Face Occlusion Detection Using Deep Convolutional Neural Networks

Leaf disease detection is a crucial task in modern agriculture, aiding in early diagnosis and prevention of crop infections. In this research paper, authors present a comprehensive study comparing nine widely used pre-trained models, namely DenseNet201, EfficientNetB3, EfficientNetB4, InceptionResNetV2, MobileNetV2, ResNet50, ResNet152, VGG16, and Xception, with our newly developed custom CNN (Convolutional Neural Network) for leaf disease detection. The objective is to determine if our custom CNN can match the performance of these established pre-trained models while maintaining superior efficiency. The authors trained and fine-tuned each pre-trained model and our custom CNN on a large dataset of labeled leaf images, covering various diseases and healthy states. Subsequently, the authors evaluated the models using standard metrics, including accuracy, precision, recall, and F1-score, to gauge their overall performance. Additionally, the authors analyzed computational efficiency regarding training time and memory consumption. Surprisingly, our results indicate that the custom CNN performs comparable to the pre-trained models, despite their sophisticated architectures and extensive pre-training on massive datasets. Moreover, our custom CNN demonstrates superior efficiency, outperforming the pre-trained models regarding training speed and memory requirements. These findings highlight the potential of custom CNN architectures for leaf disease detection tasks, offering a compelling alternative to the commonly used pre-trained models. The efficiency gains achieved by our custom CNN can be beneficial in resource-constrained environments, enabling faster inference and deployment of leaf disease detection systems. Overall, our research contributes to the advancement of agricultural technology by presenting a robust and efficient solution for the early detection of leaf diseases, thereby aiding in crop protection and yield enhancement.

Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, unlike most existing CNNs trained on private databases. We propose three CNN architectures which are the first reported architectures trained using LFW data. This paper quantitatively compares the architectures of CNNs and evaluate the effect of different implementation choices. We identify several useful properties of CNN-FRS. For instance, the dimensionality of the learned features can be significantly reduced without adverse effect on face recognition accuracy. In addition, traditional metric learning method exploiting CNN-learned features is evaluated. Experiments show two crucial factors to good CNN-FRS performance are the fusion of multiple CNNs and metric learning. To make our work reproducible, source code and models will be made publicly available.

The performance of current algorithms used in occluded face detection for surveillance systems is limited when detecting a face covered with an obstacle, or a non-frontal view of the face. Therefore, a method able to capture a face from any viewpoint is necessary. In this paper, we propose a new algorithm by using 2 subdivision regions and skin ratio for detecting occluded faces from any head viewpoint during +90 degrees to -90 degrees around the yaw axis. This algorithm consists of 3 steps: head region identification, skin extraction, and occluded face detection. First, the system is fed with an image sequence capturing the whole target body, to define the head region. The head region is detected using a blob technique under an experimental condition. Second, skin data is extracted, for computing skin ratio. Skin color is considered in multiple color spaces, and compared with a database by Mahalanobis Distance technique. Third, for occluded face detection, the human head area is equally divided into 2 vertical regions. The skin ratio of each part is used as a criterion for occlusion detection. To test the performance of the proposed algorithm, data from 35 subjects is used. The data of a subject is captured from any viewpoint of the head, varying from +90 degrees to -90 degrees. As this paper aims to develop surveillance systems, obstacles covering the whole face are focused on, such as helmets and masks. The accuracy rate of non-occluded face and occluded face detection is 98.81 and 94.90 %, respectively. The average accuracy rate is 95.39 %. The advantage of this method over recent research is that this is the first method to detect an occluded face from any viewpoint of the head varying from +90 degrees to -90 degrees. doi: 10.14456/WJST.2015.4

Fine-grained face verification: FGLFW database, baselines, and human-DCMN partnership

It is observed that pneumonia is the largest cause of death in toddlers. Early detection would facilitate in early treatment, hence, saving many lives. This paper intend to develop a method for automating the detection of pneumonia using chest X-rays and comparing convolutional neural network and multilevel perceptron. Custom Convolutional neural network and multi-layer perceptron were implemented on a chest X-ray dataset by Kaggle. A GUI was created that accepts the chest X-ray and predicts the presence of pneumonia and gives the congestion percentage. The model accuracy was 92.63% and 77.56% for convolutional neural network and multilayer perceptron respectively. The GUI developed gives favourable outcomes. Convolutional neural network showed better results as compared to multi-layer perceptron. Thus, the custom convolutional neural network was used for the GUI.

