Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons

Face detection by electronic systems has been leveraged by private and government establishments to enhance the effectiveness of a wide range of applications in our day to day activities, security, and businesses. Most face detection algorithms that can reduce the problems posed by constrained and unconstrained environmental conditions such as unbalanced illumination, weather condition, distance from the camera, and background variations, are highly computationally intensive. Therefore, they are primarily unemployable in real-time applications. This paper developed face detectors by utilizing selected Haar-like and local binary pattern features, based on their number of uses at each stage of training using MATLAB’s trainCascadeObjectDetector function. We used 2577 positive face samples and 37,206 negative samples to train Haar-like and LBP face detectors for a range of False Alarm Rate (FAR) values (i.e., 0.01, 0.05, and 0.1). However, the study shows that the Haar cascade face detector at a low stage (i.e., at six stages) for 0.1 FAR value is the most efficient when tested on a set of classroom images dataset with 100% True Positive Rate (TPR) face detection accuracy. Though, deep learning ResNet101 and ResNet50 outperformed the average performance of Haar cascade by 9.09% and 0.76% based on TPR, respectively. The simplicity and relatively low computational time used by our approach (i.e., 1.09 s) gives it an edge over deep learning (139.5 s), in online classroom applications. The TPR of the proposed algorithm is 92.71% when tested on images in the synthetic Labeled Faces in the Wild (LFW) dataset and 98.55% for images in MUCT face dataset “a”, resulting in a little improvement in average TPR over the conventional face identification system.

Download Full-text

Uncertainty-Aware Deep Learning-Based Cardiac Arrhythmias Classification Model of Electrocardiogram Signals

Computers ◽

10.3390/computers10060082 ◽

2021 ◽

Vol 10 (6) ◽

pp. 82

Author(s):

Ahmad O. Aseeri

Keyword(s):

Deep Learning ◽

Cardiac Arrhythmias ◽

Large Scale ◽

Clinical Decision Making ◽

Probabilistic Approach ◽

Classification Model ◽

Gating Mechanism ◽

Uncertainty Estimates ◽

Wide Range

Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the accurate detection and classification of cardiac arrhythmias, which can be achieved via electrocardiograms (ECGs). Motivated by the desire to enhance conventional clinical methods in diagnosing cardiac arrhythmias, we introduce an uncertainty-aware deep learning-based predictive model design for accurate large-scale classification of cardiac arrhythmias successfully trained and evaluated using three benchmark medical datasets. In addition, considering that the quantification of uncertainty estimates is vital for clinical decision-making, our method incorporates a probabilistic approach to capture the model’s uncertainty using a Bayesian-based approximation method without introducing additional parameters or significant changes to the network’s architecture. Although many arrhythmias classification solutions with various ECG feature engineering techniques have been reported in the literature, the introduced AI-based probabilistic-enabled method in this paper outperforms the results of existing methods in outstanding multiclass classification results that manifest F1 scores of 98.62% and 96.73% with (MIT-BIH) dataset of 20 annotations, and 99.23% and 96.94% with (INCART) dataset of eight annotations, and 97.25% and 96.73% with (BIDMC) dataset of six annotations, for the deep ensemble and probabilistic mode, respectively. We demonstrate our method’s high-performing and statistical reliability results in numerical experiments on the language modeling using the gating mechanism of Recurrent Neural Networks.

Download Full-text

BUILDING CHANGE DETECTION FROM BITEMPORAL AERIAL IMAGES USING DEEP LEARNING

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-565-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 565-571

Author(s):

S. Su ◽

T. Nawata ◽

T. Fuse

Keyword(s):

