Design and construction of an automatic detection system for orange defects using an attunable lightness algorithm

Document Type : Research Article

Authors

1 Mechanics of Biosystems Engineering Department, Faculty of Agricultural Engineering and Rural Development, Agricultural Sciences and Natural Resources University of Khuzestan.

2 Assistant professor of Khuzestan Agricultural Sciences and Natural Resources University

Abstract

The automatic detection of defective fruit through the computer vision system continues to be a problem due to the uneven instability distribution on the citrus surface. As a result of the development of a system that is capable of detecting damage in citrus with high accuracy and speed is essential. Therefore, an adaptive lightness correction algorithm was implemented in this paper that simply overcomes the disturbance of the indirect distribution intensity in the fruit level in online and static conditions and avoids error detection. In the study, 200 specimens containing 50 healthy oranges and 150 defective oranges (Green Fruit Molds, Diaspididae, Alternaria Fruit and mechanical damage) were investigated. In this system, 4 images were taken from each sample and after applying the proposed algorithm, all four oranges were categorized into healthy and defective groups. Based on the results, it was found that the accuracy of the system for the damage of Green Fruit Molds, Diaspididae, Alternaria Fruit and mechanical damage was 87.80, 71.42, 74.28 and 100, indicating high performance of the proposed method.

Graphical Abstract

Design and construction of an automatic detection system for orange defects using an attunable lightness algorithm

Highlights

  • Using an adaptive lightness correction algorithm to overcome the interference of the distribution of indirect reflection intensity at the fruit surface and preventing error detection.
  • Design and manufacture of a separator to detect defects in orange.
  • On-line detection of Green Fruit Molds, Diaspididae, Alternaria Fruit and mechanical damage.
  • High detection accuracy of the sound and defective orange (96% and 84/67%, respectively).

Keywords

Main Subjects

References

 [1] Bennedsen, B.S., Peterson, D.L. (2005). Performance of a System for Apple Surface Defect Identification in Near-infrared Images. Biosyst. Eng., 90, 419–431.
[2] Aleixos, N., Blasco, J., Navarrón, F., Moltó, E. (2002). Multispectral inspection of citrus in real-time using machine vision and digital signal processors. Comput. Electron. Agric., 2, 121–137.
[3] Tao, Y. (1996). Spherical transform of fruit images for on-line defect extraction of mass objects. Opt. Eng., 35, 344–350.
[4] Li, J.B., Rao, X.Q., Wang, F.J., Wu, W., Ying, Y.B. (2013). Automatic detection of common surface defects on oranges using combined lighting transform and image ratio methods. Postharvest Biol. Tec., 82, 59–69.
[5] Kleynen, O., Leemans, V., Destain, M.F. (2005). Development of a multi-spectral vision system for the detection of defects on apples. INT. J. Food Eng., 69, 41–49.
[6] Gómez-Sanchis, J., Moltó, E., Camps-Valls, G., Gómez-Chova, L., Aleixos, N., Blasco, J. (2008). Automatic correction of the effects of the light source on spherical objects. An application to the analysis of hyperspectral images of citrus fruits. INT. J. Food Eng., 85, 191–200.
[7] Cubero, S., Aleixos, N., Moltó, E., Gómez-Sanchis, J., Blasco, J. (2011). Advances in machine vision applications for automatic in-spection and quality evaluation of fruits and vegetables. Food Bioprocess Tech., 4, 487–504.
[8] Lorente, D., Aleixos, N., Gómez-Sanchis, J., Cubero, S., García-Navarrete, O.L., Blasco, J. (2012). Recent advances and applications of hyperspectral imaging for fruit and vegetable quality assessment. Food Bioprocess Tech., 5, 1121–1142.
[9] Leemans, V., Destain, M.F. (2004). A real-time grading method of apples based on features extracted from defects. INT. J. Food Eng., 61, 83–89.
[10] Blasco, J., Aleixos, N., Gómez, J., Moltó, E. (2007). Citrus sorting by identification of the most common defects using multispectral computer vision. INT. J. Food Eng., 83, 384–393.
[11] Kim, D.G., Burks, T.F., Qin, J.W., Bulanonm, D.M. (2009). Classification of grapefruit peel diseases using colour texture feature analysis. Agric. Biol. Eng., 2, 41–50.
]12[ نداف‌زاده، م.؛ آبدانان مهدی‌زاده، س. (1395) تعیین زمان پخت سبزیجات با کمک پردازش تصاویر دیجیتال و اندازه‌گیری مختصات رنگی. فناوری نوین غذایی، جلد 3، شماره 11، ص 49-57.
 ]13[ اورک، ه.؛ آبدانان مهدی‌زاده، س. (1396) توسعۀ یک سامانۀ دقیق کنترل علفهای هرز برای زمینهای چمن به کمک بینایی ماشین. تحقیقات سامانه‌ها و مکانیزاسیون کشاورزی، جلد 19، شمار 70، ص 55-68.
[14] Ying, Y.B. (2000). Study on background segment and edge detection of fruit image using machine vision. J. Zhejiang. Univ-Sc A., 26, 35–38.
[15] Niphadkar, N.P., Burks, T.F., Qin, J., Ritenour, M. (2013). Edge effect compensation for citrus canker lesion detection due to light source variation—a hyperspectral imaging application. Agric. Eng. Int. CIGR J., 15, 314–327.
[16] Solomon, C., Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons.
[17] Throop, J.A., Aneshansley, D.J., Upchurch, B.L., Anger, B. (2001). Apple orientation on two conveyors: performance and predictability based on fruit shape characteristics. Trans. ASAE., 44, 99–109.
[18] López-García, F., Andreu-García, G., Blasco, J., Aleixos, N., Valiente, J.M. (2010). Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach. Comput. Electron. Agric., 71, 189-197.
[19] Zhang, B., Huang, W., Gong, L., Li, J., Zhao, C., Liu, C., Huang, D. (2015). Computer vision detection of defective apples using automatic lightness correction and weighted RVM classifier. INT. J. Food Eng., 146, 143-151.
Innovative Food Technologies
Volume 8, Issue 1
November 2020
Pages 13-28

Files

History

  • Receive Date: 01 March 2019
  • Revise Date: 13 April 2019
  • Accept Date: 13 January 2020

Share

How to cite

Statistics