Image processing and prediction of leaf area in cereals: A comparison of artificial neural networks, an adaptive neuro‐fuzzy inference system, and regression methods

Abstract

In this study, the leaf area was estimated by different regression models and new methods of image processing by using artificial intelligence (AI) in bread (Triticum aestivum L.) and durum wheat (Triticum durum L.) and triticale (×Tritosecale Wittm. ex A. Camus) at seedling, booting, and milk development stages. Data on leaf traits in 1,000 plants of breed wheat, triticale, and durum wheat were studied. Among regression models using general data, LA = + √ , LA = + (), and LA = + (∕) models had a R 2 > 90% for all three cultivars (L and W represented length and width of leaves). For wheat bread, models + () and √ × () exhibited a good estimate of the leaf area at all stages of growth, whereas in triticale, the linear models that used the product of √ × and √ were more suitable to estimate leaf areas in booting and milk development. The multilayer perceptron (MLP) neural network modeling indicated that the 'trainlm,' 'trainlm,' and 'traincgb' algorithms with an optimal structure of 2-10-1, 2-3-1, and 2-10-1 had the least amount of the mean square error for bread wheat, triticale, and durum wheat, respectively, for each of the growth stages. Furthermore, based on the adaptive neuro-fuzzy inference system (ANFIS) method, a very accurate estimate of the leaf area was obtained for each of the growth stages. The comparison of different models in the leaf area estimation showed that unlike estimating leaf area by regression, AI-based methods did not depend on plant growth stages. In this study, we suggested the utilization of image processing and artificial intelligence in leaf area estimation. It will accelerate leaf area measurement in the field, by extending these methods and transferring it into smartphone applications.

Application of image processing and soft computing strategies for non-destructive estimation of plum leaf area

“…The ANFIS model was the most accurate LA estimator in the study’s performance criteria. This finding is consistent with Sabouri and Sajadi’s [ 38 ] findings, who reported that the ANFIS was more accurate than ANN and regression methods for estimating the LA of wheat and triticale leaves. Comparison of the selected models derived from each genotype with the final model (achieved by pooling all genotypes data) proved that the developed models accommodated the effect of changes in leaf shape between genotypes and could be used for other genotypes of plum with considerable accuracy.…”

“…Shastry and Sanjay [ 37 ] describe the fundamental concept and architecture of ANFIS, as well as some of the applications of ANFIS in agriculture. Sabouri and Sajadi [ 38 ] demonstrated the efficacy of using ANFIS and ANN modeling to predict the LA of bread wheat, durum wheat, and triticale plants using image-extracted L and W dimension values. Additionally, ANFIS was successfully used to predict LA plant species using leaf L, leaf W, plant type, and a specific coefficient defined for each plant with an R 2 = 0.997.…”

Leaf Area Prediction of Pennywort Plants Grown in a Plant Factory Using Image Processing and an Artificial Neural Network

“…Studies [64,65] utilized ANNs with architectures like 2-50-1 and 2-3-1, achieving accuracy rates of 99.99% and high correlation (>0.98) for estimating leaf area in various plant species, including wheat, triticale, durum, and sesame. Another study [66] compared methods like ANN, adaptive neurofuzzy inference system, and regression, reporting accuracy ranges of 97-99% for cereals. Additionally, the study [67] assessed basic ANN, ANFIS, and regression methods, affirming the potential of ANNs in precise leaf area estimation based on leaf characteristics.…”

Leaf area estimation based on ANFIS using embedded system and PV panel

“…As one such method, an Adaptive Neuro-Fuzzy Inference System (ANFIS) is a machine learning technique that combines the learning capabilities of artificial neural networks and fuzzy logic systems for classification and modeling [ 22 ]. It was reported that [ 23 ] ANFIS and ANN modeling can be effectively used to predict leaf area in bread wheat species, and ANFIS achieved successful leaf area prediction using specific coefficients related to leaves with an accuracy of R 2 = 0.997 [ 24 ]. A tool was developed [ 25 ] to determine leaf area using a PV panel as a sensor, a wooden enclosure to protect it from the external environment, a flashlight as a light source, and a commercial digital multimeter for voltage measurements.…”