scholarly journals Comparison of Viola-Jones And Kanade-Lucas-Tomasi Face Detection Algorithms

2017 ◽  
Vol 10 (1) ◽  
pp. 151-159
Author(s):  
Kamath Aashish ◽  
A. Vijayalakshmi
Keyword(s):  
Face Detection ◽  
Mobile Phones ◽  
Detection Algorithm ◽  
Digital Cameras ◽  
Detection Algorithms ◽  
Single Face ◽  
Recognition Systems ◽  
Cctv Surveillance ◽  
Common Face ◽  
Detection Technologies

Face detection technologies are used in a large variety of applications like advertising, entertainment, video coding, digital cameras, CCTV surveillance and even in military use. It is especially crucial in face recognition systems. You can’t recognise faces that you can’t detect, right? But a single face detection algorithm won’t work in the same way in every situation. It all comes down to how the algorithm works. For example, the Kanade-Lucas-Tomasi algorithm makes use of spatial common intensity transformation to direct the deep search for the position that shows the best match. It is much faster than other traditional techniques for checking far fewer potential matches between pictures. Similarly, another common face detection algorithm is the Viola-Jones algorithm that is the most widely used face detection algorithm. It is used in most digital cameras and mobile phones to detect faces. It uses cascades to detect edges like the nose, the ears etc. However, if there is a group of people and their faces are close to each other, the algorithm might not work that well as edges tend to overlap in a crowd. It might not detect individual faces. Therefore, in this work, we test both the Viola-Jones and the Kanade-Lucas-Tomasi algorithm for each image to find out which algorithm works best in which scenario.

scholarly journals DTFA-Net: Dynamic and Texture Features Fusion Attention Network for Face Antispoofing

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Xin Cheng ◽  
Hongfei Wang ◽  
Jingmei Zhou ◽  
Hui Chang ◽  
Xiangmo Zhao ◽  
...  
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Feature Fusion ◽  
Texture Features ◽  
Replay Attack ◽  
Attention Network ◽  
Detection Failure ◽  
The Face ◽  
Recognition Systems ◽  
Common Face

For face recognition systems, liveness detection can effectively avoid illegal fraud and improve the safety of face recognition systems. Common face attacks include photo printing and video replay attacks. This paper studied the differences between photos, videos, and real faces in static texture and motion information and proposed a living detection structure based on feature fusion and attention mechanism, Dynamic and Texture Fusion Attention Network (DTFA-Net). We proposed a dynamic information fusion structure of an interchannel attention block to fuse the magnitude and direction of optical flow to extract facial motion features. In addition, for the face detection failure of HOG algorithm under complex illumination, we proposed an improved Gamma image preprocessing algorithm, which effectively improved the face detection ability. We conducted experiments on the CASIA-MFSD and Replay Attack Databases. According to experiments, the DTFA-Net proposed in this paper achieved 6.9% EER on CASIA and 2.2% HTER on Replay Attack that was comparable to other methods.

scholarly journals A Joint Learning Approach to Face Detection in Wavelet Compressed Domain

2014 ◽  
Vol 2014 ◽  
pp. 1-13
Author(s):  
Szu-Hao Huang ◽  
Shang-Hong Lai
Keyword(s):  
Face Detection ◽  
Learning Algorithm ◽  
Feature Space ◽  
Detection Algorithm ◽  
Feature Representation ◽  
Compressed Domain ◽  
Discrimination Power ◽  
Detection Algorithms ◽  
The Face ◽  
Active Research

Face detection has been an important and active research topic in computer vision and image processing. In recent years, learning-based face detection algorithms have prevailed with successful applications. In this paper, we propose a new face detection algorithm that works directly in wavelet compressed domain. In order to simplify the processes of image decompression and feature extraction, we modify the AdaBoost learning algorithm to select a set of complimentary joint-coefficient classifiers and integrate them to achieve optimal face detection. Since the face detection on the wavelet compression domain is restricted by the limited discrimination power of the designated feature space, the proposed learning mechanism is developed to achieve the best discrimination from the restricted feature space. The major contributions in the proposed AdaBoost face detection learning algorithm contain the feature space warping, joint feature representation, ID3-like plane quantization, and weak probabilistic classifier, which dramatically increase the discrimination power of the face classifier. Experimental results on the CBCL benchmark and the MIT + CMU real image dataset show that the proposed algorithm can detect faces in the wavelet compressed domain accurately and efficiently.

scholarly journals Implementing Facial Recognition by Interfacing MATLAB Along with Arduino

