Click here to Skip to main content
11,495,272 members (34,761 online)
Rate this: bad
good
Please Sign up or sign in to vote.
Package:
- OpenCV 2.1
- windows 7(64)
- Visual Studio 2008
- PlayStation Eye Camera


I have used MORPHING_METHOD_ERODE_DILATE to track finger area which does not track accurately

I have to scan a text in ROI rectangle which will be marked above finger.

http://www.youtube.com/watch?v=_xLwlOx-EyU[^]

need some suggestion
- to perform better finger tracking
- for machine learning of text in ROI




Thanks..
Posted 13-Apr-11 23:35pm
01.mandar1.3K

1 solution

Rate this: bad
good
Please Sign up or sign in to vote.

Solution 1

i suggest you use Viola and jones classifier and train it for fingers(thats one way)
OR
from the video you just need to blur the image to a certain level and a simple background subtraction will give you an accurate movement of the finger, then a morphological operation and getting the biggest area would give a better detection.
OR color tracking, skin color tracking also would give you another solution.
  Permalink  
v2

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

  Print Answers RSS
0 Dnyaneshwar@Pune 692
1 CHill60 318
2 Sascha Lefèvre 280
3 Sergey Alexandrovich Kryukov 245
4 Nakul Chaudhari 236
0 Sergey Alexandrovich Kryukov 10,307
1 OriginalGriff 8,821
2 Sascha Lefèvre 3,889
3 Maciej Los 3,412
4 Richard Deeming 2,560


Advertise | Privacy | Mobile
Web03 | 2.8.150520.1 | Last Updated 15 Nov 2011
Copyright © CodeProject, 1999-2015
All Rights Reserved. Terms of Service
Layout: fixed | fluid

CodeProject, 503-250 Ferrand Drive Toronto Ontario, M3C 3G8 Canada +1 416-849-8900 x 100