COLOR IMAGE ANALYSIS FOR DETERMINING HARVEST TIME OF BEAN AND PEA PODS

El-Raie, A.E.; Bader, Y.A.; Hassan, H.E.; Khamis, R.

doi:10.21608/mjae.2012.102607

COLOR IMAGE ANALYSIS FOR DETERMINING HARVEST TIME OF BEAN AND PEA PODS

Document Type : Original Article

Authors

¹ Prof. Dr., Agric. Eng. Dep., Fac. of Ageic., Cairo Univ., Egypt.

² Prof. Dr., Nat. Inst. of Laser Enhanced Sc., Cairo Univ., Egypt.

³ Assoc. Prof., Nat. Inst. of Laser Enhanced Sc., Cairo Univ., Egypt.

⁴ Res., Agric. Eng. Res. Inst, Agric. Res Center, Dokki, Egypt.

10.21608/mjae.2012.102607

Abstract

The main objectives of this research are to study color image analysis for determining the optimal harvest time of green beans (Phaseolus vulgaris L. var Paulista) and green peas (Pisum Sativum L. var Sugar Lays) depending on maturity, and creating the color standards at different ages. Obtained results are summarized as follows: 1) The percentages of color components increased for read (R), green (G) and blue (B) from 29.0% to 60.4%, from 44.3% to 76.5%, and from 15.3% to 49.0% for pod ages from 10 to 31 days, respectively. Meanwhile, the values for sweet pea pods increased from 26.67% to 51.76%, from 41.18% to 61.57%, and from 15.29% to 29.80% for pod ages from 6 to 33 days, respectively. 2) The relationships between red color (R), green color (G) and blue color (B) as functions of the pod age (A) resulted as follows:
R = 39.490 + 3.909A, G = 78.203 + 3.755 A, and B = 3.826 A - 1.063 (green bean pods)
R = 52.767 + 2.423A, G = 96.462 + 1.817 A, and B = 34.027 + 1.080 A (sweet peas pods)
3) According to this study, the criteria as a standard for quality depending on the color to determine the optimal harvest time appeared about 22 and18 days for green bean and pea pods (from appearing the pod from its flower) were 34.12% (R), 43.04%(G) and 22.83% (B) for bean, while they were 33.45% (R), 45.99% (G) and 20.56%(B)for peas.

Keywords

Main Subjects

Processing Engineering of Agricultural Products

References

Choi, K.; G. Lee; Y. J. Han and J. M. Bunn. 1995. Tomato maturity evaluation using color image analysis. Trans. ASAE. 38(1): 171-176.

Helmy M. A., A. A. AbdEl-Rahman and H. E. Hassan 2003. Classification of tomato fruits using color image analysis technique. Misr J. of Agric. Eng., 20(3): 597 – 608.

Hutchings, J. B. 1999. Food color and appearance, a Chapman and Hill, Food Sc. B., Inst. Physics, UK, Gaithersburg, Maryland 2 ^nd., Aspen Publ. Inc. : 171-172.

Laykin, S.; V. Alchanatis; E. Fallik and Y. Edan. 2002.Image processing algorithms for tomato classification. Trans. ASAE. 45(3): 851–858.

Mayer, G. E. and D. A. Davison. 1987. An electronic image plant growth measurement system. Trans. ASAE 30(1): 242-248.

Ng, H. F.; W. F. Wilcke; R. V. Morey and J. P. Lang. 1998. Machine vision color calibration in assessing corn kernel damage. Trans. of the ASAE. Vol. 41(3): 727-732.

Ounasekaran, P. and O. Paulsen. 1986. Performance evaluation of the four classes of textural features. Pattern recognition 25: 829-833.

Robert, A.; N. John and K. Karry. 2004. Agricultural, Remote Sensing basics, NDSU Ext. Servi., and North Dakota State Univ., Fargo, North Dakota 58105: 1-4.

The Color Management Company. 2000. Components of the color perception. The visual observing situation. Tech. Servi. Dep., Hunter Assoc. Lab., Inc. Virginia, USA, 12 (5): 1-8.

Whiteman, T. A. 1999. Additive color process (RGB). The magazine of the Graphic Arts Technical Foundation, No. 53, 2 ^nd S.: 1-4.