Enhanced MSRCR optical frequency segmented filter algorithm for alow-light vehicle environment

2021 ◽  
pp. 095440702110518
Author(s):  
Xin Lai ◽  
Hang Chen
Keyword(s):  
Face Detection ◽  
Large Scale ◽  
Frequency Noise ◽  
Low Light ◽  
Multi Scale ◽  
Guided Filtering ◽  
The Face ◽  
Color Restoration ◽  
Light Vehicle ◽  
Face Detector

To solve the problem of difficult face detection in a low illumination vehicle environment, a novel multi-scale retinex color restoration (MSRCR) approach exploiting the RGB three-channel decomposition and guided filtering (MSRCR-3CGF) is proposed. The MSRCR algorithm is employed to remove the artifacts and interference of low-light in the image based on the face detector using a multi-task cascaded convolutional neural network (MTCNN). The enhanced face image is decomposed into RGB, and GF is applied to each channel. The proposed method is tested on three widely used datasets: Dark Face, large-scale CelebFaces attributes (CelebA) and WIDER FACE, and an actual low-light scene in vehicles. The experimental results show that the proposed method suppresses the high-frequency noise of MSRCR, whilst improving the image enhancement and accuracy in the face detection in a low-light vehicle environment.

scholarly journals Mask Detection and Tracing System

2021 ◽  
pp. 406-412
Author(s):  
Sanket Shete ◽  
Kiran Tingre ◽  
Ajay Panchal ◽  
Vaibhav Tapse ◽  
Prof. Bhagyashri Vyas
Keyword(s):  
Neural Networks ◽  
Face Detection ◽  
Large Scale ◽  
Face Mask ◽  
Detection Algorithm ◽  
Detection Task ◽  
Loss Of Face ◽  
Satisfactory Performance ◽  
Training Samples ◽  
The Face

Covid19 has given a new identity for wearing a mask. It is meaningful when these masked faces are detected accurately and efficiently. As a unique face detection task, face mask detection is much more difficult because of extreme occlusions which leads to the loss of face details. Besides, there is almost no existing large-scale accurately labelled masked face dataset, which increase the difficulty of face mask detection. The system encourages to use CNN-based deep learning algorithms which has done vast progress towards researches in face detection In this paper, we propose novel CNN-based method which is formed of three convolutional neural networks to detect face mask. Besides, because of the shortage of face masked training samples, we propose a new dataset called” face mask dataset” to finetune our CNN models. We evaluate our proposed face mask detection algorithm on the face mask testing set, and it achieves satisfactory performance

scholarly journals A Support Vector Data Description Committee for Face Detection

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Yi-Hung Liu ◽  
Yung Ting ◽  
Shian-Shing Shyu ◽  
Chang-Kuo Chen ◽  
Chung-Lin Lee ◽  
...  
Keyword(s):  
Face Detection ◽  
Kernel Principal Component Analysis ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Detection Accuracy ◽  
Vector Data ◽  
Data Set ◽  
Data Description ◽  
The Face ◽  
Face Detector

Face detection is a crucial prestage for face recognition and is often treated as a binary (face and nonface) classification problem. While this strategy is simple to implement, face detection accuracy would drop when nonface training patterns are undersampled. To avoid these problems, we propose in this paper a one-class learning-based face detector called support vector data description (SVDD) committee, which consists of several SVDD members, each of which is trained on a subset of face patterns. Nonfaces are not required in the training of the SVDD committee. Therefore, the face detection accuracy of SVDD committee is independent of the nonface training patterns. Moreover, the proposed SVDD committee is also able to improve generalization ability of the original SVDD when the face data set has a multicluster distribution. Experiments carried out on the extended MIT face data set show that the proposed SVDD committee can achieve better face detection accuracy than the widely used SVM face detector and performs better than other one-class classifiers, including the original SVDD and the kernel principal component analysis (Kernel PCA).

scholarly journals Real-Time Multi-Scale Face Detector on Embedded Devices

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2158 ◽  
Author(s):  
Xu Zhao ◽  
Xiaoqing Liang ◽  
Chaoyang Zhao ◽  
Ming Tang ◽  
Jinqiao Wang
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Class Imbalance ◽  
Network Capacity ◽  
Raspberry Pi ◽  
Class Imbalance Problem ◽  
Embedded Devices ◽  
Basic Step ◽  
The Face ◽  
Face Detector

Face detection is the basic step in video face analysis and has been studied for many years. However, achieving real-time performance on computation-resource-limited embedded devices still remains an open challenge. To address this problem, in this paper we propose a face detector, EagleEye, which shows a good trade-off between high accuracy and fast speed on the popular embedded device with low computation power (e.g., the Raspberry Pi 3b+). The EagleEye is designed to have low floating-point operations per second (FLOPS) as well as enough capacity, and its accuracy is further improved without adding too much FLOPS. Specifically, we design five strategies for building efficient face detectors with a good balance of accuracy and running speed. The first two strategies help to build a detector with low computation complexity and enough capacity. We use convolution factorization to change traditional convolutions into more sparse depth-wise convolutions to save computation costs and we use successive downsampling convolutions at the beginning of the face detection network. The latter three strategies significantly improve the accuracy of the light-weight detector without adding too much computation costs. We design an efficient context module to utilize context information to benefit the face detection. We also adopt information preserving activation function to increase the network capacity. Finally, we use focal loss to further improve the accuracy by handling the class imbalance problem better. Experiments show that the EagleEye outperforms the other face detectors with the same order of computation costs, on both runtime efficiency and accuracy.

