Tomato Growth Stage Monitoring for Smart Farm Using Deep Transfer Learning with Machine Learning-based Maturity Grading

Abstract

The tomato farming industry needs to adopt new ideas in applying the technology for its growth monitoring and main. Machine vision and image processing techniques have become useful in the increasing need for quality inspection of fruits, particularly, tomatoes. This paper deals with the design and development of a computer-vision monitoring system to assess the growth of tomato plants in a chamber by detecting the presence of flowers and fruits. The system also provides maturity grading for the tomato fruit. Two pre-trained deep transfer learning models were used in the study for the detection of flowers and fruits, namely, the Regional-based Convolutional Neural Network (R-CNN) and the Single Shot Detector (SDD). Maturity classification of tomato fruits are implemented using the Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), and the Support Vector Machine (SVM). Evaluation results show that for the detection of flowers and fruits, the overall accuracy of the R-CNN is 1.67% for flower detection and 19.48% for the fruit detection while SSD registered 100% and 95.99% for flower and fruit detection respectively. In the machine learning for maturity grading, SVM produced the training-testing accuracy rate of 97.78%-99.81%, KNN with 93.78%-99.32%, and ANN with 91.33%-99.32%.

Definition and Application of a Computational Parameter for the Quantitative Production of Hydroponic Tomatoes Based on Artificial Neural Networks and Digital Image Processing

“…Zhao et al [14] showed that, combining the AdaBoost classifier and color analysis, tomatoes can be detected with a precision of 96%. With the Single Shot Detector, (SSD) the authors of Reference [40] showed a precision of 95.99% in the detection of tomatoes. Other works, like Mu et al [41], achieved a precision of 87.83% using faster R-CNN, also in tomatoes.…”

“…Other works in the literature, besides identification, use the count of objects as productivity parameter [4,14,[40][41][42][43]. As explained before, counting of objects is not a precise indicator for productivity, and that is one reason this works introduces the PI.…”

“…Most of the works in the literature focus on detecting objects and not on monitoring of objects, which is what this current paper is emphasizing. For monitoring, there are works that keep a register of the size of plants [20], controlling diseases [44], environmental control [11], tracking the count of flowers and tomatoes [40,45], and keeping a registry of the volume of tomatoes [46]. This last work of Fukui et al [46] is the closest to the current paper, and one important point to notice is that the authors of Reference [46] achieved good results in a controlled environment inside a laboratory, whereas, in outside environments, the results were not as expected.…”

IHDS: Intelligent Harvesting Decision System for Date Fruit Based on Maturity Stage Using Deep Learning and Computer Vision

“…They classified the Philippine coconut into three different maturity levels (pre-mature, mature, and over-mature) using random forest and support vector machine (SVM) classification systems. Another study has been done in 2020 by de Luna, R. G., E. P. Dadios, et al [17] to monitor the growth stage of tomatoes using SVM, ANN, and KNN, which achieved maximum accuracy levels of 99.81% for SVM, 99.32% for KNN, and 99.32% for ANN. Another research using MLK was introduced in 2020 by Harel, B., Y. Parmet, et al [11] to classify the maturity levels of sweet red and yellow peppers.…”

Dynamics of Certain Chemical Components in Tomato Fruit (Lycopersicon Eculentum Mill.) Maintained at Different Temperatures After Harvest

“…We must not overlook the favorable proportion of amino acids and organic acids found in tomato fruit, as well as the salts of magnesium, sodium, potassium and iron which are also found in an appropriate percentage for the proper functioning of the human body (Heuvelink, 2005). Local tomato varieties that have been maintained and perpetuated over the years are an important source of germplasm for tomato growers in certain areas (de Luna et al, 2020). In this paper, the behaviour of two local varieties of tomatoes from Cluj County, Romania was maintained at different temperatures after harvest, in terms of the dynamics of certain chemical components, given that some smaller local producers do not refrigerate tomatoes after harvesting, but keeps them in environmental conditions until capitalization.…”