scholarly journals Face Recognition Based on Lightweight Convolutional Neural Networks

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 191
Author(s):  
Wenting Liu ◽  
Li Zhou ◽  
Jie Chen
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Recognition Task ◽  
Training Method ◽  
The Face ◽  
And Storage ◽  
And Training

Face recognition algorithms based on deep learning methods have become increasingly popular. Most of these are based on highly precise but complex convolutional neural networks (CNNs), which require significant computing resources and storage, and are difficult to deploy on mobile devices or embedded terminals. In this paper, we propose several methods to improve the algorithms for face recognition based on a lightweight CNN, which is further optimized in terms of the network architecture and training pattern on the basis of MobileFaceNet. Regarding the network architecture, we introduce the Squeeze-and-Excitation (SE) block and propose three improved structures via a channel attention mechanism—the depthwise SE module, the depthwise separable SE module, and the linear SE module—which are able to learn the correlation of information between channels and assign them different weights. In addition, a novel training method for the face recognition task combined with an additive angular margin loss function is proposed that performs the compression and knowledge transfer of the deep network for face recognition. Finally, we obtained high-precision and lightweight face recognition models with fewer parameters and calculations that are more suitable for applications. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed methods.

scholarly journals PulseNetOne: Fast Unsupervised Pruning of Convolutional Neural Networks for Remote Sensing

2020 ◽  
Vol 12 (7) ◽  
pp. 1092
Author(s):  
David Browne ◽  
Michael Giering ◽  
Steven Prestwich
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Recognition Task ◽  
Scene Recognition ◽  
Training Data ◽  
Learning Approach ◽  
Scene Classification

Scene classification is an important aspect of image/video understanding and segmentation. However, remote-sensing scene classification is a challenging image recognition task, partly due to the limited training data, which causes deep-learning Convolutional Neural Networks (CNNs) to overfit. Another difficulty is that images often have very different scales and orientation (viewing angle). Yet another is that the resulting networks may be very large, again making them prone to overfitting and unsuitable for deployment on memory- and energy-limited devices. We propose an efficient deep-learning approach to tackle these problems. We use transfer learning to compensate for the lack of data, and data augmentation to tackle varying scale and orientation. To reduce network size, we use a novel unsupervised learning approach based on k-means clustering, applied to all parts of the network: most network reduction methods use computationally expensive supervised learning methods, and apply only to the convolutional or fully connected layers, but not both. In experiments, we set new standards in classification accuracy on four remote-sensing and two scene-recognition image datasets.

scholarly journals A Study of The Convolutional Neural Networks Applications

2019 ◽  
Vol 3 (2) ◽  
pp. 31-40 ◽  
Author(s):  
Ahmed Shamsaldin ◽  
Polla Fattah ◽  
Tarik Rashid ◽  
Nawzad Al-Salihi
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Text Classification ◽  
Scene Labeling ◽  
Real World Problems

At present, deep learning is widely used in a broad range of arenas. A convolutional neural networks (CNN) is becoming the star of deep learning as it gives the best and most precise results when cracking real-world problems. In this work, a brief description of the applications of CNNs in two areas will be presented: First, in computer vision, generally, that is, scene labeling, face recognition, action recognition, and image classification; Second, in natural language processing, that is, the fields of speech recognition and text classification.

scholarly journals AN APPROACH TO ACCELERATE THE TRAINING OF CONVOLUTIONAL NEURAL NETWORKS BY TUNING THE HYPERPARAMETERS OF LEARNING

2020 ◽  
Vol 2 (2) ◽  
pp. 32-37
Author(s):  
P. RADIUK ◽  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Video Processing ◽  
Network Architecture ◽  
Random Search ◽  
Machine Learning Algorithms ◽  
Language Recognition ◽  
Data Set ◽  
Training Time

