scholarly journals An Efficient Multi-Scale Anchor Box Approach to Detect Partial Faces from a Video Sequence

2022 ◽  
Vol 6 (1) ◽  
pp. 9
Author(s):  
Dweepna Garg ◽  
Priyanka Jain ◽  
Ketan Kotecha ◽  
Parth Goel ◽  
Vijayakumar Varadarajan
Keyword(s):  
Deep Learning ◽  
Face Detection ◽  
Machine Learning Techniques ◽  
Face Shape ◽  
Detection Algorithms ◽  
Accuracy And Precision ◽  
Learning Techniques ◽  
Proposed Model ◽  
The Face ◽  
Scale Anchor

In recent years, face detection has achieved considerable attention in the field of computer vision using traditional machine learning techniques and deep learning techniques. Deep learning is used to build the most recent and powerful face detection algorithms. However, partial face detection still remains to achieve remarkable performance. Partial faces are occluded due to hair, hat, glasses, hands, mobile phones, and side-angle-captured images. Fewer facial features can be identified from such images. In this paper, we present a deep convolutional neural network face detection method using the anchor boxes section strategy. We limited the number of anchor boxes and scales and chose only relevant to the face shape. The proposed model was trained and tested on a popular and challenging face detection benchmark dataset, i.e., Face Detection Dataset and Benchmark (FDDB), and can also detect partially covered faces with better accuracy and precision. Extensive experiments were performed, with evaluation metrics including accuracy, precision, recall, F1 score, inference time, and FPS. The results show that the proposed model is able to detect the face in the image, including occluded features, more precisely than other state-of-the-art approaches, achieving 94.8% accuracy and 98.7% precision on the FDDB dataset at 21 frames per second (FPS).

scholarly journals Advanced Agro Field & Crop Surveillance Systems

2019 ◽  
Vol 8 (4S2) ◽  
pp. 616-619
Keyword(s):  
Deep Learning ◽  
Primary Productivity ◽  
Machine Learning Techniques ◽  
Productivity Index ◽  
Surveillance Systems ◽  
Motion Sensing ◽  
Detection Algorithms ◽  
On Demand ◽  
Learning Techniques ◽  
The Cost

Agriculture becoming the major driver for Indian economy, applying some of the latest technological digital innovations to solve critical Agri-based challenges are becoming vital to improve the productivity and lower the cost of operations. Primary productivity index of agriculture is directly dependent on how much the crops escaped from attacks either by pests or by external intruders. Applying some of the advanced machine learning techniques in Computer Vision and multiple object detection algorithms in the field of Agriculture surveillance generates huge interest among farmer communities. In this paper, an aapproach which includes deployment of sensors to monitor the whole cultivation area, fixing appropriate cameras and detecting motions in the agro field, is proposed for Agro field surveillance. An orchestrated deployment of necessary sensing devices such as motion-sensing, capturing video based on demand and passes it on to the deep learning algorithms for further synthesis. The model is developed and trained leveraging technologies such as tensorflow, keras with google Colab, Jupyter notebook environment that runs entirely in the google cloud that requires very minimal setup. To evaluate the model, the authors create a test set which contains 200 captured events, more than 60,000 images that are relevant for this scope and available in public to train Deep Learning CNN based models.

scholarly journals Automated Amharic News Categorization Using Deep Learning Models

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Demeke Endalie ◽  
Getamesay Haile
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Document Classification ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Language Resources ◽  
Data Set ◽  
Learning Techniques ◽  
Proposed Model

For decades, machine learning techniques have been used to process Amharic texts. The potential application of deep learning on Amharic document classification has not been exploited due to a lack of language resources. In this paper, we present a deep learning model for Amharic news document classification. The proposed model uses fastText to generate text vectors to represent semantic meaning of texts and solve the problem of traditional methods. The text vectors matrix is then fed into the embedding layer of a convolutional neural network (CNN), which automatically extracts features. We conduct experiments on a data set with six news categories, and our approach produced a classification accuracy of 93.79%. We compared our method to well-known machine learning algorithms such as support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), XGBoost (XGB), and random forest (RF) and achieved good results.

