Click here to Skip to main content
15,884,176 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more:
in my code i take an image and apply this pre-processing on it

bitwise_not(src, src);
	
	// matrices used
	Mat dst; // image after preprocessing
	
	
		//frame=src;
		cvtColor(src, dst, CV_BGR2GRAY);
		GaussianBlur(dst, dst, Size(7, 7), 5, 3, BORDER_CONSTANT); // tiny bit of smoothing is always a good idea
		threshold(dst, dst,0, 255, CV_THRESH_BINARY | THRESH_OTSU);


now i want to apply uniformlbp on the result image

is this right
if not what is the best pre-processing to apply in order to remove noise from image
Posted
Updated 11-Jun-14 22:29pm
v2
Comments
Sergey Alexandrovich Kryukov 10-Jun-14 18:19pm    
There are no the "best" or "perfect" noise reduction algorithms. They all have limited effect, do not completely smooth out noise, they reduce real resolution; and the preferences depend on original image. What works better for one image can be worse for another one. Sounds sad but true. :-)
—SA
MSMHMA 10-Jun-14 18:26pm    
ok i know i asked this question to know if these function effect badly on image as the lbp take gray level image
Legor 12-Jun-14 4:33am    
To see which effect the gaussian has you can compare your classification results with and without using smoothed images.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900