Fig 1
![Geometrical facial recognition [8].](publication/351911803/figure/fig1/AS:1028069003386887@1622122159875/Geometrical-facial-recognition-8.jpg)
Source publication
![Fig. 1. Geometrical facial recognition [8].](publication/351911803/figure/fig1/AS:1028069003386887@1622122159875/Geometrical-facial-recognition-8_Q320.jpg)
![Fig. 2. Photometric stereo image [10].](publication/351911803/figure/fig2/AS:1028069003370500@1622122159901/Photometric-stereo-image-10_Q320.jpg)
Feature extracting and training module can be done by using face recognition neural learning techniques. Moreover, these techniques are widely employed to extract features from human images. Some detection systems are capable to scan the full body, iris detection, and finger print detection systems. These systems have deployed for safety and securi...
Context in source publication
Context 1
... is based entirely on the geometric court between facial features, or we can say dimensional arrangements about facial features. In this way, predictions of face, including eyes, mouth and nostrils, are placed first, the face is labeled with geographical distances and angles whose characteristics are described in Fig. 1. ...
Similar publications
Garcinia kola Heckel is a valuable fruit tree species that plays a significant role in contributing to household economies in West and Central Africa where the species is endemic. This study assessed the variations in six sources of G. kola in Southern Nigeria. Fruit and seed characteristics (fruit length (FL), fruit diameter (FD), number of seeds...
Citations
... FN transforms the facial images into a densely packed Euclidean space in which separations increase the distance between the faces. The purpose of this research [5] is to investigate deep learning-based face representation under a variety of situations, including lower and upper face occlusions, misalignment, varying angles of head poses, shifting illuminations, and incorrect facial feature localisation. In this study, two prominent Deep learning models termed Lightened CNN and VGG-Face were used to extract face representation. ...
In recent years face recognition system is emerging technology in research areas. Face recognition is used in many applications such as attendance management system, People tracking system and access control system etc. Major challenges faced in face recognition are detection and recognition because it is not easy to detect multiple faces in one frame and difficult to recognize the faces with poor resolution. Therefore, the main objective of this paper is to obtain better accuracy by using the combination of FaceNet and Deep Neural Network (DNN). In this proposed system, FaceNet is used for feature extraction by embedding 128 dimensions per face and DNN is used to classify the given training data with extracted feature of FaceNet. The outcome of the system is practical, reliable and consumes less time.
... True positives (TP) are tuberculosis images that were correctly identified as such; true negatives (TN) are normal images that were correctly identified as such; false positives (FP) are normal images that were incorrectly identified as tuberculosis images; and false negatives (FN) are normal tuberculosis images. Accuracy simply indicates how close our expected result is to the actual result [24]. It is represented as a percentage. ...
Deep learning has emerged as a promising technique for a variety of elements of infectious disease monitoring and detection,
including tuberculosis. We built a deep convolutional neural network (CNN) model to assess the generalizability of the deep
learning model using a publicly accessible tuberculosis dataset. *is study was able to reliably detect tuberculosis (TB) from chest
X-ray images by utilizing image preprocessing, data augmentation, and deep learning classification techniques. Four distinct deep
CNNs (Xception, InceptionV3, InceptionResNetV2, and MobileNetV2) were trained, validated, and evaluated for the classification of tuberculosis and nontuberculosis cases using transfer learning from their pretrained starting weights. With an F1-score
of 99 percent, InceptionResNetV2 had the highest accuracy. *is research is more accurate than earlier published work. Additionally, it outperforms all other models in terms of reliability. *e suggested approach, with its state-of-the-art performance,
may be helpful for computer-assisted rapid TB detection.
... There are many ways in which the ensembles may be generated with the ensuing output from every classifier then blended to classify new instances. In this way, we can evaluate both the dataset and the performance of the strategies used for prediction [8]. ...
The problem of a facial biometrics system is discussed in this research, in which different classifiers are used within the framework of face recognition. Different similarity measures are existed to solve the performance of facial recognition problems. Here four machine learning approaches are considered, namely, K-nearest neighbor (KNN), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Principal Component Analysis (PCA).The usefulness of multiple classification systems is also seen and evaluated in terms of their ability to correctly classify a face. We used combination of multiple algorithms such as PCA+1NN, LDA+1NN, PCA+ LDA+1NN, SVM, and SVM+PCA. All of them performed with exceptional values of above 90% but PCA+LDA+1N scored the highest average accuracy is 98%.
Poisson noises are common in underexposed radiographs due to a lack of photons reaching the detector. Scatter radiations damage radiographs, and the severity of picture quality degradations is determined by the amount of scatters reaching the detectors. To forecast scatters and reduce Poisson noises, a convolutional neural network (CNN) method and autoencoders are employed in this study. Autoencoders (AEs) are neural networks with the goal of copying their inputs to their outputs. They function by compressing the input into a latent-space representation and reconstructing the output from this representation. Radiation exposures of 60% underexposed the radiograph. Poisson noises are successfully minimised, and image contrast and details are increased, thereby enhancing the image. After applying the CNN algorithm, the contrast and details in the radiograph were considerably improved and are now adequate for establishing a diagnosis, resulting in a 60% reduction in radiation exposure. The quality of radiographs can be enhanced by minimising scatters and Poisson disturbances, as demonstrated in this study.KeywordsConvolutional neural networkRadiographsAutoencodersCone-beam computed tomographyMax pooling layer
