Ripeness Evaluation of Mango using Image Processing

IDL - International Digital Library Of
Technology & Research
Volume 1, Issue 4,April 2017 Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017
IDL - International Digital Library 1 | P a g e Copyright@IDL-2017
Ripeness Evaluation of Mango using Image
Processing
Sharadha shree 1
, Dr. Chandrappa D.N2
1
Student ,M.Tech, DEC, GMIT Davangere.
2
Professor and HOD, Dept. Electronics Engineering, GMIT DAVANGERE.
ABSTRACT
Abstract— Mangoes are delicious seasonal fruits
grown in the tropics. They are harvested from its
grove when matured enough for the market. They do
not mature uniformly in trees but stage by stage.
Most farmers use manual experts for ripening
evaluation of the mangoes which is time consuming,
inconsistent and inaccurate. To avoid manual effort,
an automated Computer vision technique is
introduced in this paper. This includes preprocessing,
Segmentation, Feature extraction and classification.
Here 24 color features are extracted from the mango
image. Classifying the mango into two different
classes according to their maturity level using k-NN
Classifier and this proposed system resulted in the
accuracy of about 97% in evaluation of ripeness of
Mangoes.
General Terms
Quality Inspection, Feature Extraction, Color Feature.
Keywords
Feature Extraction Keywords—Segmentation,
Feature Extraction, k-NN classifier.
1. INTRODUCTION
Agriculture is one of the largest economic sector and it
plays a major role in the development of our country. The
ever-increasing population demands for higher quality of
mangoes with good appearance. There is a need for the
development of accurate, fast and focused quality
determination of mangoes.
Harvesting of mangoes is performed in several steps like
cutting of fruits from the farm, washing, sorting, grading,
packing, transporting and finally storing. Out of these
sorting and grading are major processing tasks associated
for preserving the quality of mangoes.
Sorting of mangoes is done based on appearance of fruits,
whereas grading is done based on the overall quality
features of fruits by considering a number of attributes
like shape, size, color and texture etc.
Classification is necessary for the quality evaluation of
mangoes. Fruit industry for its excellent trading purpose
goes for highly selective ones in quality and standard. It
demands the suppliers and the distributors the fruits of
high standards of quality, package and presentation. So
there is a increasing need to supply quality fruits within a
short period of time has development of Computer Vision
Techniques to improve the quality.
In present scenario, sorting and grading of fruit
according to maturity level are performed manually
before transportation. This manual sorting by visual
inspection is labour intensive, time consuming and

suffers from the problem of inconsistency and
inaccuracy in judgement by different human and
provides an opportunity to apply Computer Vision
based systemto assess this problem
Problem statement
For exports, grading is done manually by the experts now
which is very time consuming and subjective. So,
farmers need alternatives for sorting and grading
mangoes. An automated mango sorting system could be
more preferable as it can be cheaper, consistent and
could result in better overall quality. Thus the scope of
the project is to develop an automated computer vision
systemfor sorting of mango based on maturity level.
Literature Survey
Chandra Nandi et al. (2012), implemented a computer
vision based system for automatic grading and sorting of
mangoes based on maturity level from its RGB image
frame, collected with the help of CCD camera.
Parameters of different classes of mangoes are estimated
using Gaussian Mixture Model. Graph contour tracking
method based on chain code is adapted for finding the
boundary of the mango. This automated technique is
good but is further affected by ambient light intensity.
Response time of systemis on the order of 50 ms [1].
CCD camera was used to collect video image of
Mangoes and several significant features of maturity
level of Mango was obtained. Colour of Mango was
estimated using Gaussian Mixture Model. Accuracy can
be improved by using Support vector machine and neural
network. Gaussian Mixture Model (GMM) and fuzzy
logic was combined for size based grading of Mango.
Size of Mango was calculated using pixel area covered
by Mango [2].
Tajul Rosli et al. Proposed and implemented
methodologies and algorithms to determine the grade of
local mango production in Perlis. The main contribution
a design and development of an efficient algorithm for
detecting and sorting the mango at more than 80%
accuracy in grading compared to human expert sorting.
This work proposes a mango grading technique for
mangoes quality classification by fuzzy logic based
image processing [3].
P. Sudhakara Rao et al. (2009) have adopted HSI
model for sorting and grading of fruits by color and
developed a system for on-line sorting of Apples based
on color, size and shape. Images are captured by a color
CCD camera and frames are separated by a frame grabber
card and it produced the image in RGB model. The image
is analyzed by using advanced image processing
techniques to estimate the color of image. Using image
processing system achieved around 98 % accuracy in
color inspection of apples [4].
Suzanawati Abu et al. Proposed and implemented
Automated Mango Fruit Assessment Using Fuzzy Logic
Approach. This work developed a new method of
automated mango Size and grade assessment using RGB
fiber optic sensor and fuzzy log ic approach. The
calculation of maximum, minimum and mean values
based on RGB fiber optic sensor. To analyse the data and
make the classification for the mango fruit uses the
minimum entropy formulation method. The automated
mango grading system using fuzzy logic achieved
77.78% accuracy in overall categories [5].
Methodology
The following steps are followed to perform the ripeness
evaluation of mango
1. Select the mango image.
2. Crop the area of mango.
3. Find and calculate the major axis.