2021 ◽  
Vol 10 (4) ◽  
pp. 66-71
Author(s):  
E. Ramkumar ◽  
T. Guna ◽  
S.M. Dharshan ◽  
V.S. Ashok Ramanan
Keyword(s):  
Face Recognition ◽  
Face Detection ◽  
Mobile Phones ◽  
Electronic Device ◽  
Facial Recognition ◽  
Residential Buildings ◽  
Biometric Authentication ◽  
Digital Cameras ◽  
Industrial Sectors ◽  
Detection Rule

Facial recognition has become one of the recent trends in attracting abundant attention within the society of social media network. The face is flat and therefore needs plenty of mathematical computations. Facial knowledge has become one in every of the foremost necessary biometric, we tend to witness it from the day-to-day gadgets like mobile phones. Every transportable electronic device currently being discharged includes a camera embedded in it. Network access management via face recognition not solely makes hackers just about not possible to steal one's "password", however conjointly will increase the user-friendliness in human-computer interaction. For the applications of videophone and conference, the help of face recognition conjointly provides an additional economical secret writing theme. Face detection technologies are employed in an oversized kind of applications like advertising, diversion, video secret writing, digital cameras, CCTV police investigation, and even in military use. Totally different algorithms are used for biometric authentication. The Kanade-Lucas-Tomasi rule makes use of abstraction common intensity transformation to direct the deep explore for the position that shows the simplest match. Another common face detection rule is that the Viola-Jones rule that's the foremost wide used face detection rule. It's employed in most digital cameras and mobile phones to notice faces. It uses cascades to notice edges just like the nose, the ears, etc. Hence, during this paper, we've got planned the Viola-Jones rule because the best one supported our application. The rule is employed within the biometric authentication of individuals and also the pictures are kept during processing. The kept information is employed for recognizing the faces and if the information matches, an impression signal is given to the controller. The MATLAB software is employed to relinquish control signals to the motor, which is employed for gap and shutting the door. The input image is fed by a digital camera and also the image is processed within MATLAB. The output is given to the external controller interfaced with MATLAB. The image process field has several sub-fields, biometric authentication is one in each of them because it gains additional quality for security functions these days. The planned system can be employed in residential buildings, malls, and industrial sectors. Thus, this technique is helpful for homemakers to be safer in their homes.

scholarly journals Performance Tuning Techniques for Face Detection Algorithms on GPGPU

2020 ◽  
Vol 10 (2) ◽  
pp. 103-108
Author(s):  
Yara M. Abdelaal ◽  
M. Fayez ◽  
Samy Ghoniemy ◽  
Ehab Abozinadah ◽  
H. M. Faheem
Keyword(s):  
Face Detection ◽  
Performance Tuning ◽  
Double Precision ◽  
Occupancy Rate ◽  
Register File ◽  
File Size ◽  
Detection Algorithms ◽  
And Performance ◽  
Gpu Architectures ◽  
Common Face

Face detection algorithms varies in speed and performance on GPUs. Different algorithms can report different speeds on different GPUs that are not governed by linear or nearlinear approximations. This is due to many factors such as register file size, occupancy rate of the GPU, speed of the memory, and speed of double precision processors. This paper studies the most common face detection algorithms LBP and Haar-like and study the bottlenecks associated with deploying both algorithms on different GPU architectures. The study focuses on the bottlenecks and the associated techniques to resolve them based on the different GPUs specifications.

scholarly journals PIG FACE DETECTION ALGORITHM AND SUPPLEMENTARY LIGHT SYSTEM DESIGN BASED ON OPEN MV3

2021 ◽  
pp. 453-460
Author(s):  
Hongwen Yan ◽  
Zhenyu Liu ◽  
Qingliang Cui
Keyword(s):  
Data Acquisition ◽  
Face Detection ◽  
Detection Algorithm ◽  
Great Difficulty ◽  
Digital Cameras ◽  
Image Brightness ◽  
Essential Step ◽  
Light System ◽  
Intelligent Management ◽  
Low Efficiency

Individual pig recognition is an essential step for accurate breeding and intelligent management of pigs. To realize individual pig identification, applicable dataset of pigs needs to be built. For pigs’ behaviour is difficult to control, the data acquisition is of great difficulty and low efficiency. In addition, few reports on pig face detection are there at home and abroad, thus, face data acquisition faces more difficulty. In this study, double open mv3 digital cameras were adopted, and the approach of starting the pig face acquisition program by acquiring pig figure with a vertical camera to calculate the slope of their back before sending a signal to the horizontal camera was adopted. The image brightness was calculated based on RGB function: when the value was less than 90, the supplementary light system would be started by L298 module, and when the value was more than 120, the acquisition system would be restarted. This study provides a reference for solving the key problem of automatic acquisition of pig face data for pig face detection.

