# A b then the total number of white pixels are

• 5

This preview shows pages 3–5. Sign up to view the full content.

(a) (b) Then the total number of white pixels are calculated which will be equal to the total number of pixels corresponding to damaged skin. Once it is obtained, the area of damaged skin is calculated by: Total defective area = N x 6.093845 x 10 -4 sqcm. Where N = no: of defective pixels. Fig 3: Contour extracted from the image of the mango Fig 4: (a) Original Image (b) Binarised image were defective skin is represented as white 2015 IEEE International Advance Computing Conference (IACC) 1193

This preview has intentionally blurred sections. Sign up to view the full version.

This is then used to grade the mango into the right category using the AGMARK standards. V.RESULTS & D ISCUSSIONS The algorithms for sorting and grading of mangos were implemented using OpenCv2, the python2.7 computer vision library and Image processing library in MATLAB7.8. To validate the algorithms a set of 12 mangos containing 9 Alphonso mangos and 3 non Alphoso verities were used. The sorting method used in the system was tested on this set of 12 mangos. The reference contour of the Alphonso mango is taken. Hue moments (Eq5) are calculated for all these mangos. The difference in Hue moments between these and the reference are then computed. It was found that when this difference is less than 0.2, it corresponds to Alphonso mango. The Fig 6 shows a boxplot representing the classification of mangos into Alphonso and non Alphonso varieties. In a boxplot each box represents a set of values, where the central value represents the median, the box edges represent the 25th and 75th percentiles and the outliers are plotted individually. The X-axis of the given plot represents the two varieties of mangos i.e. the Alphonso and the Non Alphonso categories and the Y-axis represents the deviation from the reference Hue moments. In the set of Alphonso mangos 8 out of 9 mangos were classified correctly. The wrongly classified one is placed as outlier in the boxplot. In the set of Non-Alphonso mangos 2out of the 3 non Alphonso mangos were correctly classified. Since the wrongly classified one has a very low difference value the plot extends towards the Alphonso class. The developed system correctly sorted 10 out of 12 mangos in to the correct categories. It shows an overall accuracy of 83.33%. For calibration the camera with resolution 700x525 was fixed at a height of 17cm above the level of the mango tray. An image of 1sqcm was taken as shown in Fig 5 below. The colored region in the Fig ure represents area corresponding to 1sqcm. Next the number of pixels in that one square centimeter was calculated, which was found to be 1641 pixel for the particular camera used. Then the area of each pixel was calculated as follows: No of pixels in 1cm 2 = 1641 pixels So 1 pixel = 1/641=6.093845 x 10 -4 sqcm. Thus the area corresponding to one pixel was calculated to be 6.093845 x 10 -4 sqcm. Using these calculations the number of defective pixels and the defective area was found for these nine mangos. The results are tabulated and shown in table1.
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern