Ask Your Question

Damien45's profile - activity

2020-10-08 15:13:03 -0500 received badge  Notable Question (source)
2019-11-10 07:42:56 -0500 received badge  Popular Question (source)
2018-04-13 07:23:09 -0500 received badge  Student (source)
2018-04-04 06:47:46 -0500 commented question Enable cudacodec::VideoReader

I think that it is a bug, so I created an issue :

2018-04-04 05:46:04 -0500 commented question Enable cudacodec::VideoReader

Did not work with WITH_NVCUVID. Always the same error message.

2018-04-04 03:40:36 -0500 commented question Enable cudacodec::VideoReader

Thank you, it helps me to go further (see EDIT on the question)

2018-04-04 03:12:31 -0500 received badge  Enthusiast
2018-04-03 13:51:22 -0500 asked a question Enable cudacodec::VideoReader

Enable cudacodec::VideoReader Good morning, I try to use the cuda VideoReader to read a mkv/h264 file. I see in the doc

2017-05-15 14:54:07 -0500 asked a question Best approach to detect read numbers from 1 to 99

Hi !

I'm currently using OpenCV to detect things on a video and those things have sometime a number printed on, which I want to read. Theses numbers could be from 1 to 99 and I'm able to extract them in a binary image as :

I try these approches : - Cascade classification using HAAR and HOG classifier : very poor results even if I work with ~500 positives images and thousands of negatives (I train these classifier using gray-scale images) - Tesseract OCR, but, even with these binary images, and even if I told him that there is only digits, it reads 3 as many as 8, so it is not reliable (And it actually reads nothing most of the time).

Have you any advice to handle these case ? Maybe a feature type that I don't try ? A hack using hough line detection or things like that ?

Thank you in advance.