A Deformation Measurement for Withered Plant Leaf Based on Vision

Abstract:

If plants absorb too little water and the cells in plant leaves is not full, there might exist atrophy characteristic distortion of the cell concentration of leaf and leaf morphological characteristic. Traditional algorithm carries out deformation measurement for withered leaf based on cell concentration characteristics and leaf morphological characteristics. Once the character distorted, characteristic parameters of leaf cell sap will be inaccurate reducing the measurement accuracy for withered leaf deformation. Therefore, we propose a computer vision-based plant leaves wilt deformation measurement method. The experimental results show that this algorithm significantly improves the accuracy of the measurement.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 770-773
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.770
• Online since: November 2013
• Authors: Zhong Yi Hu*
• Keywords: Plant Leaves, Wither Region Pixels, Withered Deformation Measurement

References

[1] J. Koenderink. The Structure of Images[J]. Biological Cybernetics, 1984, pp.363-396.

[2] D. Lowe. Object Recognition from Local Scale-Invariant Features[C]. International Conference onComputer Vision, 1999, pp.1150-1157.

[3] D. Lowe. Distictive Image Features from Scale-Invariant Keypoints[J]. International Journal of ComputerVision, 2004, 60(2): pp.91-110.

[4] C. Fish. A Random Sample Consensus: A Paradigm Formodel Fitting with Application to Image Analysis and Automated Cartography[J]. Communication AssociationMachine, 1981, 24(6): pp.381-395.

DOI: 10.1145/358669.358692

[5] P. Smith, D. Sinclair, R. Cipora and K. Cood. Effective Corner Matching[C]. British Machine VisionConference, 1998, pp.545-556.