scholarly journals A web-based application for face detection in real-time images and videos

2022 ◽  
Vol 2161 (1) ◽  
pp. 012071
Author(s):  
Mehul Arora ◽  
Sarthak Naithani ◽  
Anu Shaju Areeckal
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Face Detection ◽  
User Interfaces ◽  
Detection Algorithm ◽  
Frame Rate ◽  
Web Based ◽  
Detection Algorithms ◽  
Haar Cascade ◽  
The Web

Abstract Face detection is widely used in the consumer industry such as advertising, user interfaces, video streaming apps and in many security applications. Every application has its own demands and constraints, and hence cannot be fulfilled by a single face detection algorithm. In this work, we developed an interactive web-based application for face detection in real-time images and videos. Pretrained face detection algorithms, namely Haar cascade classifier, HOG-based frontal face detector, Multi-task Cascaded Convolutional Neural Network (MTCNN) and Deep Neural Network (DNN), were used in the web-based application. A performance analysis of these face detection algorithms is done for various parameters such as different lighting conditions, face occlusion and frame rate. The web app interface can be used for an easy comparison of different face detection algorithms. This will help the user to decide on the algorithm that suits their purpose and requirements for various applications.

A dual U-Net algorithm for automating feature extraction from satellite imagery

2021 ◽  
pp. 154851292098354
Author(s):  
Samuel Humphries ◽  
Trevor Parker ◽  
Bryan Jonas ◽  
Bryan Adams ◽  
Nicholas J Clark
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Satellite Images ◽  
Detection Algorithm ◽  
Military Operations ◽  
Detection Algorithms ◽  
Us Military ◽  
Standard Product ◽  
Different Types ◽  
Road Intersections

Quick identification of building and roads is critical for execution of tactical US military operations in an urban environment. To this end, a gridded, referenced, satellite images of an objective, often referred to as a gridded reference graphic or GRG, has become a standard product developed during intelligence preparation of the environment. At present, operational units identify key infrastructure by hand through the work of individual intelligence officers. Recent advances in Convolutional Neural Networks, however, allows for this process to be streamlined through the use of object detection algorithms. In this paper, we describe an object detection algorithm designed to quickly identify and label both buildings and road intersections present in an image. Our work leverages both the U-Net architecture as well the SpaceNet data corpus to produce an algorithm that accurately identifies a large breadth of buildings and different types of roads. In addition to predicting buildings and roads, our model numerically labels each building by means of a contour finding algorithm. Most importantly, the dual U-Net model is capable of predicting buildings and roads on a diverse set of test images and using these predictions to produce clean GRGs.

scholarly journals A novel algorithm to detect non-wear time from raw accelerometer data using deep convolutional neural networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shaheen Syed ◽  
Bente Morseth ◽  
Laila A. Hopstock ◽  
Alexander Horsch
Keyword(s):  
Threshold Value ◽  
Detection Algorithm ◽  
Classification Model ◽  
Type I ◽  
Accelerometer Data ◽  
Deep Convolutional Neural Networks ◽  
Major Drawback ◽  
Wear Time ◽  
Detection Algorithms ◽  
Type Ii Errors

AbstractTo date, non-wear detection algorithms commonly employ a 30, 60, or even 90 mins interval or window in which acceleration values need to be below a threshold value. A major drawback of such intervals is that they need to be long enough to prevent false positives (type I errors), while short enough to prevent false negatives (type II errors), which limits detecting both short and longer episodes of non-wear time. In this paper, we propose a novel non-wear detection algorithm that eliminates the need for an interval. Rather than inspecting acceleration within intervals, we explore acceleration right before and right after an episode of non-wear time. We trained a deep convolutional neural network that was able to infer non-wear time by detecting when the accelerometer was removed and when it was placed back on again. We evaluate our algorithm against several baseline and existing non-wear algorithms, and our algorithm achieves a perfect precision, a recall of 0.9962, and an F1 score of 0.9981, outperforming all evaluated algorithms. Although our algorithm was developed using patterns learned from a hip-worn accelerometer, we propose algorithmic steps that can easily be applied to a wrist-worn accelerometer and a retrained classification model.

Sign in / Sign up

Export Citation Format

Share Document