scholarly journals A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

2021 ◽  
Vol 9 (1) ◽  
pp. 115
Author(s):  
Faisal Dharma Adhinata ◽  
Diovianto Putra Rakhmadani ◽  
Merlinda Wibowo ◽  
Akhmad Jayadi
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Face Detection ◽  
Detection System ◽  
Video Data ◽  
Training Data ◽  
Public Places ◽  
Learning Techniques ◽  
The Face ◽  
F Measure

The use of masks on the face in public places is an obligation for everyone because of the Covid-19 pandemic, which claims victims. Indonesia made 3M policies, one of which is to use masks to prevent coronavirus transmission. Currently, several researchers have developed a masked or non-masked face detection system. One of them is using deep learning techniques to classify a masked or non-masked face. Previous research used the MobileNetV2 transfer learning model, which resulted in an F-Measure value below 0.9. Of course, this result made the detection system not accurate enough. In this research, we propose a model with more parameters, namely the DenseNet201 model. The number of parameters of the DenseNet201 model is five times more than that of the MobileNetV2 model. The results obtained from several up to 30 epochs show that the DenseNet201 model produces 99% accuracy when training data. Then, we tested the matching feature on video data, the DenseNet201 model produced an F-Measure value of 0.98, while the MobileNetV2 model only produced an F-measure value of 0.67. These results prove the masked or non-masked face detection system is more accurate using the DenseNet201 model.

scholarly journals An Enhanced Deep Neural Network for Predicting Workplace Absenteeism

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Syed Atif Ali Shah ◽  
Irfan Uddin ◽  
Furqan Aziz ◽  
Shafiq Ahmad ◽  
Mahmoud Ahmad Al-Khasawneh ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Learning Algorithms ◽  
Single Layer ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Proposed Model ◽  
The Cost

Organizations can grow, succeed, and sustain if their employees are committed. The main assets of an organization are those employees who are giving it a required number of hours per month, in other words, those employees who are punctual towards their attendance. Absenteeism from work is a multibillion-dollar problem, and it costs money and decreases revenue. At the time of hiring an employee, organizations do not have an objective mechanism to predict whether an employee will be punctual towards attendance or will be habitually absent. For some organizations, it can be very difficult to deal with those employees who are not punctual, as firing may be either not possible or it may have a huge cost to the organization. In this paper, we propose Neural Networks and Deep Learning algorithms that can predict the behavior of employees towards punctuality at workplace. The efficacy of the proposed method is tested with traditional machine learning techniques, and the results indicate 90.6% performance in Deep Neural Network as compared to 73.3% performance in a single-layer Neural Network and 82% performance in Decision Tree, SVM, and Random Forest. The proposed model will provide a useful mechanism to organizations that are interested to know the behavior of employees at the time of hiring and can reduce the cost of paying to inefficient or habitually absent employees. This paper is a first study of its kind to analyze the patterns of absenteeism in employees using deep learning algorithms and helps the organization to further improve the quality of life of employees and hence reduce absenteeism.

scholarly journals The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances

2022 ◽  
Author(s):  
Hang Du ◽  
Hailin Shi ◽  
Dan Zeng ◽  
Xiao-Ping Zhang ◽  
Tao Mei
Keyword(s):  
Deep Learning ◽  
Face Recognition ◽  
Face Detection ◽  
Recognition System ◽  
Face Alignment ◽  
Face Representation ◽  
Learning Techniques ◽  
Face Recognition System ◽  
The Face ◽  
End To End

