Machinery analysis can be very fruitful in agricultural field, as defect prophecy can be done in earlier stages of fruit maturity which can help farmers in taking necessary steps. Even there are some seasonal fruits which are sorted in nonuniform manner (in refer to fruit maturity). So, computerized analysis can help in detecting: accuracy of fruit maturity, defect, quality level and even predictions of a harvest can be made. Increase in machine learning can also increase consumer choices and preferences as well as help farmers in saving time and money. This paper provides the detailed overview of various methodologies used for fruit analysis, like surface color method and feature selection, in which few supplementary models are being used for example: RGB color model with HSI model and many more. At last, in this paper, we will conclude some better methods with algorithms than can show better results.
CITATION STYLE
Tulli, S., & Yogesh. (2023). Application of Machine Learning for Analysis of Fruit Defect: A Review. In Lecture Notes in Electrical Engineering (Vol. 968, pp. 527–537). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-7346-8_45
Mendeley helps you to discover research relevant for your work.