-
Notifications
You must be signed in to change notification settings - Fork 405
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Image size for detection #12
Comments
Could you write a code that you use to perform detection? I have tried to detect objects when the image dimensions are not multiple of 16, but the algorithm works fine. So I think that you could incorrect use Simd::Detection. |
This is pretty much it: #include "simd/src/Simd/SimdDetection.hpp" typedef Simd::DetectionSimd::Allocator Detection; void Debug(const char *s) extern "C" long InitDetection(char *detectionPath, int pictureWidth, int pictureHeight)
} extern "C" int CloseDetection(long detectionObject) extern "C" int CalcDetection(long detectionObject, int pictureWidth, int pictureHeight, void* pictureData, int* results)
} |
You have a mistake at this line:
This constructor creates a Simd::View with given alignment but original image doesn't have the same one.
|
Thank, this solves my problem, closing the issue. |
It appears that the number of pixels in each direction must be a multiple of 16 for the detection to find e.g. faces using the included Haar cascade for frontal faces. When the image dimensions are not multiple of 16, there is no error reported, but the detection algorithm does not find any faces.
The text was updated successfully, but these errors were encountered: