دانلود رایگان مقاله انگلیسی بررسی تکنیک های پردازش تصویر برای استخراج و تقسیم بندی گیاه های اراضی - الزویر 2016

abstract

In this review, we present a comprehensive and critical survey on image-based plant segmentation techniques. In this context, ‘‘segmentation” refers to the process of classifying an image into plant and nonplant pixels. Good performance in this process is crucial for further analysis of the plant such as plant classification (i.e. identifying the plant as either crop or weed), and effective action based on this analysis, e.g. precision application of herbicides in smart agriculture applications. The survey briefly discusses pre-processing of images, before focusing on segmentation. The segmentation stage involves the segmentation of plant against the background (identifying plant from a background of soil and other residues). Three primary plant extraction algorithms, namely, (i) colour index-based segmentation, (ii) threshold-based segmentation, (iii) learning-based segmentation are discussed. Based on its prevalence in the literature, this review focuses in particular on colour index-based approaches. Therefore, a detailed discussion of the segmentation performance of colour index-based approaches is presented, based on studies from the literature conducted in the recent past, particularly from 2008 to 2015. Finally, we identify the challenges and some opportunities for future developments in this space.

6. Discussion and conclusions

According to some of the studies considered above, colour index-based methods have some limitations: they may result in over-segmentation (excessive green) in one application and under-segmentation in another application, especially when a single index is applied by itself. This varies considerably with imaging conditions, and the fact that the same test data are not used in all studies makes direct comparison more difficult. Few comparative studies have been carried out using a common set of test data. One somewhat recent example was carried out by Meyer and Camargo-Neto (2008), to compare three green indices, namely, ExGR, ExG, and NDI. However, colour index-based methods have both advantages and disadvantages that can be summarised as follows:

Advantages:

 Simple methods that are easy to understand and implement.

 Easy to modify their formulas to create a new colour index.

 Generally do not require training.

 Generally require low computation which makes them suitable for real time use.

 They are effective in normal condition where the light is neither very high nor very low.

 Some of the colour index-based methods have shown results that are comparable to other more sophisticated methods e.g. see study by Bai et al. (2013).