Deep Learning ◽

Change Detection ◽

Urban Areas ◽

Network Architecture ◽

Aerial Images ◽

Detection Accuracy ◽

Detection Model ◽

Wide Range ◽

Surface Models ◽

Data Source

Abstract. Automatic building change detection has become a topical issue owing to its wide range of applications, such as updating building maps. However, accurate building change detection remains challenging, particularly in urban areas. Thus far, there has been limited research on the use of the outdated building map (the building map before the update, referred to herein as the old-map) to increase the accuracy of building change detection. This paper presents a novel deep-learning-based method for building change detection using bitemporal aerial images containing RGB bands, bitemporal digital surface models (DSMs), and an old-map. The aerial images have two types of spatial resolutions, 12.5 cm or 16 cm, and the cell size of the DSMs is 50 cm × 50 cm. The bitemporal aerial images, the height variations calculated using the differences between the bitemporal DSMs, and the old-map were fed into a network architecture to build an automatic building change detection model. The performance of the model was quantitatively and qualitatively evaluated for an urban area that covered approximately 10 km2 and contained over 21,000 buildings. The results indicate that it can detect the building changes with optimum accuracy as compared to other methods that use inputs such as i) bitemporal aerial images only, ii) bitemporal aerial images and bitemporal DSMs, and iii) bitemporal aerial images and an old-map. The proposed method achieved recall rates of 89.3%, 88.8%, and 99.5% for new, demolished, and other buildings, respectively. The results also demonstrate that the old-map is an effective data source for increasing building change detection accuracy.

Download Full-text

Ship Detection Based on YOLOv2 for SAR Imagery

Remote Sensing ◽

10.3390/rs11070786 ◽

2019 ◽

Vol 11 (7) ◽

pp. 786 ◽

Cited By ~ 41

Author(s):

Yang-Lang Chang ◽

Amare Anagaw ◽

Lena Chang ◽

Yi Wang ◽

Chih-Yu Hsiao ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Real Time ◽

Experimental Results ◽

Detection Methods ◽

Computational Time ◽

Detection Accuracy ◽

Single Shot ◽

Ship Detection ◽

Sar Imagery

Synthetic aperture radar (SAR) imagery has been used as a promising data source for monitoring maritime activities, and its application for oil and ship detection has been the focus of many previous research studies. Many object detection methods ranging from traditional to deep learning approaches have been proposed. However, majority of them are computationally intensive and have accuracy problems. The huge volume of the remote sensing data also brings a challenge for real time object detection. To mitigate this problem a high performance computing (HPC) method has been proposed to accelerate SAR imagery analysis, utilizing the GPU based computing methods. In this paper, we propose an enhanced GPU based deep learning method to detect ship from the SAR images. The You Only Look Once version 2 (YOLOv2) deep learning framework is proposed to model the architecture and training the model. YOLOv2 is a state-of-the-art real-time object detection system, which outperforms Faster Region-Based Convolutional Network (Faster R-CNN) and Single Shot Multibox Detector (SSD) methods. Additionally, in order to reduce computational time with relatively competitive detection accuracy, we develop a new architecture with less number of layers called YOLOv2-reduced. In the experiment, we use two types of datasets: A SAR ship detection dataset (SSDD) dataset and a Diversified SAR Ship Detection Dataset (DSSDD). These two datasets were used for training and testing purposes. YOLOv2 test results showed an increase in accuracy of ship detection as well as a noticeable reduction in computational time compared to Faster R-CNN. From the experimental results, the proposed YOLOv2 architecture achieves an accuracy of 90.05% and 89.13% on the SSDD and DSSDD datasets respectively. The proposed YOLOv2-reduced architecture has a similarly competent detection performance as YOLOv2, but with less computational time on a NVIDIA TITAN X GPU. The experimental results shows that the deep learning can make a big leap forward in improving the performance of SAR image ship detection.

