ELECTRONIC
pauly2015.pdf

# A hue moments there are seven hue moments which are

• 5

This preview shows pages 2–4. Sign up to view the full content.

A. HUE MOMENTS There are seven Hue moments which are used for shape analysis. They can be computed as: The spatial moments m ji of an image are computed as [8]: i j ji y x y x I m . ). , ( (1) the central moments mu ji are calculated as: i y x j ji y y x x y x I mu , ) .( ) ).( , ( (2) the y x , are the center of mass calculated by : 00 01 00 10 , m m y m m x (3) The normalized central moments nu ji are calculated as: l j i ji ij m mu nu 2 / ) ( . (4) The moments of a contour are also calculated similarly but by using the Green’s formula [9]. The seven Hue Moments of a contour are defined as: Capturing Image Sorting Grading Place mangos in correct basket Fig 1: Block level description of the developed system Fig 2: Top view image of the mango in blue 1192 2015 IEEE International Advance Computing Conference (IACC)

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

] ) ( ) ( 3 )[ )( 3 ( ] ) ( ) ( 3 )[ )( 3 ( ] 6 [ ) )( ( 4 ] ) ( ) )[( ( ] 5 [ ] ) ( ) ( 3 )[ )( 3 ( ] ) ( 3 ) )[( )( 3 ( ] 4 [ ) ( ) ( ] 3 [ ) 3 ( ) 3 ( ] 2 [ 4 ) ( ] 1 [ ] 0 [ 2 03 21 2 12 30 03 21 12 30 2 03 21 2 12 30 03 21 03 21 03 21 12 30 11 2 3 0 21 2 12 30 02 20 2 03 21 2 12 30 03 21 03 21 2 03 21 2 12 30 12 30 12 30 2 03 21 2 12 30 2 03 21 2 12 30 11 2 02 20 20 hu hu hu hu hu hu hu 02 2 (5) where ji stands for the normalized moments nu ji. The first six values are independent to the image scale, rotation, and reflection. But the sign of the seventh value changes during reflection . Hence these values can be used as criteria to define a particular shape. B. S ORTING ALGORITHM The image of mango is taken as input and contours corresponding to the shape are extracted from it. The Fig .3 shows the contour extracted from the image of the mango shown in Fig 2. All the seven Hue moments of this contour is calculated using equation 5. These seven values are then compared with seven Hue moments of reference model of an Alphonso mango. The difference in the hue moments between the image and the reference is computed using the equation: A i B i B i i A A i A i B i A i h h sign m hi h sign m where m m B A d log ). ( log ). ( , | | ) , ( (6) And B i A i h h , are the Hue moments of A and B respectively. If this difference of Hue moments d(A, B) is zero then the shapes matches perfectly. It was found that if the difference has values less than 0.2 it belongs to Alphonso variety of mango. C. G RADING ALGORITHM This is one of the most important preprocessing steps that determine the quality of the mango being exported. The export quality of the mango is determined suing AGMARK standards, the Indian standardization for ensuring quality of food items. The purpose of the computer vision algorithm is to calculate the area of defective skin of the mango and grade the mango into any of the 3 classes respectively. A color image of the mangos was used for the analysis. If the pixel value is less than 100 it is considered as a part of defective skin. Any pixel value greater than 100 is a part of pure skin. The image is binarised with pure part of the image made black while the damaged ones white. The Fig 4 shows the original image and the binarised image were white represents the defective skin.
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