commented answer changing the fps of a video?

As the name says, CAP_PROP_FPS sets the frame rate of capturing (this is in fact a parameter of the camera). For readi

2019-06-17 02:56:35 -0500 commented question how to detect receipt rectange shape in android

The algorithm is the same in C++ and Java. As for the code, we won't do it for you.

2019-06-14 05:42:59 -0500 commented question Convert yaw, pitch and roll values to rVec for projectPoints.

I suggest to do this thing manually using raycasting. Compute the Lat/Lon of the 4 corners of the image using Y/P/R and

2019-06-14 05:26:50 -0500 commented question how to detect waterdroplet in given images

I think the fast radial symmetry transform (Roy&Zelinsky 2003) is worth trying: article

2019-06-13 04:23:30 -0500 commented question editing mat is so slow

First, don't use clock_t. It measures the CPU ticks (operations), which is not the same than the elapsed time (as modern

2019-06-13 04:15:59 -0500 commented question Live video object detection

Can you post an example image comparing the ffmpeg-recorded video frame vs. a frame acquired directly from the webcam?

2019-06-12 10:06:20 -0500 commented question Is it possible to record in 4 bit greyscale with recording in color then converting to 4 bit greyscale?

The answer is two lines above. Just tell me if you need explanation about the meaning of "NO".

2019-06-05 08:45:43 -0500 commented answer How to calculate scale factor between two images (by SIFT matching)

The homography estimation will try to get the best pair of SIFT points to match the images. If it doesn't work, you have

2019-06-04 08:52:08 -0500 commented question Facenet with OpenCV and Neural compute stick 2

...and how is this related to OpenCV? Just follow the OpenVINO samples and documentation

2019-06-04 08:47:51 -0500 edited answer How to calculate scale factor between two images (by SIFT matching)

After matching the keypoints calculate the homography matrix. There are lots of tutorials on feature matching and homogr

2019-06-04 08:47:07 -0500 answered a question How to calculate scale factor between two images (by SIFT matching)

After matching the keypoints calculate the homography matrix. There are lots of tutorials on feature matching and homogr

2019-06-03 10:41:38 -0500 commented question Camera for Gear Inspection

There is always a difference between theory and practice. So while in theory your resolution is at 15um, I'm not sure th

2019-06-03 07:37:34 -0500 commented question Camera for Gear Inspection

I think you mistake the sensor pixel size (i.e. the surface of a phototransistor) with the optical resolution of the cam

2019-06-03 03:40:34 -0500 commented question Camera for Gear Inspection

Well, this is not an easy task. You need an accuracy of ~1/2000, so a high resolution.On global shutter cameras you are

2019-05-27 04:52:45 -0500 commented question paper edge detection and perspective transform

For this problem I would use a Hough line detector. Knowing that the paper is rectangular and the edges are mostly paral

2019-05-09 05:07:18 -0500 commented question Analog clock read

Ok, then here's the algorithm: https://github.com/basselhossam/clockreader#algorithm Good news: you have everything you

2019-05-08 07:08:29 -0500 commented question Analog clock read

what did you try? this is a forum for helping with your opencv related problems, not to solve your projects. see faq

2019-04-30 02:04:18 -0500 commented answer Fit ellipse with most points on contour (instead of least squares)

Well, 2% difference isn't that much, it might be difficult to detect (1 pixel on a 50 pixel radius circle) essentially i

2019-04-29 14:56:46 -0500 answered a question Fit ellipse with most points on contour (instead of least squares)

If the object is a circle (not ellipse), try the circular Hough transform on the contours of the object. Otherwise you

2019-04-28 05:40:51 -0500 commented question How to detect blue color in blue background like sea

In a case when you can't use color detection, the next step is to try texture segmentation (Haralick, Gabor filters, wav

2019-04-26 08:29:46 -0500 commented question Mask a room using OpenCV

or grabcut

2019-04-26 05:04:13 -0500 answered a question Display the bottom image of the line and cut the upper image using Opencv

You need the fillConvexPoly function with the following points: (0,0), (frame.shape(1),0), (0,frame.shape(0)), (0,0) and

2019-04-15 07:41:26 -0500 edited answer Enhancing low-contrast detail

The Perona-Malik anisothropic diffusion (from the OpenCV extended image processing module) is used a lot for photo denoi

2019-04-15 07:28:39 -0500 answered a question Enhancing low-contrast detail

The Perona-Malik anisothropic diffusion (from the OpenCV extended image processing module) is used a lot for photo denoi

2019-04-11 08:39:26 -0500 commented question How to detect unclosed hexagon?

I don't really understand what do you mean by "unclosed hexagon" Maybe some simpler methods (like connected component a

2019-04-11 08:28:48 -0500 commented question Detecting Very light particles in an image

Did you try to remove the spots from the image and see what you can do after? Threshold the image to get the bright poin

2019-03-25 11:40:52 -0500 commented question Capture the frame from iDS uEye camera.

Probably there are several things to change in that code to adapt it to your case (he used an Ethernet camera, yours is

2019-03-25 11:40:39 -0500 commented question Capture the frame from iDS uEye camera.

Probably there are several things to change in that code to adapt it to your case (he used an Ethernet camera, yours is

2019-03-25 11:39:58 -0500 commented question Capture the frame from iDS uEye camera.

Probably there are several things to change in that code to adapt it to your case (he used an Ethernet camera, yours is

2019-03-20 09:58:50 -0500 answered a question multithreading in c++, capturing thread stops after some loops

Well, your code is quite complicated, I didn't test it, and I don't understand all of it either. This is more a comment