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
Measurement of Sugarcane Leaf Chlorophyll
1
Prof. Dr.Sanjay B. Patil, 2Mr. Sujit S. Patil
1
2
Dept. of E&TC,MBT Campus, Islampur, (M.S.),India
Dept. of Computer Sic., MBT Campus, Islampur, (M.S.), India
ABSTRACT
An image analysis is used for determination of chlorophyll content of leaves of sugarcane plant using the HSV color space. A
Liner mathematical HSV model is proposed to co-relate with the chlorophyll content, apart from the simple correlation analysis.
Among the mean HSV (Hue, Saturation, and Value), the significant co-relation is observed between Saturation and Value
parameter with chlorophyll content, while no co-relation is observed with Hue parameter. 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 CM1000 meter is found to be 1.9334.
Keywords: Anlysis, Chlorophyll, Colour, Dilation, Distruction, Image, Filter
1. INTRODUCTION
The duration of sugarcane crop ranges from 10-18 months, a 12 month’s crop is most common. Experimentally and by
research it has been proved that for high yield of the sugarcane, careful crop status management is essential during the
germination and tillring stages of the growth [1].
Soil quality, fertilizer and micronutrients, irrigation water and other environmental factors such as temperature and
humidity play an important role in the growth of the sugarcane. Compared to other crops, the cultivation of sugarcane
demands more water (150-200 times more than other crop like rice). The application of fertilizers and pesticides is also
quite more [2]. Considering all these factors the productivity of sugarcane crop draws attention of farmers.
The plant leaf colour is commonly used tool to specify health status of the plant. Chlorophyll is a green pigment found in
almost all plants, which allows the plants to obtain energy from light [3]. The loss of chlorophyll content in leaves occurs
due to nutrient imbalance, excessive use of pesticide, environmental changes and ageing. Various kinds of colour plates
are available for estimation of chlorophyll content of plants [4]. Chlorophyll meter (SPAD), has been developed to
estimate leaf chlorophyll content [5]. These tools are a good option to chemical analysis method and remote sensing
method used to find the chlorophyll content of the plants [6].
Most of these techniques are quite accurate but they are rarely used in practice because of the high cost of SPAD meter,
unavailability of a remote sensing system and other constraints.
Chlorophyll is a green pigment which is the basic ingredient of the leaf of a plant [7]. It is due to the presence of
chlorophyll, that the leaves are green colours in nature. Chlorophyll absorbs certain wavelengths of light within the
spectrum of visible light as shown in Figure 1. It absorbs both red region (long wavelength) and the blue region (short
wavelength) of the visible light spectrum while the green colour wavelength which makes the plant appear to be green [8,
9].
Figure 1 Absorption spectra of chlorophyll
Plants are able to satisfy their energy requirements by absorbing light from the blue and red parts of the spectrum.
However, there is still a large spectral region between 500 to 600 nm where chlorophyll absorbs a little amount of light.
Chlorophyll measuring meters measure the optical absorption of a leaf to estimate its chlorophyll content [10].
Volume 3, Issue 2, February 2014
Page 97
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
Chlorophyll molecules absorb in the blue and red bands, but not the green and infra-red bands, thus meters measure the
amount of absorption at these bands to estimate the amount of chlorophyll present in the leaf.
2. ANALYSIS AND DESIGN
From the frequency spectra of absorption of chlorophyll, it can be seen that there is a good relation between chlorophyll
content of leaf and primary colours light (Red, Green, and Blue).
The intensity of colour for each leaf disk is an arbitrary unit of intensity called inverse integrated gray value per pixel
[11]. It is proportional to the actual concentration of chlorophyll per pixel. Thus the concentration of chlorophyll per pixel
can be measured from the colour image of leaf.
The chlorophyll value of sugarcane leaf can be measured by chlorophyll meter but it tends to be costlier [12]. It also
suffers from another limitation that the readings cannot be taken at low light intensity.
Thus there is a need of a cost effective system which can overcome the above limitation.
Hence an algorithm is designed to measure the chlorophyll content of the sugarcane leaf using RGB based image analysis.
Presumably, any colour can be decomposed into the primary colour components (RGB) and the intensity of an individual
colour upto some extent can be represented by brightness in a digital image [13]. Thus it is possible to develop a
mathematical correlation between the chlorophyll content of the leaf of the sugarcane plant and the brightness values of
the primary colours.
For the purpose of verification of results, the chlorophyll value of sugarcane leaf was measured by chlorophyll meter (CM
1000 meter manufactured by Spectrum Technology USA). The meter readings were considered as a standard measured
value.
a) Proposed Image processing based method of chlorophyll measurement:
Taking into consideration, the targeted area of leaf the leaf was cut to 6  2 cm size and the image of a leaf was
captured by digital camera. From this image of a leaf, the mean brightness of primary colour (R, G, and B) was recorded
and transformed into spectral parameters such as hue (H), saturation (S) and value (V).
The formula to obtain the chlorophyll content the above value is given in equation (1) as [13]:
Y  aH  bS  cV
(1)
Where,
Y - Predicated chlorophyll,
H, S and V - spectral parameters of basic primary colours and
a, b and c- Model parameters
Model parameters a, b and c are evaluated using the regressive method (discussed in detail in further section).
Thus the proposed system is designed for measurement of chlorophyll content of sugarcane leaf that involves:
1. Operation of capturing of image,
2. Computation of mean H, S and V values and
3. Estimation of chlorophyll content of leaf.
b) Implementation:
In this research an algorithm is designed to measure the chlorophyll content of the sugarcane leaves.
 Algorithm:
The processing steps of the proposed algorithm are as follows:
1. Acquire the image of a leaf
2. Preprocessing of image to convert into proper format
 Image resizing
 RGB to HSV conversion
3. Segmentation of leaf region
 Smoothing the image
4. Feature extraction
 Compute the model parameters a, b and c
 Estimate the Chlorophyll value by formula
1. Acquiring the images:
Following experimental set-up was made for image acquisition:
1) Digital camera: 12 Mega pixel, 4X zoom (Nikon make) was used for acquiring the image.
2) Background selection: Selection of background is an important step to distinguish objects from the background.
Magenta colour is complementary to green and therefore provides good colour contrast, making hue separation
successful, but the sharp edge between magenta and green area results in noise during the background separation
therefore white background was used [14].
Volume 3, Issue 2, February 2014
Page 98
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
3) Sugarcane leaf was placed flat on white background in natural light. The optical axis of digital camera were adjusted
perpendicular to the leaf plane to shoot images.
2. Preprocessing of image to convert in proper format:
To separate leaf from the background, the following steps are followed.
 Resize the image:
The size of the captured image is 4000 3000 . The image is down sampled by a factor of 10 (i.e. Resized to
400  300 ), to improve the speed of further process. The resizing of an image is performed by the process of the
interpolation [15]. This resized colour image is used for HSV space conversion.
 RGB to HSV conversion:
The hue (H) defines the colour according to wavelength, while saturation (S) is the amount of colour. An object
that has a deep, rich tone has a high saturation and one that looks washed out has a low saturation. The last component
value (V) describes the amount of light in the colour [16]. The main disadvantage of the RGB model is that humans do
not see colour as a mix of three primaries. Rather our vision differentiates between hues with high or low saturation and
intensity; which makes the HSV colour model closer to the human perception than the RGB model. In the HSV space it is
easy to change the colour of an object in an image and still retain variations in intensity and saturation such as shadows
and highlights. It is simply achieved by changing the hue component, which would be impossible in the RGB space. This
feature implied that the effects of shading and lighting can be reduced. [17].
r , g , b  0, 1 be the red, green, and blue coordinates, respectively, of a colour in RGB space. Let maximum be
the greatest of r, g and b and minimum the least.To find the hue angle, h  0, 360 for HSV space is computed as:
Let
if max  min
0 ,