Face recognition is one of the most popular and long-standing topics in computer vision. With the recent development of deep learning techniques and large-scale datasets, deep face recognition has made remarkable progress and been widely used in many real-world applications. Given a natural image or video frame as input, an end-to-end deep face recognition system outputs the face feature for recognition. To achieve this, a typical end-to-end system is built with three key elements: face detection, face alignment, and face representation. The face detection locates faces in the image or frame. Then, the face alignment is proceeded to calibrate the faces to the canonical view and crop them with a normalized pixel size. Finally, in the stage of face representation, the discriminative features are extracted from the aligned face for recognition. Nowadays, all of the three elements are fulfilled by the technique of deep convolutional neural network. In this survey article, we present a comprehensive review about the recent advance of each element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved the capability of them. To start with, we present an overview of the end-to-end deep face recognition. Then, we review the advance of each element, respectively, covering many aspects such as the to-date algorithm designs, evaluation metrics, datasets, performance comparison, existing challenges, and promising directions for future research. Also, we provide a detailed discussion about the effect of each element on its subsequent elements and the holistic system. Through this survey, we wish to bring contributions in two aspects: first, readers can conveniently identify the methods which are quite strong-baseline style in the subcategory for further exploration; second, one can also employ suitable methods for establishing a state-of-the-art end-to-end face recognition system from scratch.

Real Time Gender and Age Prediction using Deep Learning Techniques

2020 ◽  
Vol 9 (6) ◽  
pp. 797-801
Keyword(s):  
Deep Learning ◽  
Face Recognition ◽  
Real Time ◽  
Vital Role ◽  
Learning Techniques ◽  
Gender And Age ◽  
The Face ◽  
And Gender ◽  
Gender Detection ◽  
Age Prediction

Face recognition plays a vital role in security purpose. In recent years, the researchers have focused on the pose illumination, face recognition, etc,. The traditional methods of face recognition focus on Open CV’s fisher faces which results in analyzing the face expressions and attributes. Deep learning method used in this proposed system is Convolutional Neural Network (CNN). Proposed work includes the following modules: [1] Face Detection [2] Gender Recognition [3] Age Prediction. Thus the results obtained from this work prove that real time age and gender detection using CNN provides better accuracy results compared to other existing approaches.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Assessing the Accuracy of Fault Interpretation using Machine Learning Techniques when Risking Faults for CO2 Storage Site Assessment

2021 ◽  
pp. 1-55
Author(s):  
Emma A. H. Michie ◽  
Behzad Alaei ◽  
Alvar Braathen
Keyword(s):  
Deep Learning ◽  
New Technologies ◽  
Co2 Storage ◽  
Fault Reactivation ◽  
Machine Learning Techniques ◽  
Close Similarity ◽  
Storage Site ◽  
Site Assessment ◽  
Learning Techniques ◽  
Fault Interpretation

Generating an accurate model of the subsurface for the purpose of assessing the feasibility of a CO2 storage site is crucial. In particular, how faults are interpreted is likely to influence the predicted capacity and integrity of the reservoir; whether this is through identifying high risk areas along the fault, where fluid is likely to flow across the fault, or by assessing the reactivation potential of the fault with increased pressure, causing fluid to flow up the fault. New technologies allow users to interpret faults effortlessly, and in much quicker time, utilizing methods such as Deep Learning. These Deep Learning techniques use knowledge from Neural Networks to allow end-users to compute areas where faults are likely to occur. Although these new technologies may be attractive due to reduced interpretation time, it is important to understand the inherent uncertainties in their ability to predict accurate fault geometries. Here, we compare Deep Learning fault interpretation versus manual fault interpretation, and can see distinct differences to those faults where significant ambiguity exists due to poor seismic resolution at the fault; we observe an increased irregularity when Deep Learning methods are used over conventional manual interpretation. This can result in significant differences between the resulting analyses, such as fault reactivation potential. Conversely, we observe that well-imaged faults show a close similarity between the resulting fault surfaces when both Deep Learning and manual fault interpretation methods are employed, and hence we also observe a close similarity between any attributes and fault analyses made.

Sign in / Sign up

Export Citation Format

Share Document