Leaf area is important for estimating biomass productivity, adaptation to the environment, nutrition, and soil-water relations. It also plays an important role in determining the proper application rates of insecticides and fungicides. Image processing is considered one of the best methods for estimating the leaf area of a plant as it is inexpensive and saves time. In the image processing method, leaf area is calculated through pixel number statistics by counting the number of pixels in the leaf area region of digital images. In this study, a simple system based on image analysis using the ImageJ software application was developed to estimate cotton leaf area. Two hundred and forty Egyptian cotton (Giza 86) leaves were captured using a digital camera. These leaves were collected randomly from different heights and different fields at Kafer El-Dawar center, El-Behera
One of the new crop varieties that have been adopted for high yield is the Egyptian faba bean. However, poor-quality faba bean has reduced economic value. Quality evaluation is thus important and can be performed using computational intelligence. We developed a robust method based on morphological features and artificial neural network for quality grading and classification of Egyptian faba-bean seeds, covering five varieties: Giza3, Giza461, Misr1, Nobarya1, and Sakha1. Fifteen seed morphological features were then calculated, and artificial neural networks classified faba beans into different varieties. The results indicated an overall classification accuracy of 77.5% was achieved in training phase and it was 100% when testing dataset was used. The preliminary work presented in this paper could be further enhanced by real time faba beans identification by capturing seed morphological features through the help of digital images.
Cotton is considered as one of the most important crops in Egypt. Measuring the leaf area of such plant is one of the most accurate indicators to estimate the quantity of pesticides and productivity. Several research works have shown that deriving mathematical models as a method to estimate the leaf area of various plants is considered more precise, time-saving, cost-reducing and less harmful on the examined plants compared to direct methods of measuring leaf area such as digital planimeter, electronic devices and manual engineering measuring tools. In spite of all this developing mathematical models in the field of determining Egyptian cotton leaves area has not attained the least of research work. Therefore, the aim of the study is deriving a mathematical model suitable for predicting the area of cotton leaves. To achieve this aim, a mathematical model was developed using 240 Egyptian cotton leaves (Giza 86). These leaves were collected at random from different heights and different fields in Kafer El-Dawar centre, El-Behera Governorate, Egypt. Regression analysis has been used in developing 19 mathematical models to choose the best model for predicting leaf area through calculating statistical indicators that included: R 2 , root mean square error and mean absolute error. The selected models have been mathematically analyzed to obtain the regression constants of each model. Data analysis has shown that the best model is the one that determined the actual area of the leaf area. The outcome equation is as follows: Where (LA) is the leaf area (cm 2) and the rest of dimensions are measured in centimeters. The efficiency of this model has been tested by defining R 2 and comparing predicted leaf area results from the model with measured leaf area results. The results have shown that the developed model mentioned above is the most accurate model to be recommended in estimating Egyptian cotton leaves area from leaf width (W), main lobe length (L), right lobe length (L1) and left lobe length (L2). The developed regression model can be considered an alternative method to determine the Egyptian cotton leaves area instead of the direct method represented by for example the leaf area measuring instrument.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.