The fruit categorization according to their visual quality has recently experienced tremendous growth in the field of agriculture and food products. Due to post-harvest loses during handling and processing, there is an increasing demand for quality products in agro industry which requires accuracy to predict the fruit. Various techniques of machine learning have been successfully applied for classifying the fruit built on binary class. In this paper, machine leaning technique is used to automate the process of categorization and to improve the accuracy of different types of fruits by feature selection. To categorized images domain specific features such as color, shape and textual features are considered. Statistical color features are extracted from the image, bounding box feature for shape features and gray-level co-occurrence matrix (GLCM) is used to extract the textual feature of an image. These features are combined in a single feature fusion. A support vector machine (SVM) classification model is trained using training set features on fruit360 dataset which includes six fruit categories (classes) with two sub category (sub-classes) which builds multiclass classification task. We present one-vs-one coding design of Error correcting output codes (ECOC) and apply to SVM classifier; validation followed a fivefold cross validation strategy. The result shows that the textual features combined with color and shape feature improved fruit classification accuracy.
The research study aim to improve the performance of fruit quality by two approaches, first by applying kernel technique combined with specific classification method support vector machine (SVM) with error-correcting output codes for fruit categorization and then by cross validation. It is measured by analyzing the different mention kernel selection on color and shape features. Two coding design method such as one-vs.-one and one-vs.-all are examined with three commonly used kernel function linear, polynomial (cubic) and Radial Basis Function (Gaussian). The Experiment was conducted on fruit dataset created from fruit 360 dataset with six categories such as Apples, Avacados, Bananas, Cherrys, Grapes and lemons. The accuracy obtained for the fruit category with 98% accuracy was enhanced by the proposed method by the use of kernel technique selection resulted to 99%. However kernel choice highly depends on the parameter used for fruit categorization is introduced and discussed. The Experiments was carried out to find the best SVM kernel among linear, cubic and Gaussian for fruit categorization. The Experiment also focuses on evaluation process using cross validation methods kfold and hold out which resulted in a better accuracy for the classification model. The results show that the proposed method provides very stable and successful fruit classification performance over six categories of fruits. The coding design one-vs.-one performed better when compared to one-vs.-all with respect to accuracy and training speed.
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.