Review on the proceeding of automatic seedlings classification by computer vision

Abstract

The classification of seedlings is important to ensure the viability of seedlings after transplantation and is acknowledged as a key factor in forestation and environmental improvement. Based on numerous papers on automatic seedling classification (ASC), the seedling grading theory, traditional grading methods, the background and the proceeding of ASC techniques are described. The automation of the measurement of seedling morphological characteristics by photoelectric meters and computer vision is studied, and the automatic methods of the current grading systems are described respectively. And the further researches on ASC by computer vision are proposed.

Keywords

Seedlings classification / Automation / Morphological characteristic / Computer vision / S753.1 / A

References

[1] Ardalan S.H., Hassan A.E. Automatic feeding and sorting of bare root seedlings [J]. Transactions of the ASEA, 1982, 25(2): 266-270.

[2] Jingfeng Bai, Xuezeng Zhao, Xifu Qiang et al. Study on extraction of computer vision features of conifer seedling [J]. Journal of Northeast Forestry University, 2000, 28(5): 94-96.

[3] Jingfeng Bai, Xuezeng Zhao, Xifu Qiang et al. Study on the automatic grading system of conifer seedling [J]. Forestry Machinery and Woodworking Equipment, 2000, 28(8): 9-11.

[4] Jingfeng Bai, Xuezeng Zhao, Xifu Qiang et al. Edge detection based on fuzzy gradient method [J]. Control and Decision, 2001, 16(3): 351-354.

[5] Bukley D.J., Rerd W.S., Armson K.A. A digital recording system for measuring root area and dimensions of tree seedling [J]. Transactions of the ASAN, 1978, 21(2): 222-226.

[6] Gasvoda, D. 1994. Machine vision computerized sorting and grading system for tree seedling [R]. Timber tech tips, Missoula Technology Development Center, USDA Forest Service.

[7] Junfeng Guo, Yuanlong Cai Study on 3D image reconstruction basing on morphology interpolation [J]. Journal of Xi’an JiaoTong University, 1994, 28(2): 109-114.

[8] Hassan A.E., Tohinaz A.S., Roise J.P. Evaluation of manual sorting in three pine nurseries [J]. Transactions of the ASAE, 1992, 35(6): 1981-1986.

[9] Howarth M.S., Stanwood P.C. Measurement of seedling growth rate by machine vision [C] Optics in Agriculture, Forestry, and Biological Processing, Proceedings of SPIE, 1992, 1836: 185-194.

[10] Chang Joongho, Han Gunhee, Valverde J.M. Cork quality classification system using a unified image processing and fuzzy-neural network methodology [J]. Transactions on Neural Networks, 1997, 8(4): 964-973.

[11] Kutz L.J., Wlihoit J.H., Fly D.E. Multiple camera machine vision system for pine seedlings measurements [R], 1993 St. Joseph, MI 49085: ASAE

[12] Lebowitz R.J. Digital analysis measurement of root length and diameter [J]. Environmental and Experimental Botany, 1988, 28(3): 267-273.

[13] Qingzhong Li, Man Zhang, Maohua Wang Real-time apple color grading based genetic neural network [J]. Journal of Image and Graphics, 2000, 5(9): 779-789.

[14] Zhexing Liu, Shuxiang Li, Qingwen Lu A directional interpolation method for 3D gray-scale image based on local plane information [J]. Beijing Biomedical Engineering, 1999, 18(4): 216-220.

[15] Ringey M.P., Kranzler G.A. “Performance of a machine vision based tree seedling grader” [R], 1989 St. Joseph, MI 49085: ASAE

[16] Miller B.K., Delwiche M.J. A color vision system for peach grading [J]. Tranaction of the ASAE, 1989, 32(4): 1484-1490.

[17] Morrison, I.K., Armson, K.A. 1968. The rhizometer-adevice for measuring roots of tree seedling [C]. The Forestry Chroaide, 21–23.

[18] Neuman M.R., Sapirstein H.D., Shwedyk E. et al. Wheat grain color analysis by digital image processing [J]. Wheat Class Discrimantion. Journal of Cereal Science, 1989, 10: 183-188.

[19] Ringey M.P., Kranzler G.A. Neural network recognition of the conifer seedling root collar [C] Optics in Agriculture and Forestry, Proceedings of SPIE, 1997, 2907: 109-118.

[20] Ringey M.P., Kranzler G.A. Machine vision for grading southern pine seedlings [J]. Transactions of the ASAN, 1988, 31(2): 642-646.

[21] Ringey M.P., Kranzler G.A. Line-scan inspection of conifer seedlings [C] Optics in Agriculture and Forestry, Proceedings of SPIE, 1992, 1836: 166-174.

[22] Ringey M.P., Kranzler G.A. Machine vision for measuring conifer seedlings morphology [C] Optics in Agriculture, Forestry, and Biological Processing, Proceedings of SPIE, 1994, 2345: 26-35.

[23] Ruzhitsky, V., Ling, P. P. 1992. Image analysis for tomato seedling grading [R]. ASAE Paper No. 92-3588, St. Joseph, MI.

[24] Schubert Erhard, Rath H., Juergen Klicker Fast 3D object recognition using a combination of color-coded phase-shift principle and color-coded triangulation [C] Proceedings of SPIE—The International Society for Optical Engineering, 1994, 2247: 202-213.

[25] Suh, S.R., Miles, G.E. 1988. Measurement of morphological properties of tree seedlings using machine vision and image processing [R]. ASAE Paper No. 88-1542, St. Joseph, MI.

[26] Tao Y., Heinemann P.H., Varghese Z. et al. Machine vision for color inspection of potatoes and apples [J]. Tranaction of the ASAE, 1995, 38(5): 1555-1561.

[27] Wilhot J.H., Kutz L.J., Fly D.E., South D.B. PC-based multiple camera machine vision systems for pine seedling measurement [J]. Applied Engineering in Agriculture, 1994, 34(4): 48-52.

[28] Wilhot J.H., Kutz L.J., Vandiver W.A. Machine vision system for quality control assessment of bare root pine seedlings [C] Optics in Agriculture, Forestry, and Biological Processing, Proceedings of SPIE, 1994, 2345: 36-49.

[29] Woebbecke D.M., Meyer G.E., Bargen K.V. Plant species identification, size, and enumeration using machine vision techniques on near-binary images [J]. Optics in Agriculture and Forestry, 1992, 1836: 208-218.

[30] Xian Wu, jingfeng Bai, Balan Lin et al. System of automatic grading of conifer seedling by computer vision [J]. Journal of Northeast Forestry University, 1998, 26(4): 32-35.

[31] Jian Zhou, Mingtao Zhao, Yuxiao Yang Study on the multiscale binary-wavelet based edge detection for layer-by-layer 3D profilometry image [J]. China Mechanical Engineering, 1999, 10(11): 1242-1246.