Download Full-text

Design patterns and software techniques for large-scale, open and reproducible data reduction

10.21504/10962/172169 ◽

2021 ◽

Author(s):

◽

Gijs Jan Molenaar

Keyword(s):

Deep Learning ◽

Data Reduction ◽

Large Scale ◽

Expert Knowledge ◽

Lessons Learned ◽

Computational Time ◽

Generative Adversarial Network ◽

Software Packages ◽

Starting Point ◽

Wide Range

The preparation for the construction of the Square Kilometre Array, and the introduction of its operational precursors, such as LOFAR and MeerKAT, mark the beginning of an exciting era for astronomy. Impressive new data containing valuable science just waiting for discovery is already being generated, and these devices will produce far more data than has ever been collected before. However, with every new data instrument, the data rates grow to unprecedented quantities of data, requiring novel new data-processing tools. In addition, creating science grade data from the raw data still requires significant expert knowledge for processing this data. The software used is often developed by a scientist who lacks proper training in software development skills, resulting in the software not progressing beyond a prototype stage in quality. In the first chapter, we explore various organisational and technical approaches to address these issues by providing a historical overview of the development of radioastronomy pipelines since the inception of the field in the 1940s. In that, the steps required to create a radio image are investigated. We used the lessons-learned to identify patterns in the challenges experienced, and the solutions created to address these over the years. The second chapter describes the mathematical foundations that are essential for radio imaging. In the third chapter, we discuss the production of the KERN Linux distribution, which is a set of software packages containing most radio astronomy software currently in use. Considerable effort was put into making sure that the contained software installs appropriately, all items next to one other on the same system. Where required and possible, bugs and portability fixes were solved and reported with the upstream maintainers. The KERN project also has a website, and issue tracker, where users can report bugs and maintainers can coordinate the packaging effort and new releases. The software packages can be used inside Docker and Singularity containers, enabling the installation of these packages on a wide variety of platforms. In the fourth and fifth chapters, we discuss methods and frameworks for combining the available data reduction tools into recomposable pipelines and introduce the Kliko specification and software. This framework was created to enable end-user astronomers to chain and containerise operations of software in KERN packages. Next, we discuss the Common Workflow Language (CommonWL), a similar but more advanced and mature pipeline framework invented by bio-informatics scientists. CommonWL is supported by a wide range of tools already; among other schedulers, visualisers and editors. Consequently, when a pipeline is made with CommonWL, it can be deployed and manipulated with a wide range of tools. In the final chapter, we attempt something unconventional, applying a generative adversarial network based on deep learning techniques to perform the task of sky brightness reconstruction. Since deep learning methods often require a large number of training samples, we constructed a CommonWL simulation pipeline for creating dirty images and corresponding sky models. This simulated dataset has been made publicly available as the ASTRODECONV2019 dataset. It is shown that this method is useful to perform the restoration and matches the performance of a single clean cycle. In addition, we incorporated domain knowledge by adding the point spread function to the network and by utilising a custom loss function during training. Although it was not possible to improve the cleaning performance of commonly used existing tools, the computational time performance of the approach looks very promising. We suggest that a smaller scope should be the starting point for further studies and optimising of the training of the neural network could produce the desired results.

Download Full-text

Deep Neural Network for Better Face Processing

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c6238.118419 ◽

2019 ◽

Vol 8 (4) ◽

pp. 2236-2239

Keyword(s):

Neural Network ◽

Deep Learning ◽

Face Detection ◽

Deep Neural Network ◽

Low Cost ◽

Raspberry Pi ◽

The Face ◽

Frame Work ◽

Haar Cascade ◽

Cascade Method

This Paper represents the face detection using advanced method deep neural network which uses deep learning frame work. The old models used to detect the faces were like Haar-cascade method which detect the faces with good approaches but there is some uncertainty in the accuracy of the old models, so in this system we will use the latest deep neural network model which is embedded with latest open cv and by using the deep learning model frame work which is weighted with some other files. By using this model, we can achieve the better accuracy in face detection which can be used for further purposes like auto focus in cameras, counting number of people etc. This model detects the faces accurately and paves the way for better recognition systems which can be used in many face biometric applications. For this purpose, low-cost computer board Raspberry Pi and Camera Sensor will be used.

