The paper presents MNPDenseNet, an automated model for detecting monkeypox using deep feature engineering and multiple nested patch division. The authors created a new dataset of 910 open-source images classified into five categories: healthy, monkeypox, chickenpox, smallpox, and zoster zona. The proposed model includes multiple nested patch division, deep feature extraction using pre-trained DenseNet201, feature selection with NCA, Chi2, and ReliefF selectors, classification using SVM with 10-fold cross-validation, majority voting, and a greedy algorithm for selecting the best result. The model achieved a classification accuracy of 91.87% on the collected dataset, outperforming other CNN models such as AlexNet, MobileNetv2, DarkNet53, and ResNet50. The study highlights the effectiveness of the proposed model in detecting monkeypox from skin images, with potential applications in real-time detection and medical assistance.The paper presents MNPDenseNet, an automated model for detecting monkeypox using deep feature engineering and multiple nested patch division. The authors created a new dataset of 910 open-source images classified into five categories: healthy, monkeypox, chickenpox, smallpox, and zoster zona. The proposed model includes multiple nested patch division, deep feature extraction using pre-trained DenseNet201, feature selection with NCA, Chi2, and ReliefF selectors, classification using SVM with 10-fold cross-validation, majority voting, and a greedy algorithm for selecting the best result. The model achieved a classification accuracy of 91.87% on the collected dataset, outperforming other CNN models such as AlexNet, MobileNetv2, DarkNet53, and ResNet50. The study highlights the effectiveness of the proposed model in detecting monkeypox from skin images, with potential applications in real-time detection and medical assistance.