Multiclass Apple Varieties Classification Using Machine Learning with Histogram of Oriented Gradient and Color Moments
نویسندگان
چکیده
It is critically necessary to maximize the efficiency of agricultural methods while concurrently reducing cost production. Varieties, types, and fruit classification grades are crucial High expenditure, inconsistent subjectivity, tedious labor characterize traditional manual varieties classification. This study developed machine learning (ML) models classify ten apple varieties, extracting histogram oriented gradient (HOG) color moments from RGB images. Support vector (SVM), random forest classifier (RFC), multilayer perceptron (MLP), K-nearest neighbor (KNN) were trained with 10-fold stratified cross-validation (Skfold) by using textural features, a GridSearch was implemented fine-tune hyperparameters. The models, SVM, RFC, MLP, KNN tested separate test data performed well, having an accuracy 98.17%, 96.67%, 98.62%, 91.28%, respectively. Having top results, MLP SVM demonstrated potential applying HOG train ML for classifying varieties. suggests conducting further research thoroughly examine additional image features determine impact combining utilizing different classifiers.
منابع مشابه
Plant Leaf Recognition and Classification using Zernike Moments (ZM) and Histogram of Oriented Gradients (HOG)
A method using Zernike Moments (ZM) and Histogram of Oriented Gradients (HOG) for classification and recognition of plant leaf images is proposed in this paper. After preprocessing, we compute the shape features of a leaf using Zernike Moments (ZM) and texture features using Histogram of Oriented Gradients (HOG) and then Support Vector Machine (SVM) classifier is used for plant leaf image class...
متن کاملVisual Tracking using Learning Histogram of Oriented Gradients by SVM on Mobile Robot
The intelligence of a mobile robot is highly dependent on its vision. The main objective of an intelligent mobile robot is in its ability to the online image processing, object detection, and especially visual tracking which is a complex task in stochastic environments. Tracking algorithms suffer from sequence challenges such as illumination variation, occlusion, and background clutter, so an a...
متن کاملEfficient Seizure Classification using Multiclass Support Vector Machine with RFE
A new multi classification scheme based on Support Vector Machine called Hierarchical multi-class support vector machine with a new Extreme Learning Machine kernel is introduced. The Recursive Feature Elimination (RFE) is used for ranking the features. Wavelets Transform based features such as Statistical Values, and Approximate Entropy have been used for the encephalogram signal classification...
متن کاملActivity Recognition Using Histogram of Oriented Gradient Pattern History
Human activity recognition is an important task in computer vision because it has many application areas such as, healthcare, security, entertainment, and tactical scenarios. This paper presents a methodology to automatically recognize human activity from input video stream using Histogram of Oriented Gradient Pattern History (HOGPH) features and SVM classifier. For this purpose, the proposed s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied sciences
سال: 2023
ISSN: ['2076-3417']
DOI: https://doi.org/10.3390/app13137682