Evaluating VGG16 and Mobilenetv2 for Automatic Recognition of Art Periods Using Transfer Learning (Published)
Artificial intelligence offers new ways to organize and share cultural heritage collections. This paper evaluates its potential for automatically classifying paintings by art period, as a tool for the digitization and accessibility of art-related information. Two convolutional neural network (CNN) models, VGG16 and MobileNetV2, were adapted through transfer learning from ImageNet-pretrained weights and trained on the WikiArt dataset, which contains 81,444 paintings across 27 art periods. Class imbalance was addressed with data augmentation and class weights, and the data were split into stratified training, validation and test sets (70/15/15). VGG16 achieved the best performance, with an AUC of 0.966, an accuracy of 0.763 and an F1-score of 0.701, compared with 0.946, 0.703 and 0.699 for MobileNetV2. MobileNetV2, however, trained faster and used less memory. The results reveal a trade-off between accuracy and efficiency that can guide the choice of model for galleries, museums and educational platforms.
Keywords: Computer Vision, MobileNetV2, VGG16, art period classification, convolutional neural networks, transfer learning
Leveraging Transfer Learning Across Industrial and Medical Anomaly Domains: From Aircraft Fuselage Defect Detection to Chest X-ray Abnormality Identification (Published)
Transfer learning (TL) enables knowledge learned in one domain to improve performance in another related domain; however, its application to industrial and medical anomaly detection (AD) is often limited by domain discrepancies and scarce labeled data. This research addresses these challenges by bridging Aircraft Fuselage Defect Detection (AFDD) and Chest X-ray (CXR) Abnormality Identification through cross-domain TL, enabling effective feature generalization between industrial and medical imaging tasks. Publicly available aircraft inspection images and CXR datasets are used to ensure diversity and representative anomalies. Data pre-processing incorporates adaptive histogram equalization (AHE) for contrast enhancement and median filtering (MF) to reduce noise, followed by image normalization to standardize input dimensions. For robust feature representation, Gray-Level Co-occurrence Matrix (GLCM) and Histogram of Oriented Gradients (HOG) are employed to capture complementary structural and texture information. The proposed Dynamic Grey Wolf Optimizer-driven Deep Convolutional Transform Network (DGWO-DCTN) integrates preprocessing, feature extraction, and AD into a unified framework. A DC Neural Network (DCNN) extracts hierarchical spatial features, while a Transformer module models long-range dependencies and global contextual relationships. To improve convergence and generalization, the DGWO adaptively tunes network hyperparameters and weights. TL is realized by fine-tuning the model on CXR data using pretrained knowledge from fuselage defect detection. Experimental evaluation implemented in Python demonstrates strong performance, achieving 94% precision, 93.75% recall, 96.80% accuracy, and a 93.80% F1-score. These results confirm that combining TL with hybrid deep architectures provides an effective and computationally efficient solution for cross-domain AD.
Keywords: Computer Vision, abnormality identification, cross-domain, industrial inspection, medical imaging
Transformative Potential of Artificial Intelligence and Computer Vision in Modern Healthcare Diagnostics (Published)
Artificial intelligence and computer vision technologies are fundamentally transforming healthcare diagnostics and treatment through enhanced detection capabilities, improved accuracy, and revolutionary spatial precision. This comprehensive article examines five interconnected domains where computational intelligence is reshaping clinical practice: the diagnostic paradigm shift toward AI integration, machine learning algorithms for enhanced lesion detection across specialties, real-time analysis capabilities during procedures, robotic integration for unprecedented manipulation precision, and advanced spatial mapping technologies that revolutionize navigation within complex anatomy. The transformation demonstrates significant advancements in reducing diagnostic errors, minimizing inter-observer variability, improving treatment customization, enabling earlier detection of pathology, enhancing procedural safety, increasing precision of interventions, and facilitating remote healthcare delivery to underserved populations. Through the synergistic integration of human expertise with computational intelligence, these technologies collectively establish new standards for diagnostic and therapeutic capabilities while simultaneously addressing longstanding challenges in healthcare delivery. The evidence demonstrates that AI-augmented healthcare represents not merely an incremental improvement but rather a fundamental reconceptualization of how medical data is processed, analyzed, and translated into clinical decisions.
Keywords: Artificial Intelligence, Augmented Reality, Computer Vision, diagnostic accuracy, personalized medicine, robotic precision