A Novel Approach for Image segmentation algorithm has been developed and tested for green
color glove. In this approach, color based segmentation was attempted using HSV color space. The H, S and V separation was done using following equations.
V=max{R,G,B}
δ= V-min{R,G,B}
S= δ/V
To obtain value for hue following are the cases
(i) if R=V then H=1/6(G-B)/δ
(ii) if G=V then H=1/6(2+(B-R)/δ)
(iii) if B=V then H=1/6(4+(R-G)/δ)
The input image of green color samples was passed to the algorithm and from H-S histogram the
H_range = [0.4 0.55 0.6 0.6] and S_range = [0.2 1.0] were experimented for segmentation.
Algorithm could able to subtract dynamic background. Skin color samples needed to be passed to
the algorithm for skin color detection. The drawback of this algorithm was training samples of the
color need to be stored. It was sensitive to little variation in color brightness.
Hand Segmentation Using Lab Color Space (HSL)
The Input captured RGB image was converted to lab color space. In CIE L* a* b* co-ordinates,
where L* defines lightness, a* represent red/green value and b* denotes the blue/yellow color
value. a* axis and +a direction shift towards red while along the b* axis +b movement shift toward
yellow. Once the image gets converted into a* and b* planes, thresholding was done. Convolution
operation was applied on binary images for the segmentation. Morphological processing was
done to get the superior hand shape. This algorithm was found to work for skin color detection but
it was sensitive for complex background. Figure 2 shows the output with intermediate steps.
HSL Algorithm
i) Capture the Image
ii) Read the input image
iii) Convert RGB image into lab color space
iv) Convert the color values in I into color structure specified in cform
v) Compute the threshold value.
vi) Convert Intensity image into binary image
vii) Performing morphological operations such as erosion.
출처 논문은 Hand Segmentation Techniques to Hand Gesture Recognition for
Natural Human Computer Interaction
댓글 없음:
댓글 쓰기
글에 대한 의문점이나 요청점, 남기고 싶은 댓글이 있으시면 남겨 주세요. 단 악성 및 스팸성 댓글일 경우 삭제 및 차단될 수 있습니다.
모든 댓글은 검토 후 게시됩니다.