Over the last decade, a set of machine learning algorithms called deep learning has led to significant improvements in computer vision, natural language recognition and processing. This has led to the widespread use of a variety of commercial, learning-based products in various fields of human activity. Despite this success, the use of deep neural networks remains a black box. Today, the process of setting hyperparameters and designing a network architecture requires experience and a lot of trial and error and is based more on chance than on a scientific approach. At the same time, the task of simplifying deep learning is extremely urgent. To date, no simple ways have been invented to establish the optimal values of learning hyperparameters, namely learning speed, sample size, data set, learning pulse, and weight loss. Grid search and random search of hyperparameter space are extremely resource intensive. The choice of hyperparameters is critical for the training time and the final result. In addition, experts often choose one of the standard architectures (for example, ResNets and ready-made sets of hyperparameters. However, such kits are usually suboptimal for specific practical tasks. The presented work offers an approach to finding the optimal set of hyperparameters of learning ZNM. An integrated approach to all hyperparameters is valuable because there is an interdependence between them. The aim of the work is to develop an approach for setting a set of hyperparameters, which will reduce the time spent during the design of ZNM and ensure the efficiency of its work. In recent decades, the introduction of deep learning methods, in particular convolutional neural networks (CNNs), has led to impressive success in image and video processing. However, the training of CNN has been commonly mostly based on the employment of quasi-optimal hyperparameters. Such an approach usually requires huge computational and time costs to train the network and does not guarantee a satisfactory result. However, hyperparameters play a crucial role in the effectiveness of CNN, as diverse hyperparameters lead to models with significantly different characteristics. Poorly selected hyperparameters generally lead to low model performance. The issue of choosing optimal hyperparameters for CNN has not been resolved yet. The presented work proposes several practical approaches to setting hyperparameters, which allows reducing training time and increasing the accuracy of the model. The article considers the function of training validation loss during underfitting and overfitting. There are guidelines in the end to reach the optimization point. The paper also considers the regulation of learning rate and momentum to accelerate network training. All experiments are based on the widespread CIFAR-10 and CIFAR-100 datasets.

scholarly journals Reionization Models Classifier using 21cm Map Deep Learning

2017 ◽  
Vol 12 (S333) ◽  
pp. 47-51
Author(s):  
Sultan Hassan ◽  
Adrian Liu ◽  
Saul Kohn ◽  
James E. Aguirre ◽  
Paul La Plante ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Power Spectrum ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Next Generation ◽  
Simple Network

AbstractNext-generation 21cm observations will enable imaging of reionization on very large scales. These images will contain more astrophysical and cosmological information than the power spectrum, and hence providing an alternative way to constrain the contribution of different reionizing sources populations to cosmic reionization. Using Convolutional Neural Networks, we present a simple network architecture that is sufficient to discriminate between Galaxy-dominated versus AGN-dominated models, even in the presence of simulated noise from different experiments such as the HERA and SKA.

scholarly journals Real Time Face Detection using DNN with Raspberry Pi 4

2019 ◽  
Vol 8 (4) ◽  
pp. 9771-9778
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Face Recognition ◽  
Human Brain ◽  
Raspberry Pi ◽  
Application Range ◽  
Emerging Trends ◽  
The Face ◽  
Image Pixels

The concept of face recognition is in the emerging trends nowadays ,because of its wide application range .Usually ,the face recognition is used in the surveillance ,security and Here, Face recognition is used to allocate attendance for a candidate.Deep neural networks is a group of artificial intelligence entirely based on neural networks, because the algorithm will imitate the human brain, so deep learning can be a kind of imitation of the human brain.Local Binary Pattern (LBP) is a basic but also very advanced creaminess operator that names image pixels through thresholding every pixel's district and considers the outcome as just a binary number.If the recognised face is not authenticated or if unauthorised person is identified by the system ,it immediately alerts the server and the classroom door remains closed. In this project we have created our own database with faculty and students of our section using Logitech C270 HD camera with resolution of 720p/30fps

ADAPTIVE CLASSIFIER INTEGRATION FOR INVARIANT FACE RECOGNITION (ACIIFR)