Download Full-text

Performance analysis of flow-based attacks detection on CSE-CIC-IDS2018 dataset using deep learning

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v20.i3.pp1413-1418 ◽

2020 ◽

Vol 20 (3) ◽

pp. 1413

Author(s):

Rawaa Ismael Farhan ◽

Abeer Tariq Maolood ◽

Nidaa Flaih Hassan

Keyword(s):

Deep Learning ◽

Cyber Security ◽

Detection System ◽

Detection Accuracy ◽

Deep Model ◽

Normal Behavior ◽

Wide Range ◽

High Level ◽

Communications System ◽

The Internet Of Things

<p>The emergence of the Internet of Things (IOT) as a result of the development of the communications system has made the study of cyber security more important. Day after day, attacks evolve and new attacks are emerged. Hence, network anomaly-based intrusion detection system is become very important, which plays an important role in protecting the network through early detection of attacks. Because of the development in machine learning and the emergence of deep learning field, and its ability to extract high-level features with high accuracy, made these systems involved to be worked with real network traffic CSE-CIC-IDS2018 with a wide range of intrusions and normal behavior is an ideal way for testing and evaluation . In this paper , we test and evaluate our deep model (DNN) which achieved good detection accuracy about 90% .</p>

Download Full-text

Network Intrusion Detection using a Deep Learning Approach

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b4086.099320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 59-64

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Intrusion Detection ◽

Detection System ◽

Research Work ◽

Computer Hardware ◽

Classification Model ◽

Network Intrusion Detection ◽

Network Intrusion ◽

Wide Range

At present situation network communication is at high risk for external and internal attacks due to large number of applications in various fields. The network traffic can be monitored to determine abnormality for software or hardware security mechanism in the network using Intrusion Detection System (IDS). As attackers always change their techniques of attack and find alternative attack methods, IDS must also evolve in response by adopting more sophisticated methods of detection .The huge growth in the data and the significant advances in computer hardware technologies resulted in the new studies existence in the deep learning field, including ID. Deep Learning (DL) is a subgroup of Machine Learning (ML) which is hinged on data description. The new model based on deep learning is presented in this research work to activate operation of IDS from modern networks. Model depicts combination of deep learning and machine learning, having capacity of wide range accurate analysis of traffic network. The new approach proposes non-symmetric deep auto encoder (NDAE) for learning the features in unsupervised manner. Furthermore, classification model is constructed using stacked NDAEs for classification. The performance is evaluated using a network intrusion detection analysis dataset, particularly the WSN Trace dataset. The contribution work is to implement advanced deep learning algorithm consists IDS use, which are efficient in taking instant measures in order to stop or minimize the malicious actions

Download Full-text

An Intelligent Forensics Approach for Detecting Patch-Based Image Inpainting

Mathematical Problems in Engineering ◽

10.1155/2020/8892989 ◽

2020 ◽

Vol 2020 ◽

pp. 1-10

Author(s):

Xinyi Wang ◽

He Wang ◽

Shaozhang Niu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Time Complexity ◽

Image Inpainting ◽

Image Forensics ◽

Detection Accuracy ◽

Semantic Level ◽

Wide Range ◽

Blind Image ◽

Deep Learning Model

Image inpainting algorithms have a wide range of applications, which can be used for object removal in digital images. With the development of semantic level image inpainting technology, this brings great challenges to blind image forensics. In this case, many conventional methods have been proposed which have disadvantages such as high time complexity and low robustness to postprocessing operations. Therefore, this paper proposes a mask regional convolutional neural network (Mask R-CNN) approach for patch-based inpainting detection. According to the current research, many deep learning methods have shown the capacity for segmentation tasks when labeled datasets are available, so we apply a deep neural network to the domain of inpainting forensics. This deep learning model can distinguish and obtain different features between the inpainted and noninpainted regions. To reduce the missed detection areas and improve detection accuracy, we also adjust the sizes of the anchor scales due to the inpainting images and replace the original nonmaximum suppression single threshold with an improved nonmaximum suppression (NMS). The experimental results demonstrate this intelligent method has better detection performance over recent approaches of image inpainting forensics.

