Multiclass Apple Varieties Classification Using Machine Learning with Histogram of Oriented Gradient and Color Moments

Taner, Alper; Mengstu, Mahtem; Selvi, K.; Duran, Hüseyin; Kabaş, Önder; Gür, İbrahim; Karaköse, Tuğba; Gheorghiță, N. E.

doi:10.3390/app13137682

Cited by 10 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed system is evaluated based on its sensitivity (S), specificity (SP), and accuracy (AC). Equations (3)–(5) provide the mathematical expressions for S, SP, and AC, respectively [ 28 , 31 , 32 ]:

where TN represents true negatives, TP represents true positives, FN represents false negatives, and FP represents false positives.…”

Section: Dataset and Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Feature-Learning-Based PSO-PCA Feature Engineering Approach for Blood Cancer Classification

2023

View full text Add to dashboard Cite

Acute lymphoblastic leukemia (ALL) is a lethal blood cancer that is characterized by an abnormal increased number of immature lymphocytes in the blood or bone marrow. For effective treatment of ALL, early assessment of the disease is essential. Manual examination of stained blood smear images is current practice for initially screening ALL. This practice is time-consuming and error-prone. In order to effectively diagnose ALL, numerous deep-learning-based computer vision systems have been developed for detecting ALL in blood peripheral images (BPIs). Such systems extract a huge number of image features and use them to perform the classification task. The extracted features may contain irrelevant or redundant features that could reduce classification accuracy and increase the running time of the classifier. Feature selection is considered an effective tool to mitigate the curse of the dimensionality problem and alleviate its corresponding shortcomings. One of the most effective dimensionality-reduction tools is principal component analysis (PCA), which maps input features into an orthogonal space and extracts the features that convey the highest variability from the data. Other feature selection approaches utilize evolutionary computation (EC) to search the feature space and localize optimal features. To profit from both feature selection approaches in improving the classification performance of ALL, in this study, a new hybrid deep-learning-based feature engineering approach is proposed. The introduced approach integrates the powerful capability of PCA and particle swarm optimization (PSO) approaches in selecting informative features from BPI mages with the power of pre-trained CNNs of feature extraction. Image features are first extracted through the feature-transfer capability of the GoogleNet convolutional neural network (CNN). PCA is utilized to generate a feature set of the principal components that covers 95% of the variability in the data. In parallel, bio-inspired particle swarm optimization is used to search for the optimal image features. The PCA and PSO-derived feature sets are then integrated to develop a hybrid set of features that are then used to train a Bayesian-based optimized support vector machine (SVM) and subspace discriminant ensemble-learning (SDEL) classifiers. The obtained results show improved classification performance for the ML classifiers trained by the proposed hybrid feature set over the original PCA, PSO, and all extracted feature sets for ALL multi-class classification. The Bayesian-optimized SVM trained with the proposed hybrid PCA-PSO feature set achieves the highest classification accuracy of 97.4%. The classification performance of the proposed feature engineering approach competes with the state of the art.

show abstract

where TN represents true negatives, TP represents true positives, FN represents false negatives, and FP represents false positives.…”

Section: Dataset and Methodsmentioning

confidence: 99%

“…The proposed system is evaluated based on its sensitivity (S), specificity (SP), and accuracy (AC). Equations ( 3)-( 5) provide the mathematical expressions for S, SP, and AC, respectively [28,31,32]:…”

Section: Performance Metricsmentioning

confidence: 99%

Hybrid Feature-Learning-Based PSO-PCA Feature Engineering Approach for Blood Cancer Classification

2023

View full text Add to dashboard Cite

show abstract

“…In machine learning, algorithms are trained to find patterns and correlations in large data sets and make the best decisions and predictions based on this analysis [15]. Machine learning algorithms are one of the extremely popular methods applied to classification and regression problems in many fields, such as medicine [16,17], engineering [18,19], economy [20], education [21,22], business [23,24], natural sciences [25,26], sport sciences [27] and agriculture [28,29]. Alkali et al (2014) [30] utilized an artificial neural network (ANN) to predict some mechanical properties of melon fruit.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Leaf Break Resistance of Green and Dry Alfalfa Leaves by Machine Learning Methods