2002 ◽  
Vol 16 (06) ◽  
pp. 749-772 ◽  
Author(s):  
G. A. KHUWAJA ◽  
M. S. LAGHARI
Keyword(s):  
Face Recognition ◽  
Network Architecture ◽  
Recognition Rate ◽  
Recognition Task ◽  
Recognition System ◽  
Face Image ◽  
Divide And Conquer ◽  
Accuracy Rate ◽  
Learning Time ◽  
The Face

The integration of multiple classifiers promises higher classification accuracy and robustness than can be obtained with a single classifier. We address two problems: (a) automatic recognition of human faces using a novel fusion approach based on an adaptive LVQ network architecture, and (b) improve the face recognition up to 100% while maintaining the learning time per face image constant, which is an scalability issue. The learning time per face image of the recognition system remains constant irrespective of the data size. The integration of the system incorporates the "divide and conquer" modularity principles, i.e. divide the learning data into small modules, train individual modules separately using compact LVQ model structure and still encompass all the variance, and fuse trained modules to achieve recognition rate nearly 100%. The concept of Merged Classes (MCs) is introduced to enhance the accuracy rate. The proposed integrated architecture has shown its feasibility using a collection of 1130 face images of 158 subjects from three standard databases, ORL, PICS and KU. Empirical results yield an accuracy rate of 100% on the face recognition task for 40 subjects in 0.056 seconds per image. Thus, the system has shown potential to be adopted for real time application domains.

scholarly journals Implications of Pooling Strategies in Convolutional Neural Networks: A Deep Insight

2019 ◽  
Vol 44 (3) ◽  
pp. 303-330 ◽  
Author(s):  
Shallu Sharma ◽  
Rajesh Mehra
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Computational Cost ◽  
Activation Function ◽  
Training Time ◽  
Pooling Strategies ◽  
Deep Cnn ◽  
And Training

Abstract Convolutional neural networks (CNN) is a contemporary technique for computer vision applications, where pooling implies as an integral part of the deep CNN. Besides, pooling provides the ability to learn invariant features and also acts as a regularizer to further reduce the problem of overfitting. Additionally, the pooling techniques significantly reduce the computational cost and training time of networks which are equally important to consider. Here, the performances of pooling strategies on different datasets are analyzed and discussed qualitatively. This study presents a detailed review of the conventional and the latest strategies which would help in appraising the readers with the upsides and downsides of each strategy. Also, we have identified four fundamental factors namely network architecture, activation function, overlapping and regularization approaches which immensely affect the performance of pooling operations. It is believed that this work would help in extending the scope of understanding the significance of CNN along with pooling regimes for solving computer vision problems.

scholarly journals xCos: An Explainable Cosine Metric for Face Verification Task

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-16
Author(s):  
Yu-Sheng Lin ◽  
Zhe-Yu Liu ◽  
Yu-An Chen ◽  
Yu-Siang Wang ◽  
Ya-Liang Chang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Recognition Task ◽  
High Accuracy ◽  
Face Verification ◽  
Verification Task ◽  
Deep Convolutional Neural Networks ◽  
Explainable Ai ◽  
The Face ◽  
Very High

We study the XAI (explainable AI) on the face recognition task, particularly the face verification. Face verification has become a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, and automatic personal log-on for mobile devices. With the increasing amount of data, deep convolutional neural networks can achieve very high accuracy for the face verification task. Beyond exceptional performances, deep face verification models need more interpretability so that we can trust the results they generate. In this article, we propose a novel similarity metric, called explainable cosine ( xCos ), that comes with a learnable module that can be plugged into most of the verification models to provide meaningful explanations. With the help of xCos , we can see which parts of the two input faces are similar, where the model pays its attention to, and how the local similarities are weighted to form the output xCos score. We demonstrate the effectiveness of our proposed method on LFW and various competitive benchmarks, not only resulting in providing novel and desirable model interpretability for face verification but also ensuring the accuracy as plugging into existing face recognition models.

Sign in / Sign up

Export Citation Format

Share Document