Tag Info

Can you identify the reason why it fails? Is there a shift in the object appearance or in the relat in on between object snd background? Can you share images? In 2012 I had good inter-detection-frame ...

I wrote an answer once for another question where the images needed some segmentation before (splitting the images into two). Some stuff to consider: the OCR algos require nice images to work well, so ...

I have 16th century Spanish books containing missed text words and low quality.

On OpenCV page I found Text Detection and Removal using OpenCV

I even found question which uses numpy in similar way: python 3.x - Detect lines of text in image openCV - Stack Overflow

it all depends on what the pages look like. If pages are white and text-lines are vertical then usually there are pixels-lines with many white pixels between text-lines. And it would allow to split it ...

OpenCV's VideoWriter does not, to my knowledge, have the ability to write videos with Presentation Timestamps (PTSes). There is at least one feature request for this: the one feature request that I ...

I used a similar idea in a vehicle detection project, where a line was just a trigger to decide when to process the frame. You can apply that here as well, but only as a trigger, not as the decision ...

This is a very challenging project considering the practical constraints involved. Before thinking about models, it is important to consider the image acquisition and processing challenges, such as ...

I don't see YOLO nor MediaPipe in project on GitHub. There is only basic code for titanic.csv

You either invert the matrix using cv::invert or np.linalg.inv. Or you simply pass the WARP_INVERSE_MAP flag to the warp function (warpPerspective or warpAffine both accept the flag), which will make ...

I have had a similar issue and solved it - maybe it helps someone else :) My goal was to extract a qr-code from an image, warp it so it's "nice and straight", then draw on it, and then warp ...

One possible approach is to combine object detection, pose estimation and behavior analysis. A typical pipeline could look like this: 1. Use an object detection model such as YOLOv8 to detect students ...

There are multiple issues with your code that I will address briefly: First of all, your calculation for the player_obstacle_distance is incorrect. Your player has already crashed into the obstacle ...

You have to use the detector you created. Just because the running mode is live stream doesn't mean the detector object knows which live stream. You've directed data out of it with the callback, but ...

Why do you think the resize 2x is very important? It adds no new information to the original image. You are better off scanning at a higher resolution in the first place. The processing chain looks ...

You should add the image with example text which makes problems to have a minimum reproducible example.

you could add image with example text which makes problem.

OpenCvSharp now has FaceDetectorYN with NuGet 4.13.0.20260302 onwards.

Thank you so much for the elaborate answer André! Your results look very promising, I will try to implement this in the coming days and get back to you. Edit 26-02-2026: I have introduced the method ...

Moved from an edit to the question: SOLUTION: I've had to train my own data to try it with the OCR. It seems that works well, but I don't know why the trained data from arturaugusto not works for me =(...