Image Based Estimation of Fruit Phytopathogenic Lesions Area

Measuring Surface and Volume of a Spheroid-Shaped 3D Object from a Single Image

“…A number of pre-processing tasks are performed to identify and evaluate the object and sub-region of interest. The initial step is to identify the calibration marks, which are used to compute an estimate of the average image resolution at the calibration plane ( R 0 in pixel/mm) [8]. The largest object inside the rectangular region defined by the 4 marks is identified as the object of interest [8].…”

“…The initial step is to identify the calibration marks, which are used to compute an estimate of the average image resolution at the calibration plane ( R 0 in pixel/mm) [8]. The largest object inside the rectangular region defined by the 4 marks is identified as the object of interest [8]. Morphological operations are then used to remove holes and adjust an ellipse to the imaged object.…”

“…Once the spheroid is defined, the x, y coordinates of each pixel in the 2D object are used to compute: z(x, y) and the height H(x, y) above the reference plane (4); the image resolution R(x, y) at the pixel height (2); the pixel size (x, y) = 1∕R(x, y) ; and the surface area A(x, y) (5)(6)(7)(8)(9). Three auxiliary images are thus created -H(x, y), R(x, y) and A(x, y), such as the example presented in Fig.…”

“…The computation of the mark area depends on a number of factors, besides the imaging geometry, such as the image resolution and the segmentation process. An evaluation of the magnitude of the error due to these factors was carried out [8], placing the colour mark on the calibration plane itself, for similar conditions as used here (camera 1). The maximum expected error due to the limited image resolution was estimated to be between about 2.5% (mark 1, A5 target) and 5.5% (mark 2, A4 target) [8].…”

“…Also of considerable interest is the evaluation of the surface area of a sub-region or spot on a fruit. As an example, the presumptive diagnosis of a number of walnut diseases, which affect severely the walnut production worldwide [10], can be made by the observation of symptomatic lesions characterized by necrotic spots or patches on walnut leaves and fruits [8], with regular quantitative measurements required to analyze the temporal evolution of the lesions. The motivation for this work is the development of an easy-to-use and low-cost system to support the detection and evaluation of lesions in walnuts, within the EVOXANT project -Evolution of Xanthomonas arboricola species complex beyond culturability.…”