Professional Documents
Culture Documents
=
=
otherwise
if
s
,
max
min
1
max
min max
0 max , 0
(3)
(4)
The range of HSV vector is a cube in the Cartesian coordinate system, but since hue is really a cyclic property, with a
cut at red, visualizations of these spaces invariably involve hue circles. Cylindrical and conical depictions are most
popular, spherical depictions are also possible.
3. Segmentation of leaf region:
The digital image of leaf grabbed by the camera is composed of leaf and background is shown in Figure 2. To
obtain leaf feature, first the leaf needed to be separated from background [18]. It is important to choose a proper colour
space for effective image segmentation.
= +
= +
= +
=
=
b if
g r
g if
r b
r if
b g
if
h
max , 240
min max
60
max , 120
min max
60
max , 360 mod ) 0
min max
60 (
min max , 0
.
International Journal of Application or Innovation in Engineering& Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 3, Issue 2, February 2014 ISSN 2319 - 4847
Volume 3, Issue 2, February 2014 Page 100
Figure 2. Original image of sugarcane leaf
In this experiment, leaf segmentation is achieved by a threshold algorithm with I
1
, I
2
and I
3
feature as follows:
1 ) ) ( (
1 1
= s T D find I
H
(5)
1 ) ) ( (
2 2
= s T D find I
S
(6)
1 ) ) ( (
3 3
= s T D find I
v
(7)
Where,
D
H
- Difference of absolute H value (i.e. 0.33 for green colour) and actual value of leaf for green colour,
D
S
- Difference of absolute S value (i.e. 0.6 for green colour) and actual value of leaf for green colour,
D
V
- Difference of absolute V value (i.e. 0.1 for green colour) and actual value of leaf for green colour,
T
1
, T
2
and T
3
- Tolerances at positive side i.e. 0.15, 0.5, and 0.5 respectively.
I
1
, I
2
and I
3
- Colour space characters.
H, S
and V constant are set from standared colour table.
Where,
3 2 1
. . I I I I
- -
= (8)
Here, I is binary image is shown in Figure 3, where white pixels correspond to leaf region and black pixels correspond to
background.
Figure 3. Binary image of leaf
- Image smoothing:
In the second step, binary image of leaf is morphologically processed to fill holes in the image. A hole is set of
background pixels that cannot be reached by filling in the background from the edge of the image. Morphological process
named closing (i.e. Dilation followed by erosion) is performed that tends to smooth sections of contours, it generally fuses
narrow breaks and long thin gulf, eliminates and fills gaps in the contour, that removes the noise pixels present in the
leaf image [19]. Finally it bridges unconnected pixels in the image.
In the third step, a new image is formed from the original image and binary image of leaf that consist only leaf without
background which includes corresponding R, G and B values of each white pixels from the original leaf image.
Separated leaf image from background is shown in Figure 4. In this way leaf is separated from a background image and
consumption of computing is significantly reduced because the follow-up algorithm will only work on the area of leaf [18,
20].
International Journal of Application or Innovation in Engineering& Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 3, Issue 2, February 2014 ISSN 2319 - 4847
Volume 3, Issue 2, February 2014 Page 101
Figure 4. Leaf separated from the background
4. Feature extraction:
Feature extraction includes colour image processing steps to measure the green colour purity to indicate the amount of
chlorophyll present in the leaf. Form this green image the mean values of H, S and V space are computed.
- Computation of model parameters:
Model parameters in equation (1) are calculated using individual H, S and V values of 120 leaves. We use chlorophyll
meter for this, the values so obtained from this meter for corresponding HSV values are, a, b and c respectively. The mean
of all a, b and c values are the model parameters for the sugarcane leaf. During the calculation of the model parameter the
value of Y is considered as the chlorophyll content of leaf determined by the chlorophyll meter.
- Estimate the Chlorophyll value:
Referring back to equation (1), the chlorophyll of the HSV colour space is:
Where,
Y is the predicated chlorophyll content of leaves,
H, S, V is mean values and
a, b and c is model parameters obtained by regressive method.
3. RESULTS AND DISCUSSION
The chlorophyll content of sugarcane leaves is predicted by using the HSV model. The model parameters as determined
by the regressive method come out to be 378.4381, 68.7543 and -216.1429 respectively.
A comparison of the estimated chlorophyll value by algorithm and actual chlorophyll value measured by meter is shown
in Figure. The Root Mean Square Error (RMSE) of the estimated values of chlorophyll by algorithm with respect to
chlorophyll measured by chlorophyll meter is 1.9334, which clearly indicates that the values are almost overlapping each
other.
Figure 5. The correlation between actual chlorophyll and predicted chlorophyll
4. CONCLUDING REMARKS
The discussed work of measurement of chlorophyll describes the use of image analysis for determination of chlorophyll
content of leaves of sugarcane plant using the HSV colour space. Linear mathematical HSV model is used to co-relate to
the chlorophyll content apart from the simple correlation analysis.
A good agreement between the predicted and actual chlorophyll content is demonstrated. The root mean square error
(RMSE) between predicted chlorophyll and chlorophyll measured by meter comes out to be 1.9334. The result indicates
that the proposed colour space analysis is reliable and efficient for estimation of chlorophyll content.