scholarly journals Urban Vertical Farming as an Example of Nature-Based Solutions Supporting a Healthy Society Living in the Urban Environment

Resources ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 109
Author(s):  
Anna Zaręba ◽  
Alicja Krzemińska ◽  
Renata Kozik
Keyword(s):  
Social Services ◽  
Urban Agriculture ◽  
Green Infrastructure ◽  
Large Scale ◽  
Agricultural Land ◽  
Multi Scale ◽  
Vertical Farming ◽  
The Face ◽  
The Subject ◽  
The City

The subject of the article concerns vertical urban farms that play an important role in nature-based solutions and ecosystem services for the city. In the face of a changing climate, progressive environmental degradation, and the related loss of agricultural land, vertical farms can be seen as an alternative to traditional agriculture. Woven into the blue-green infrastructure of cities, they may not only constitute a base for food production, but can also create a new valuable ecological, social, and economic hub in contemporary cities, changed by the COVID-19 pandemic. The objective of this paper is to show whether it is possible to introduce various functions which support ecosystem and social services, and whether they affect measurable benefits for urban residents in a large-scale system of solutions in the field of vertical urban agriculture. This research shows that urban vertical farms can perform many functions and bring diverse benefits to the inhabitants of cities. In a multi-scale system, they allow for the creation of patchwork connections, which stabilise a specific city biome in the vertical space.

scholarly journals Selective Refinement Network for High Performance Face Detection

2019 ◽  
Vol 33 ◽  
pp. 8231-8238 ◽  
Author(s):  
Cheng Chi ◽  
Shifeng Zhang ◽  
Junliang Xing ◽  
Zhen Lei ◽  
Stan Z. Li ◽  
...  
Keyword(s):  
Receptive Field ◽  
Face Detection ◽  
High Performance ◽  
Field Enhancement ◽  
Search Space ◽  
Single Shot ◽  
The Face ◽  
Face Datasets ◽  
High Level ◽  
Face Detector

High performance face detection remains a very challenging problem, especially when there exists many tiny faces. This paper presents a novel single-shot face detector, named Selective Refinement Network (SRN), which introduces novel twostep classification and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously. In particular, the SRN consists of two modules: the Selective Two-step Classification (STC) module and the Selective Two-step Regression (STR) module. The STC aims to filter out most simple negative anchors from low level detection layers to reduce the search space for the subsequent classifier, while the STR is designed to coarsely adjust the locations and sizes of anchors from high level detection layers to provide better initialization for the subsequent regressor. Moreover, we design a Receptive Field Enhancement (RFE) block to provide more diverse receptive field, which helps to better capture faces in some extreme poses. As a consequence, the proposed SRN detector achieves state-of-the-art performance on all the widely used face detection benchmarks, including AFW, PASCAL face, FDDB, and WIDER FACE datasets. Codes will be released to facilitate further studies on the face detection problem.

Research of Facial Features Extraction Based on Improved ASM

2011 ◽  
Vol 271-273 ◽  
pp. 131-136
Author(s):  
Guang Fei Zhai ◽  
Guang Da Su ◽  
Jiong Xin Liu
Keyword(s):  
Step Length ◽  
Initial Position ◽  
Active Shape Model ◽  
Shape Model ◽  
Local Optima ◽  
Multi Scale ◽  
The Face ◽  
Global Optima ◽  
Adaptive Step ◽  
Face Detector

Traditional ASM (Active Shape Model) methods usually depend heavily on the initial facial landmark positions located by the face detector. During the fitting process the ASM model may be trapped into local optima instead of the global optima due to the inaccurate initial position selection. In this paper we present that this problem can be solved by incorporating pupil and chin localizations in adjusting the initial landmark positions, together with adaptive step length selection based on two-dimensional gradient characteristic in a multi-scale ASM model. Experiments on a face database consisting of 1000 individuals show that this method is practically effective.

Multi-scale retinex with color restoration image enhancement based on Gaussian filtering and guided filtering

2017 ◽  
Vol 31 (16-19) ◽  
pp. 1744077 ◽  
Author(s):  
Jinxiang Ma ◽  
Xinnan Fan ◽  
Jianjun Ni ◽  
Xifang Zhu ◽  
Chao Xiong
Keyword(s):  
Image Enhancement ◽  
Noise Interference ◽  
Gaussian Filtering ◽  
Multi Scale ◽  
Adaptive Weight ◽  
Guided Filtering ◽  
Color Restoration ◽  
Color Cast ◽  
Detail Enhancement ◽  
Enhancement Algorithm