Ercan,

Kabas,

Moiceanu

2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Alfalfa holds an extremely significant place in animal nutrition when it comes to providing essential nutrients. The leaves of alfalfa specifically boast the highest nutritional value, containing a remarkable 70% of crude protein and an impressive 90% of essential vitamins. Due to this incredible nutritional profile, it becomes exceedingly important to ensure that the harvesting and threshing processes are executed with utmost care to minimize any potential loss of these invaluable nutrients present in the leaves. To minimize losses, it is essential to accurately determine the resistance of the leaves in both their green and dried forms. This study aimed to estimate the breaking resistance of green and dried alfalfa plants using machine learning methods. During the modeling phase, five different popular machine learning methods, Extra Trees (ET), Random Forest (RF), Gradient Boost (GB), Extreme Gradient Boosting (XGB), and CatBoost (CB), were used. The correlation coefficient (R2), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) metrics were used to evaluate the models. The obtained metric results and the graphs obtained from the prediction values of the models revealed that the machine learning methods made successful predictions. The best R2 (0.9853), RMSE (0.0171), MAE (0.0099) and MAPE (0.0969) values for the dry alfalfa plant were obtained from the model established with the ET method, while the best RMSE (0.0616) and R2 (0.96) values for the green alfalfa plant were obtained from the model established with the RF method and the best MAE (0.0340) value was obtained from the model established with the ET method. Additionally, the best MAPE (0.1447) value was obtained from the model established with the GB method.

show abstract

“…In traditional machine learning, extracting features before training models on these features is required. Thus, the quality of the extracted features has a significant impact on a given classifier [7]. Deep learning has gained much popularity in image recognition and classification tasks of fruits and vegetables, as computing power and algorithms to process big data are emerging [8].…”

Section: Introductionmentioning

confidence: 99%

Apple Varieties Classification Using Deep Features and Machine Learning

Taner,

Mengstu,

Selvi

et al. 2024

Agriculture

Self Cite

View full text Add to dashboard Cite

Having the advantages of speed, suitability and high accuracy, computer vision has been effectively utilized as a non-destructive approach to automatically recognize and classify fruits and vegetables, to meet the increased demand for food quality-sensing devices. Primarily, this study focused on classifying apple varieties using machine learning techniques. Firstly, to discern how different convolutional neural network (CNN) architectures handle different apple varieties, transfer learning approaches, using popular seven CNN architectures (VGG16, VGG19, InceptionV3, MobileNet, Xception, ResNet150V2 and DenseNet201), were adopted, taking advantage of the pre-trained models, and it was found that DenseNet201 had the highest (97.48%) classification accuracy. Secondly, using the DenseNet201, deep features were extracted and traditional Machine Learning (ML) models: support vector machine (SVM), multi-layer perceptron (MLP), random forest classifier (RFC) and K-nearest neighbor (KNN) were trained. It was observed that the classification accuracies were significantly improved and the best classification performance of 98.28% was obtained using SVM algorithms. Finally, the effect of dimensionality reduction in classification performance, deep features, principal component analysis (PCA) and ML models was investigated. MLP achieved an accuracy of 99.77%, outperforming SVM (99.08%), RFC (99.54%) and KNN (91.63%). Based on the performance measurement values obtained, our study achieved success in classifying apple varieties. Further investigation is needed to broaden the scope and usability of this technique, for an increased number of varieties, by increasing the size of the training data and the number of apple varieties.

show abstract

Multiclass Apple Varieties Classification Using Machine Learning with Histogram of Oriented Gradient and Color Moments

Cited by 10 publications

References 31 publications

Hybrid Feature-Learning-Based PSO-PCA Feature Engineering Approach for Blood Cancer Classification

Hybrid Feature-Learning-Based PSO-PCA Feature Engineering Approach for Blood Cancer Classification

Prediction of Leaf Break Resistance of Green and Dry Alfalfa Leaves by Machine Learning Methods

Apple Varieties Classification Using Deep Features and Machine Learning

Contact Info

Product

Resources

About