(60  g  b  0  ) mod 360. ,
max min

h 
br

60  max min  120 ,

60   r  g  240 ,

max min
(2)
if max  r
if max  g
if max  b
The value of h is generally normalized to lie between 0 and 360°, and h = 0 is used when max  min (that is, for
grays) though the hue has no geometric meaning there, where the saturation s is zero.
The values for s and v of an HSV colour are computed as:
0,

s   max min
min
 1
,
 max
max
if max  0
(3)
otherwise
(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.
Volume 3, Issue 2, February 2014
Page 99
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
Figure 2. Original image of sugarcane leaf
In this experiment, leaf segmentation is achieved by a threshold algorithm with I1, I2 and I3 feature as follows:
I1 ( find ( DH  T1 ) )  1
(5)
I 2 ( find ( DS  T2 ) )  1
(6)
I 3 ( find ( Dv  T3 ) )  1
(7)
Where,
DH - Difference of absolute H value (i.e. 0.33 for green colour) and actual value of leaf for green colour,
DS - Difference of absolute S value (i.e. 0.6 for green colour) and actual value of leaf for green colour,
DV - Difference of absolute V value (i.e. 0.1 for green colour) and actual value of leaf for green colour,
T1, T2 and T3 - Tolerances at positive side i.e. 0.15, 0.5, and 0.5 respectively.
I1, I2 and I3 - Colour space characters.
H, S and V constant are set from standared colour table.
Where,
I  I1. I 2 . I 3
(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].
Volume 3, Issue 2, February 2014
Page 100
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
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:
Y  aH  bS  cV
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
Volume 3, Issue 2, February 2014
Page 101
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
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”, Master’s 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 HAKOJARVI, “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.
Volume 3, Issue 2, February 2014
Page 102