Fruits are an excellent source of nutrients and minerals. They have a high concentration of antioxidants and flavonoids, which are beneficial to one's health. Pomegranates have a high potential in preventing cell damage, boosting our immunity, helping with smooth digestion, fighting type-2 diabetes, keeping vital parameters in check and are seen to be effective inthe prevention of cancers. India is considered the largest producer of excellent varieties of pomegranates and thus the quality analysis in the export operation of pomegranates is highly concerned. Grading of pomegranates is very necessary for post-harvest management and is performed based on the external appearance like attractive colours, texture, size and shape which decides the standard of the fruit. Manual grading can be done which requires human operation and consumes more time. Hence quality assessment of pomegranates can be done using Machine Learning(ML) which is highly efficient. The process of feature extraction yields accurate results and can be done quickly. ML technology improves accuracy and efficiency and has improved user experience. The review paper proposes an efficient ML approach for pomegranate quality analysis using Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) feature extraction methods. K-Nearest Neighbour (KNN) and Naive Bayes (NB) algorithms are implemented in the designed model using both sets of feature extractors and the result illustrates that the LBP + NB model performs with better efficiency and greater accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pomegranate Quality Analysis and Classification Using Feature Extraction and Machine Learning


    Contributors:


    Publication date :

    2022-12-01


    Size :

    1262978 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Feature Extraction and Classification from Planetary Science Datasets enabled by Machine Learning

    Nixon, Conor A. / Yahn, Zachary / Duncan, Ethan et al. | IEEE | 2023



    Page Segmentation and Classification Using Fast Feature Extraction and Connectivity Analysis

    Sauvola, J. / Pietikaeinen, M. | British Library Conference Proceedings | 1995



    Classification of Particulate Matter (PM2.5) Concentrations Using Feature Selection and Machine Learning Strategies

    Matara Caroline Mongina / Nyambane Simpson Osano / Yusuf Amir Okeyo et al. | DOAJ | 2024

    Free access