CLASSIFICATION OF APPLE DEFECTED FRUITS USING COLOR IMAGE ANALYSIS TECHNIQUE | ||||
| Misr Journal of Agricultural Engineering | ||||
| Article 12, Volume 30, Issue 2, April 2013, Page 487-506 PDF (1.7 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/mjae.2013.102046 | ||||
 View on SCiNiTO | ||||
| Author | ||||
| A. A. Abd El-Rahman | ||||
| Senior Res., Agr. Eng. Res. Inst., Agr. Res. Center, Cairo, Egypt. | ||||
| Abstract | ||||
| Image analysis algorithm was developed to provide the classification parameters for defect of yellow apple fruits. The objectives of this work are: 1) To use and test an image processing system which could classify defects on apple surfaces based on color analysis,and2) Extraction of values of Red, Green and Blue (RGB) coordinates and color properties of Hue, Saturation, and Intensity (HSI) from the infected area. Experimental setup of color analysis was used for taking an image for each apple sample to find and identify apple defect. The results indicated the following points: (1) The value of red color component was decreased (162 - 73.4), (170.4 - 104.4), (210.8 - 98.4), and (202.6 - 113.1 values), and the value of green color component was decreased (148.6 - 73.5), (122.2 - 61.2), (181 - 62.4), and (180.1 - 90.3 values). Meanwhile, the blue color component value changed a little, it is ranged (61.6- 61.9), (61.1- 63.4), (61.4- 62.0), and (61.6- 62.7 values), for color, fungi, bruises and operation defects (which classified into four subclasses of each defect), respectively., (2) The value of red color component was decreased (134.6 - 84.4), (203 - 186.6), (143.8 - 98.4), and (202.8 - 174.9 values), and the value of green color component was decreased (100 - 75.2), (131.4 - 118.), (115.4 - 61.4), and (184.8 - 154.6 values), respectively. Meanwhile, the blue color component value changed a little, it is ranged (62.1- 66.8), (61.6- 62.0), (61.4- 63.4), and (62.4- 62.6 values) for insect, scare, mechanical and russet defects of apple fruit (which classified into three subclasses of each defect), respectively., (3) The value of color component (R,G and B) and color properties (H, S and I) were very important to classify defect of apple fruit., (4) Using of image analysis method in estimation of apple defects, to develop of a sorting system for sorting of apples fruit based on color analysis., and (5) Establishment measuring standard for defects of apple fruits according to image processing technique. | ||||
| References | ||||
|
Arman A., A. M. Motlagh, K.Mollazade and R.F.Teimourlou (2011 ). Recognition and localization of ripen tomato based on machine vision. Dep. of Agric. Mach. Eng., Agric. Fac., Urmia univ. AJCS 5(10):1144-1149.
Bock C.H., P.E. Parker, A.Z. Cook and T.R. Gottwald (2008). Characteristics of the perception of different severity measures of citrus canker and the relationships between the various symptom types. Plant Dis. 92: 927-939.
Bulanon D.M., T. Kataoka, Y. Ota and T. Hiroma (2002). A segmentation algorithm for the automatic recognition of fuji apples at Harvest. Biosist. Eng. 83(4):405-412.
Heinemann P.H., Z.A.Varghese, C.T.Morrow, H.J. Sommer, R.M.Crassweller (1995). Machine vision inspection of Golden Delicious apples. Appl. Eng. Agric. ASAE 11 (6):901–906.
Khojastehnazhand M., M. Omid and A. Tabatabaeefar (2009). Determination of orange volume and surface area using image processing technique. Int. Agrophy. 23: 237-242.
Kleynen, O., V. Leemans, and M. F. Destain (2003). Selection of the most efficient wavelenth bands for ‘Jonagold’ apple sorting. In: Postharvest Bio. and Tech., 30: 221-232.
Leemans V, Magein H. and Destain MF (1998). Defects segmentation on ‘Golden Delicious’ apples by using color machine vision. Comput. and Electron. in Agric., 20: 117-130.
Leemans V. and Destain M.-F. (2004). A real-time grading method of apples based on features extracted from defects. In: J. of Food Eng., 61:83-89.
Leila F., R.E.Hasan; M.T.Hadis, S. Navazolah and A. Heshmatolah (2012). Computer-based recognition of severity of apple blue mould using RGB components. Comput. Eng. Dep., Sharif Un. Techn., Tehran, Iran. Int. Res. J. of Appl. and Basic Sc. 3 (1):39-45.
Lorestani A.N., M. Omid, S.B. Shooraki, A.M. Borghei and A. Tabatabaeefar (2006). Design and evaluation of a Fuzzy Logic based decision support system for grading of Golden Delicious apples. Int. J. Agric. Biol. 8(4): 440-444.
Panli, H. E. (2012). Fruit surface defects detection and classification based on attention model. Sch. Info. Eng., Shenyang Univ., Shenyang, China. J. of Comput. Info. Sys. 8 (10): 4233–4240.
Penman, D.W. (2002). Determination of stem and calyx location on apples using automatic visual inspection. Comput. and Elect. in Agric., 33: 7–18
Schaare, P. N. and D. G. Fraser. (2000). Comparison of reflectance, Interactance and transmission modes of visible near infrared spectroscopy for measuring internal properties of kiwifruit (Actinidia chinensis). Postharvest Biology and Tech., : 175 – 184.
Throop, J.A., D.J. Aneshansley, W.C. Anger, and D.L. Peterson. (2005). Quality evaluation of apples based on surface defects: development of an automated inspection system. Postharvest Biology and Tech., 36:281–290.
Toth, D. and T. Aach. (2001). Improved minimum distance classification with Gaussian outlier detection for industrial inspection. In Proc. Int. Conf. Image Analy. and Proc., Palermo : 584 – 588. | ||||
|
Statistics Article View: 107 PDF Download: 149 |
||||