Facial recognition is a critical biometric technology applied in surveillance, access control, and identity verification.However, existing Convolutional Neural Network (CNN) based models often face performance limitations under challenging conditions such as poor lighting, pose variations, occlusion, and facial expression changes.This study proposes a robust and adaptive CNN architecture to enhance recognition accuracy and generalization.The research objectives are to (i) review existing CNN based models, (ii) design an improved CNN architecture, (iii) implement and train the model using standard datasets, (iv) evaluate its performance using accuracy, precision, recall, and F1 score, and (v) compare results with baseline CNN models.The study adopts a quantitative methodology using Python based deep learning frameworks.Pre collected datasets including Labeled Faces in the Wild (LFW), CelebA, and UTKFace are processed using image normalization, face alignment via MTCNN, and data augmentation.Statistical performance metrics and confusion matrix visualization support comprehensive performance evaluation.While results demonstrate improvements, limitations include computational cost, dataset diversity, and real world deployment challenges such as latency and adaptability in dynamic environments.

Content filtering is gaining popularity due to easy exposure of explicit visual contents to the public. Excessive exposure of inappropriate visual contents can cause devastating effects such as the growth of improper mindset and rise of societal issues such as free sex, child abandonment and rape cases. At present, most of the broadcasting media sites are hiring censorship editors to label graphic contents manually. Nevertheless, the efficiency is limited by factors such as the attention span of humans and the training required for the editors. This paper proposes to study the effect of usage of Convolutional Neural Network (CNN) as feature extractor coupled with Support Vector Machine (SVM) as classifier in an automated pornographic detection system. Three CNN architectures: Mobile Net, Visual Geometry Group-19 (VGG-19) and Residual Network-50 Version 2 (ResNet50_V2), and two classifiers: CNN and SVM were utilized to explore the combination that produce the best result. Frames of films fed as input into the CNN were classified into two groups: porn or non-porn. The best accuracy was 92.80% obtained using fine-tuned ResNet50_V2 as feature extractor and SVM as classifier. Transfer learning and SVM have improved the CNN model by approximately 10%.

This study investigates the use of convolutional neural networks to automatically detect malaria-infected cells in blood smear images, offering an alternative to manual diagnosis, which depends on specialized professionals and adequate infrastructure. Manual diagnosis is time-consuming and prone to human errors, especially in malaria-endemic regions with limited resources. Automated approaches based on convolutional neural networks provide a promising solution to optimize the diagnostic process and improve access to rapid treatment in remote areas. The research evaluates the performance of different convolutional neural network architectures for malaria diagnosis, following the Cross Industry Standard Process for Data Mining methodology to structure preprocessing, modeling, and model evaluation. Preprocessing involved normalization and data augmentation techniques to enhance sample quality and diversity. Two architectures were compared: a customized convolutional neural network designed to balance computational efficiency and accuracy, and an adapted VGG16, recognized for its advanced image feature extraction capabilities. Both models were trained and evaluated using a robust dataset of blood cell images. The customized network achieved 95.6% accuracy, outperforming similar models in the literature and demonstrating its practicality for low-resource settings. It also exhibited high precision, recall, and F1-score, ensuring reliable and balanced classification of infected and healthy cells. This approach reduces reliance on specialists and advanced equipment, making malaria diagnosis more accessible and efficient. The findings position the customized convolutional neural network as a viable solution for automated malaria diagnosis, combining simplicity with high performance and offering significant potential for improving healthcare in endemic regions.

Precisely detecting masked and non-masked faces are increasingly important since wearing a face mask is an effective measure to prevent the spread of the COVID-19 pandemic. Previous literature focused mainly on occluded face detection or facial expression, which were unsuitable for the application of detecting human faces wearing masks. Hence, to overcome the issue, this work proposes a Convolutional Neural Network-based model that uses region proposals to detect masked and nonmasked faces. The depth of the Convolutional Neural Network was increased by using residual skip-connections. The model was implemented using TensorFlow Object Detection API and was pre-trained over the COCO dataset. A secondary outcome of the paper was to collect a dataset of high resolution masked and nonmasked faces for training deep learning frameworks, due to the lack of datasets available for this task. The proposed model was compared with the SSD Inception V2 model [1] and the SSD MobileNet V2 model [2] in the context of detection accuracy (mAP). The experiments highlight that the proposed framework achieves a detection accuracy (total mAP) of 85.82%, on the collected dataset. The results are significantly better in detecting non-masked faces with a detection accuracy (mAP) of 98.61% while it is 68.72% accurate in detecting masked faces. Based on this model's performance on standard parameters, a detailed study is outlined along with the conclusion and future plan of action.

The use of Convolutional Neural Networks (CNNs) for image classification is wellestablished in defect detection within manufacturing environments. However, their application in assembly processes remains underexplored. This study investigates the effectiveness of using relatively smaller CNNs for detecting assembly defects by testing multiple existing pre-trained CNNs and a custom CNN on a dataset of model train seat assembly images. The dataset includes common assembly defects such as missing, rotated, and swapped parts. Despite implementing various data augmentation and image processing techniques, such as cropping, normalization, and image transforms, and making several modifications to the models, the existing techniques struggled to accurately predict defects while providing the correct rationale for their predictions. The Grad-CAM analysis revealed that the models often focused on irrelevant features, highlighting the challenges of defect detection in complex assembly environments. These findings indicate the need for more robust machine learning approaches capable of handling high levels of noise and variations typical of realworld assembly conditions. This study underscores the limitations of current CNN-based defect detection methods in uncontrolled assembly settings and the necessity for further research to develop more reliable solutions.