4. Align the mango image.
5. Divide the 3 regions.
6. Extract the color features fromthe 3 regions.
7. Use nearest neighbour classification algorithmfor
database features.
8. Output results based on the maturity level.
1) The basic global threshold, T, is calculated as
follows:
1. Select an initial estimate for T
(typically the average grey level in the
image)
2. Segment the image using T to produce
two groups of pixels: G1 consisting of
pixels with grey levels >T and G2
consisting pixels with grey levels ≤ T
3. Compute the average grey levels of
pixels in G1 to give μ1 and G2 to give
μ2
4. Compute a new threshold value:
5. Repeat steps 2 – 4 until the difference
in T in successive iterations is less than
a predefined limit T∞.
Fig 1 .Flowchat

Fig 2. Input Mango image Fig 3. Conversion to grayscale
Fig 4. Image after thresholding Fig 5. Centroid of mango (red *)

Fig 6. Dominant bin in histogram
Rule 1
If spots are more and
Rule 4
If spots are average and
Size is less and Size is medium and
Color is unripe then Color is unripe then
Grade is Rejected Grade is Grade 3
The following range of the dominant bin over ‘a’ channel of
Lab color space was observed
Table 1: Dominant ‘a’ color range Rule 8
If spots are less and
Rule 10
If spots are less and
Category Size is medium and
Color is semi ripe then
Size is large
Color is Ripe then
Unripe Mango Grade is Grade 2 Grade is Grade 1
Semi Ripe Mango
Ripe Mango
Dominant a
a<=117
117<a<130
a>=130
After the analysis it was found that categorization into
unripe, semi ripe and ripe is possible by the range as in
Table 1.
So at this point the dominant color, spots and size features are
extracted from the mango. All the features with corresponding
values are shown in Fig 6. These are the feature parameters for
the grading. Based on this the grading rules are created. Some
of them are shown Table 2.
Table 2: Sample rules of grading
On the basis of grading rules results are shown in section 3.

