Studies On Image-based Plant Leaf Parameter Measurement

Leaf is an important organ of plant photosynthesis and transpiration, a lot of information about plant growth conditions are inextricably linked with the leaf parameters. Mastering the law of growth of plant leaves, is of positive significance to guide the production, take technical measures of high quality and efficient cultivation. Effect of the leaf Parameters on the growth and development of plants and many other activities of life is profound, therefore, how to scientifically determine the leaf parameters is very meaningful. With the development of digital image processing technology and the leap of the computer's processing speed, it also has been more and more widely applied in agriculture. Compared with the traditional measurement techniques of the leaf parameters, the new technology has the advantages of fast measurement, high accuracy and real-time, can greatly improve the efficiency of the leaf-parameters measurement.Firstly, this paper introduces some basic image processing methods rel ated to the leaf image acquisition and preprocessing. Secondly, This paper simply introduces measuring method of some simple geometric parameter such as the leaf area, perimeter, long axis, short axis, it also introduces the calculation method of Invariant moments features and invariant texture descriptors. Thirdly, this paper focuses on studying the method of measurement of plant leaf axial length and proposes a measurement method of the leaf axis length, and introduces the detail process of measurement. Experiments show that this method proposed in this paper can automatically complete the central axis detection and calculation of the leaf length for these leaves which have the long petiole and are symmetrical, it can improve the measurement accuracy and reduce labor intensity. What's more, it is convenient to realize the automatic analysis and management for the related plants' information.This paper presents a quick way to remove the petiole,which binary is based on morphology. Mathematical morphological operations for binary images are of broad application areas. Unfortunately, when large binary images and large structural elements are involved, the computational speed of the morphological operations decreases. An improved morphological dilation algorit hm is proposed for large structural elements consisting of a single connected component and whose reference point being a member of the structural element. The contours of the binary image to be dilated are extracted, and are dilated using the structural e lement. The dilated contours are then combined with the original binary image through binary OR operation to give the final dilation result. The equivalence of the standard dilation and the improved algorithm is proved. Morphological erosion operation is i mproved utilized the duality between erosion and dilation, and morphological opening and closing are accelerated using the improved erosion and dilation. Standard operations and improved ones are compared on an image base consisting of 80 high resolution binary images of plant leaves. The experimental results show that the improved algorithms can significantly promote the execution speed of the morphological operations.This paper presents an improved method of skeleton extraction which based on an sequential refinement, it can effectively reduce repetitive operations in the sequential refinement process, and efficiently manage add, find and delete operations of the removal area point in refinement sequential process by the red-black tree structure, Thereby it improve the skeleton extraction speed and can achieve good response speed performance for larger binary image.Finally, this paper implements a plant leaf parameter measuring system for the parameter measurement method of plant leaf, in order to more in tuitively observe measurement of various leaf-parameters. The system is developed in the Microsoft Visual Studio 2010 platform, which is based on the MFC single document procedures and Microsoft Visual Studio 2008 framework, it also calls Open CV library to reduce the development time. And this paper briefly introduces the software method at the end.