In order to restore image color and enhance contrast of remote sensing image without suffering from color cast and insufficient detail enhancement, a novel improved multi-scale retinex with color restoration (MSRCR) image enhancement algorithm based on Gaussian filtering and guided filtering was proposed in this paper. Firstly, multi-scale Gaussian filtering functions were used to deal with the original image to obtain the rough illumination components. Secondly, accurate illumination components were acquired by using the guided filtering functions. Then, combining with four-direction Sobel edge detector, a self-adaptive weight selection nonlinear image enhancement was carried out. Finally, a series of evaluate metrics such as mean, MSE, PSNR, contrast and information entropy were used to assess the enhancement algorithm. The results showed that the proposed algorithm can suppress effectively noise interference, enhance the image quality and restore image color effectively.

scholarly journals KPNet: Towards Minimal Face Detector

2020 ◽  
Vol 34 (07) ◽  
pp. 12015-12022
Author(s):  
Guanglu Song ◽  
Yu Liu ◽  
Yuhang Zang ◽  
Xiaogang Wang ◽  
Biao Leng ◽  
...  
Keyword(s):  
Receptive Field ◽  
Face Detection ◽  
State Of The Art ◽  
Fine Grained ◽  
Front End ◽  
The Face ◽  
Bounding Boxes ◽  
Definition Of ◽  
Appearance Feature ◽  
Face Detector

The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors. In this work, we find that the appearance feature of a generic face is discriminative enough for a tiny and shallow neural network to verify from the background. And the essential barriers behind us are 1) the vague definition of the face bounding box and 2) tricky design of anchor-boxes or receptive field. Unlike most top-down methods for joint face detection and alignment, the proposed KPNet detects small facial keypoints instead of the whole face by in the bottom-up manner. It first predicts the facial landmarks from a low-resolution image via the well-designed fine-grained scale approximation and scale adaptive soft-argmax operator. Finally, the precise face bounding boxes, no matter how we define it, can be inferred from the keypoints. Without any complex head architecture or meticulous network designing, the KPNet achieves state-of-the-art accuracy on generic face detection and alignment benchmarks with only ∼ 1M parameters, which runs at 1000fps on GPU and is easy to perform real-time on most modern front-end chips.

Face detection in single and multiple images using different skin color models

2020 ◽  
Vol 13 ◽  
Author(s):  
Manpreet Kaur ◽  
Jasdev Bhatti ◽  
Mohit Kumar Kakkar ◽  
Arun Upmanyu
Keyword(s):  
Face Detection ◽  
Skin Color ◽  
Input Image ◽  
Morphological Operations ◽  
Reliability Model ◽  
Multiple Images ◽  
Face Region ◽  
Bounding Box ◽  
The Face ◽  
Precision And Accuracy

Introduction: Face Detection is used in many different steams like video conferencing, human-computer interface, in face detection, and in the database management of image. Therefore, the aim of our paper is to apply Red Green Blue ( Methods: The morphological operations are performed in the face region to a number of pixels as the proposed parameter to check either an input image contains face region or not. Canny edge detection is also used to show the boundaries of a candidate face region, in the end, the face can be shown detected by using bounding box around the face. Results: The reliability model has also been proposed for detecting the faces in single and multiple images. The results of the experiments reflect that the algorithm been proposed performs very well in each model for detecting the faces in single and multiple images and the reliability model provides the best fit by analyzing the precision and accuracy. Moreover Discussion: The calculated results show that HSV model works best for single faced images whereas YCbCr and TSL models work best for multiple faced images. Also, the evaluated results by this paper provides the better testing strategies that helps to develop new techniques which leads to an increase in research effectiveness. Conclusion: The calculated value of all parameters is helpful for proving that the proposed algorithm has been performed very well in each model for detecting the face by using a bounding box around the face in single as well as multiple images. The precision and accuracy of all three models are analyzed through the reliability model. The comparison calculated in this paper reflects that HSV model works best for single faced images whereas YCbCr and TSL models work best for multiple faced images.

Ban Ki-moon, 2007–2016

2018 ◽  
Author(s):  
Richard Gowan
Keyword(s):  
United States ◽  
Decision Making ◽  
Security Council ◽  
Large Scale ◽  
Central African Republic ◽  
The United States ◽  
Cautious Approach ◽  
Peacekeeping Operations ◽  
Council Decision ◽  
The Face

During Ban Ki-moon’s tenure, the Security Council was shaken by P5 divisions over Kosovo, Georgia, Libya, Syria, and Ukraine. Yet it also continued to mandate and sustain large-scale peacekeeping operations in Africa, placing major burdens on the UN Secretariat. The chapter will argue that Ban initially took a cautious approach to controversies with the Council, and earned a reputation for excessive passivity in the face of crisis and deference to the United States. The second half of the chapter suggests that Ban shifted to a more activist pressure as his tenure went on, pressing the Council to act in cases including Côte d’Ivoire, Libya, and Syria. The chapter will argue that Ban had only a marginal impact on Council decision-making, even though he made a creditable effort to speak truth to power over cases such as the Central African Republic (CAR), challenging Council members to live up to their responsibilities.

Sign in / Sign up

Export Citation Format

Share Document