Table 3. Accuracy with the proposed method
Grade
Correctly
Classified
Samples
Total
Correct
Samples
Accuracy
Proposed
MethodExtra Class 86 86 100%
Grade 1 55 58 94.82%
Grade 2 187 196 95.40%
Rejected 52 58 89.66%
Average Accuracy 94.97%
Table 4. Comparison of time
Full Mango Proposed Method
Time (seconds) 499.43 secs 377.23 secs
Average time for
1 mango
1.248 sec 0.9425 sec
4. CONCLUSION AND FUTURE
DIRECTION
An algorithm for the grading of the mangoes was
developed. Color, spots and size were taken as the
feature parameters for the grading the mangoes into
grade1, grade2, grade3 and
rejected. A modified dominant color feature
extraction
technique using the Lab color model had been proposed.
Instead of taking the whole mango the color feature was
extracted from the strip on the surface of mango. The
spots were extracted from the whole surface of the
mango. Length of the major axis was used for the size
feature. Experiment shows that the proposed method
has more accuracy as well as efficiency.
Proposed algorithm was able to classify the mangoes
with an accuracy of 94.97 % into various grades. And
time taken for the grading of a mango on average was
less than a second. So the proposed method is accurate
as well as efficient. In the future work the texture on
the surface of the mango can also be used as a feature
parameter for grading so that the overall accuracy can
be improved.
Acknowledgemet
Authors would like to thank Mr.Ruknuddin Kazi
(Valsad, Gujarat) for the authentication of the dataset of
the mangoes.
5. REFERENCES
[1] Xu Liming and Zhao Yanchao, "Automated
strawberry grading system based on image
processing," Computers and Electronics in
Agriculture, vol. 71, no. Supplement
1, pp. S32-S39, April 2010.
[2] Tajul Rosli Bin Razak, Mahmod Bin
Othman(DR), Mohd Nazari Bin Abu Bakar(DR),
Khairul Adilah BT Ahmad, and AB.Razak Bin
Mansor, "Mango Grading By Using Fuzzy Image
Analysis," in In proceedings of International
Conference on Agricultural, Environment and
Biological Sciences, Phuket, 2012.
[3] Teoh, Yeong Kin, Abu Hasan, Suzanawati, AND
Sauddin@Sa’duddin, Suraiya. "Automated Mango
Fruit Grading System Using Fuzzy Logic"
Journal of Agricultural Science [Online],
Volume 6 Number 1, December 2013.
[4] Kazuhiro Nakano, "Application of neural networks
to the color grading of apples," Computers and
Electronics in Agriculture, vol. 18, no. 2-3, pp. 105-
116, August 1997.

[5] M. Khojastehnazhand, M. Omid, and A.
Tabatabaeefar, "Development of a lemon sorting
system based on color and size," African Journal of
Plant Science, vol. 4(4), pp.
122-127, April
2010.
[6] Akira Mizushima and Renfu Lu, "An image
segmentation method for apple sorting and grading
using support vector machine and Otsu‘s method,"
Computers and Electronics in Agriculture, vol. 94,
pp. 29-37, June
2013.
[7] Nursuriati Jamil, Azlinah Mohamed, and Syazwani
Abdullah, "Automated Grading of Palm Oil Fresh
Fruit Bunches (FFB) using Neuro-Fuzzy
Technique," 2009
International Conference of Soft Computing and
Pattern
Recognition, pp. 245-249,
2009.
[8] Yousef Al Ohali, "Computer vision based date
fruit grading system: Design and implementation,"
Journal of King Saud University - Computer and
Information Sciences, vol. 23, no. 1, pp. 29-39,
January 2011
[9] U. Ahmad, M. Suhil, R. Tjahjohutomo, and
H.K.
Purwadaria, "Development of Citrus Grading System
Using Image
Processing". [Online]
http://repository.ipb.ac.id/handle/123456789/68
910
[10] Naoshi Kondo, Usman Ahmad, Mitsuji Monta,
and Haruhiko Murase, "Machine vision based quality
evaluation of Iyokan orange fruit using neural
networks," Computers and Electronics in
Agriculture, vol. 29, no. 1-
2, pp. 135-147, October
2000.
[11] Ankur M Vyas, Bjial Talati and Sapan Naik.
Article: Colour Feature Extraction Techniques of
Fruits: A Survey. International Journal of
Computer Applications 83(15):15-22, December
2013. Published by Foundation of Computer
Science, New York, USA.
[12] Cheng, Heng-Da, X. H. Jiang, Ying Sun, and
Jingli Wang. "Colour image segmentation: advances
and prospects." Pattern recognition 34, no. 12
(2001): 2259-
2281
.
[13] Naik S. and Patel B, “CIELab based color
feature extraction for maturity level grading
of Mango (Mangifera Indica L ), National journal
of System and Information technology , ISSN: 0974
3308.

Ripeness Evaluation of Mango using Image Processing

More Related Content

What's hot (9)

Similar to Ripeness Evaluation of Mango using Image Processing (20)

Recently uploaded (20)

Ripeness Evaluation of Mango using Image Processing