Download Full-text

Automated identification of cephalometric landmarks: Part 1—Comparisons between the latest deep-learning methods YOLOV3 and SSD

The Angle Orthodontist ◽

10.2319/022019-127.1 ◽

2019 ◽

Vol 89 (6) ◽

pp. 903-909 ◽

Cited By ~ 9

Author(s):

Ji-Hoon Park ◽

Hye-Won Hwang ◽

Jun-Ho Moon ◽

Youngsung Yu ◽

Hansuk Kim ◽

...

Keyword(s):

Deep Learning ◽

Computational Time ◽

Automatic Identification ◽

Identification System ◽

Single Shot ◽

Learning Methods ◽

Radiographic Images ◽

Data Set ◽

Landmark Identification ◽

Significant Difference

ABSTRACT Objective: To compare the accuracy and computational efficiency of two of the latest deep-learning algorithms for automatic identification of cephalometric landmarks. Materials and Methods: A total of 1028 cephalometric radiographic images were selected as learning data that trained You-Only-Look-Once version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) methods. The number of target labeling was 80 landmarks. After the deep-learning process, the algorithms were tested using a new test data set composed of 283 images. Accuracy was determined by measuring the point-to-point error and success detection rate and was visualized by drawing scattergrams. The computational time of both algorithms was also recorded. Results: The YOLOv3 algorithm outperformed SSD in accuracy for 38 of 80 landmarks. The other 42 of 80 landmarks did not show a statistically significant difference between YOLOv3 and SSD. Error plots of YOLOv3 showed not only a smaller error range but also a more isotropic tendency. The mean computational time spent per image was 0.05 seconds and 2.89 seconds for YOLOv3 and SSD, respectively. YOLOv3 showed approximately 5% higher accuracy compared with the top benchmarks in the literature. Conclusions: Between the two latest deep-learning methods applied, YOLOv3 seemed to be more promising as a fully automated cephalometric landmark identification system for use in clinical practice.

Download Full-text

A Real-Time Vehicle Detection System under Various Bad Weather Conditions Based on a Deep Learning Model without Retraining

Sensors ◽

10.3390/s20205731 ◽

2020 ◽

Vol 20 (20) ◽

pp. 5731 ◽

Cited By ~ 1

Author(s):

Xiu-Zhi Chen ◽

Chieh-Min Chang ◽

Chao-Wei Yu ◽

Yen-Lin Chen

Keyword(s):

Deep Learning ◽

Detection System ◽

Vehicle Detection ◽

Weather Conditions ◽

Learning Model ◽

Detection Methods ◽

Computational Time ◽

Detection Accuracy ◽

Bad Weather ◽

Deep Learning Model

Numerous vehicle detection methods have been proposed to obtain trustworthy traffic data for the development of intelligent traffic systems. Most of these methods perform sufficiently well under common scenarios, such as sunny or cloudy days; however, the detection accuracy drastically decreases under various bad weather conditions, such as rainy days or days with glare, which normally happens during sunset. This study proposes a vehicle detection system with a visibility complementation module that improves detection accuracy under various bad weather conditions. Furthermore, the proposed system can be implemented without retraining the deep learning models for object detection under different weather conditions. The complementation of the visibility was obtained through the use of a dark channel prior and a convolutional encoder–decoder deep learning network with dual residual blocks to resolve different effects from different bad weather conditions. We validated our system on multiple surveillance videos by detecting vehicles with the You Only Look Once (YOLOv3) deep learning model and demonstrated that the computational time of our system could reach 30 fps on average; moreover, the accuracy increased not only by nearly 5% under low-contrast scene conditions but also 50% under rainy scene conditions. The results of our demonstrations indicate that our approach is able to detect vehicles under various bad weather conditions without the need to retrain a new model.

Download Full-text