The Chlorophyll meter was used in the present study to determine the chlorophyll content, which has already been
established as a useful tool for quantitative estimation of chlorophyll in a non destructive manner. However, while real
cV bS aH Y + + =
International Journal of Application or Innovation in Engineering& Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 3, Issue 2, February 2014 ISSN 2319 - 4847
Volume 3, Issue 2, February 2014 Page 102
time estimation of chlorophyll content of leaves, average of reading of a single leaf is the indication of chlorophyll. The
use of the proposed algorithm avoids the need of average reading. It covers the whole area of the leaf in the image and it
is possible to calculate the total chlorophyll.
This proposed method is simple and user friendly hence useful tool in laboratory as well as in the fields to measure
chlorophyll non- destructively. This methodology is also useful to measure the chlorophyll content of the leaf of other
plants by simply changing the model parameters.
ACKNOWLEDGEMENT
This work is supported by the Deprtment of Botony, Shivaji University, Kolhapur (M. S.), India and Sugarcane Research
Laboratory of Shree Datta Sahakari Sakhar Karkhana Ltd. Shirol, Dist. Kolhapur (M.S.), India.
References
[1] RGV Bramley and R. P. Quabba, Opportunities for Improving the Management of Sugarcane Production Thorough
the Adoption of Precision Agriculture, Australian Agricultural Journal, pp. 30-42, 2002.
[2] www.Jains.com, Modern Irrigation and Fertigtion Methodologies for Higher Yield in Sugarcane.
[3] J. K. Sainis, R. Rastogi and V. K. Chadda, Applications of Image Processing in Biology and Agriculture, Indian
Journal of Experimental Biology, Vol. 32, pp. 1-13, 1999.
[4] Aldea M. and Delucia E. H., Method for Quantitative Analysis for Spatially Variable Physiological Processes across
Leaf Surface, Photosyn Res, pp. 161-172, 1990.
[5] Mark Steele, Anatoly A. and Donald Rundquist, Nondestructive Estimation of Leaf Chlorophyll Content in Grapes,
American Journal of Enology and Viticulture, Vol. 59 (3), pp. 299-305, 2008.
[6] Alain Aminot, Standard Procedure for the Determination of Chlorophyll by Spectroscopic Methods, ICES
Techniques in Marine Environmental Science, pp.1-17, 2000.
[7] S. Ondimu and H. Murase, Water Stress Detection in Sunagoka Moss using Combined Thermal Infrared and
Visible Light Imaging Techniques, Bio-system Engineering, Vol. 11, pp. 4-13, May 2008.
[8] Carol L.and Niels O., Chlorophyll Estimation using Multispectral Reflectance and Height Sensing, The Society for
Engineering in Agricultural, Food and Biology Systems, 2004.
[9] Wen Jianuang and Xiao Qing, Extraction of Chlorophyll Concentration Based on Spectral Un-mixing Model using
Field Hyperspectral Data in Taihu Lake, IEEE International Conference on Geoscience and Remote Sensing, Vol. 8,
pp. 5703-5705, 2005.
[10] www.ppsystems.com, Quantifying Chlorophyll Leaves Using a Non Destructive Method with a Uni-Spec Sc, 2006.
[11] J. K. Sainis and R. Rastogi, Applications of Image Processing in Biology and Agriculture, DEA-BRNS workshop,
pp. 26-36, 1999.
[12] Hao Hu, He-Qin Liu, Hao Zhang, Jing-huan Zhu, Xu-guo Yao, Xiao-bin Zhang, and K. Feng Zhang, Assessment of
Chlorophyll Content Based on Image Colour Analysis, Comparison with SPAD 502, IEEE transaction, pp. 42-66,
2010.
[13] Satya Prakash Yadav and Yasuomi Ibaraki, Estimation of the Chlorophyll Content of Micro Propagated Potato
Plants using RGB Based Image Analysis, Springer, Plant Cell Tiss Organ Cult., Vol. 100, pp.183-188, 2010.
[14] Hakan Bjurstrom, Jon Svensson, Assessment of Grapevine Vigour using Image Processing, Masters Thesis in
image processing, Linkoping University, Sweden, 2002.
[15] B. Chanda and D. Majumdaer, Digital Image Processing and Analysis, PHI publication, New Delhi (India), Third
Edition 2000.
[16] http/ HSL and HSV- Wikipedia, encyclopedia, pp. 1-25.
[17] Mikko HAUTALA and Mikko HAKOJ ARVI, Plant Growth Models for Precision Agriculture, Journal of Plant
Physiology, University of Helsinki, Finland, pp.112-126, 2009.
[18] Changyong LI, Qixin CAO and Feng GUO, A Method for Colour Classification of Fruits Base on Machine Vision,
WSEAS Transactions on Systems, Vol. 8(2), pp. 312-321, 2009.
[19] Ten-Wen Pai, Jon H. L. and Hansen, Morphological Image Processing with Application to Medical Imaging,
Annual Engineering Conference of IEEE, Engineering in Medicine and Biology Society, Vol. 12 (1), pp. 160-163,
1990.
[20] Parviz Ahmadi and Mohammadali Haddad, Estimation of Single Leaf Chlorophyll Content in Sugar Beet Using
Machine Vision, Turak J. Agric, Vol. 35, pp.. 563-565, 2011.