Application of Face Recognition Method Under Deep Learning Algorithm in Embedded Systems

Face occlusion has been a long standing challenging issue in face recognition. In the state-of-the-art deep Convolutional Neural Network (CNN) face recognition models, occluded facial parts are generally embedded into the learned features together with the non-occluded parts in an equivalent manner. As such, the discriminative power of the generated face representation may be weakened for occluded face images. To address this problem, we propose the MaskNet, a trainable module which can be included in existing CNN architectures. With end-to-end training supervised by only the personal identity labels, MaskNet learns a proper way of adaptively generating different feature map masks for different occluded face images. Intuitively, MaskNet automatically assigns higher weights to the hidden units activated by the non-occluded facial parts and lower weights to those that are activated by the occluded facial parts. Experiments on datasets consisting of real-life and synthetic occluded faces demonstrate that MaskNet can effectively improve the robustness of CNN models towards occlusions in face recognition.

Optical inspection using unmanned aerial vehicles is a popular trend for detection of surface defects on industrial infrastructure, and full automation is the next step in order to improve potential and reduce costs. Binary classification of the obtained visual image data into defect and defect-free sets is one sub-task of these systems and is still often carried out either completely manually by an expert or by using pre-defined features as classifiers for automatic image post-processing. In contrast, deep convolutional neural networks (CNN) are able to perform both the feature extraction and classification tasks simultaneously by internal hierarchical learning. In this work, custom CNNs and a transfer-learned AlexNet are applied to an experimental data set with artificial defects in order to analyze suitability and required network depth for such surface inspections. Experiments are performed using a set of 2500 camera images total, yielding a classification accuracy of up to 99 % with a single CNN. Thereby, the amount of actual defects that are falsely classified as negative are minimized. Results proof the general effectiveness of the methodology and motivate the application to specific inspection tasks.

ObjectivesForensic age estimation from orthopantomograms (OPGs) can be performed more quickly and accurately using convolutional neural networks (CNNs), making them an ideal extension to standard forensic age estimation methods. This study evaluates improvements in forensic age prediction for children, adolescents, and young adults by training a custom CNN from a previous study, using a larger, diverse dataset with a focus on dental growth features.Methods21,814 OPGs from 13,766 individuals aged 1 to under 25 years were utilized. The custom CNN underwent 1000 epochs of training and validation using 16,000 and 4000 OPGs, respectively. The best model was chosen by the least mean absolute error (MAE) and evaluated with an additional test dataset of 1814 independent OPGs. Furthermore, the CNN was applied to OPGs from 15 available forensic age estimations conducted by experts certified by the Study Group on Forensic Age Diagnostics (AGFAD), and the results were compared.ResultsA MAE of 0.93 ± 0.81 years and a mean-signed error (MSE) of −0.06 ± 1.23 years were achieved in the test dataset. 63% of predictions were accurate within 1 year, and 95% within 2.5 years. Results of the CNN were comparable to those obtained by experts, effectively highlighting discrepancies in the reported ages of individuals.ConclusionUsing a large and diverse dataset along with custom deep learning techniques, forensic age estimation can be significantly improved, often providing predictions accurate to within 1 year. This approach offers a reliable, robust, and objective complement to standard forensic age estimation methods.Key PointsQuestionThe potential of custom convolutional neural networks for forensic age estimation, along with a large, diverse dataset, warrants further investigation, offering valuable support to experts.FindingsFor 1814 test-orthopantomograms, 63% of predictions were accurate within 1 year and 95% within 2.5 years, similar to expert estimates in 15 forensic cases.Clinical relevanceMany individuals’ fates depend on accurate age estimation. Forensic age estimation can benefit from applying CNN-based methods to further enhance reliability and accuracy.

Pest infestation is a significant challenge in agriculture, causing substantial economic losses and impacting crop yields. Manual pest identification is time-consuming and error-prone, especially in large-scale farming. This study presents a hybrid deep learning approach to automate pest detection and classification using image data. It employs a pre-trained VGG16 model for robust feature extraction, followed by a custom Convolutional Neural Network (CNN) for classification. The VGG16 model leverages transfer learning to capture high-level visual patterns from pest images, while the custom CNN is trained on these features to distinguish between multiple pest classes. The proposed pipeline is optimized using data augmentation, early stopping, and adaptive learning techniques. Performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. The model demonstrates high accuracy and robustness on agricultural image datasets, making it a scalable solution for smart farming systems. Index Terms: Pest Detection, Deep Learning, VGG16, Convolutional Neural Network, Transfer Learning, Image Classification, Precision Agriculture, Feature Extraction.