MULTI-STEP FACE RECOGNITION FOR IMPROVING FACE DETECTION AND RECOGNITION RATE

The problem of Face detection and recognition is becoming a challenge due to the wide variety of faces and the complexity of the noises and background of image. In this paper we have used C-sharp and Haar algorithm to detect the face. First in this paper the image is taken with a web-camera, storing it in the database and then once again when the person comes in the frame the name of the person is displayed. This paper is done in C-sharp which was a bit difficult for us to do and we have combined both the face detection and the recognition. The proposed method has good output and a good recognition rate. The limitation of the paper is that it does not display the name of the person above the face. In the future work will be carried on the above said topic. While developing the code some sample codes in python but those were basic programs. So this paper aims to find a solution for it and developed in C-sharp. In finding the XML file of haarcascade frontal face detection we found some problems and had to do a bit of research in finding it. The code for face detection and face recognition were found in different places and in this paper the codes for the both has been combined and found some difficulty. To overcome the basic programs we have written the code in C-sharp and the difficulty which we faced in combining the two codes have been solved. The solution has been successfully implemented and the code is fully running and the output has been successfully achieved.

Download Full-text

FACE DETECTION AND RECOGNITION USING MAXIMUM LIKELIHOOD CLASSIFIERS ON GABOR GRAPHS

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001409007211 ◽

2009 ◽

Vol 23 (03) ◽

pp. 433-461 ◽

Cited By ~ 7

Author(s):

MANUEL GÜNTHER ◽

ROLF P. WÜRTZ

Keyword(s):

Face Recognition ◽

Maximum Likelihood ◽

Face Detection ◽

Recognition System ◽

Similarity Functions ◽

Expression Variation ◽

Face Recognition System ◽

Face Detection And Recognition ◽

Ml Estimator ◽

Detection And Recognition

We present an integrated face recognition system that combines a Maximum Likelihood (ML) estimator with Gabor graphs for face detection under varying scale and in-plane rotation and matching as well as a Bayesian intrapersonal/extrapersonal classifier (BIC) on graph similarities for face recognition. We have tested a variety of similarity functions and achieved verification rates (at FAR 0.1%) of 90.5% on expression-variation and 95.8% on size-varying frontal images within the CAS-PEAL database. Performing Experiment 1 of FRGC ver2.0, the method achieved a verification rate of 72%.

Download Full-text

Sparse Neural Network for horse face detection in a Smart Riding Club Biometric System

10.36227/techrxiv.16698940 ◽

2021 ◽

Author(s):

Islem Jarraya ◽

Wael Ouarda ◽

Fatma BenSaid ◽

Adel Alimi

Keyword(s):

Neural Network ◽

Face Detection ◽

Detection System ◽

Recognition Rate ◽

Biometric System ◽

Training Time ◽

Face Detection And Recognition ◽

Global And Local ◽

Sparse Features ◽

Detection And Recognition

Horses and breeders need to be safe on the farm and the riding club. On account of the great value of the horse, the breeder needs to protect it from theft and disease. In this context, it is important to detect and to recognize the identity of each horse for security reasons. In fact, this paper proposes a Smart Riding Club Biometric System (SRCBS) consisting in automatically detecting and recognizing horses as well as humans. The proposed system is based on the facial biometrics for a horse and the gait biometrics for a human due to their simplicity and intuitiveness in an uncontrolled environment. The present work focuses mainly on horse face detection and recognition. Animal face detection is still extremely difficult given the fact that face textures and shapes are grossly diverse. In addition, recent detectors require a huge dataset for training and represent a huge number of parameters and layers, leading to so much training time. For resolving these problems and also for a useful detection system, this paper proposes a Sparse Neural Network (SNN) based on sparse features for horse face detection.<br>Different global and local features were performed to identify horses and humans for the recognition process. Due to the unavailability of horse databases, this paper presents a new benchmark for horse detection and recognition in order to evaluate our proposed system. This system achieved an average precision equal to 90% for horse face detection and a recognition rate equal to 99.89% for horse face identification.

Download Full-text

Intruder detection and recognition using different image processing techniques for a proactive surveillance

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v24.i2.pp843-852 ◽

2021 ◽

Vol 24 (2) ◽

pp. 843

Author(s):

Nelson C. Rodelas ◽

Melvin A. Ballera

Keyword(s):

Image Processing ◽

Face Recognition ◽

Face Detection ◽

Research Problem ◽

Recognition Algorithm ◽

Evaluation Framework ◽

Image Processing Techniques ◽

Face Detection And Recognition ◽

Processing Techniques ◽

Detection And Recognition

To innovate a proactive surveillance camera, there is a need for efficient face detection and recognition algorithm. The researchers used one of the ViolaJones algorithm and used different image processing techniques to recognize intruders or not. The goal of the research is to recognize the fastest way on how the homeowners will be informed if an intruder or burglar enters their home using a proactive surveillance device. This device was programmed based on the different recognition algorithms and a criteria evaluation framework that could recognize intruders and burglars and the design used was developmental research to satisfy the research problem. The researchers used the Viola-Jones algorithm for face detection and five algorithms for face recognition. The criteria evaluation was used to identify the best face recognition algorithm and was tested in a real-world situation and captured a series of images camera and processed by proactive face detection and recognition. The result shows that the system can detect and recognize intruders and proactively send a notification to the homeowners via mobile application. It is concluded that the system can recognize the intruders and proactively notify the household members using the mobile applications and activate the alarm system of the house.

Download Full-text

Face with Mask Detection and Recognition for Smart Attendance System

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.36615 ◽

2021 ◽

Vol 9 (VII) ◽

pp. 1586-1591

Author(s):

Shweta Panjabrao Dhawale

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Face Recognition ◽

Face Detection ◽

Face Mask ◽

Learning Framework ◽

The Face ◽

Face Detection And Recognition ◽

Python Programming ◽

Detection And Recognition

In this paper we will see the face mask detection and recognition for smart attendance system. In current pandemic situation our proposed system is very useful. We have used here face algorithm technique, python programming and to capture the images open cv is used., open cv2 now comes with a very new face recognizer class for the face recognition and popular computer vision liberaay started by intel in 1999. Open cv released under BSD licence that’s why used in the academic projects. We have used the concept of deep learning framework for the detection of faces. our aim is to present the study of previous attempts at face detection and recognition for smart attendance system by using deep learning .these is rapidly growing technology with its application in various aspects.

Download Full-text

Challenges in Face Detection and Recognition techniques

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.h6307.069820 ◽

2020 ◽

Vol 9 (8) ◽

pp. 221-224

Keyword(s):

Face Recognition ◽

Face Detection ◽

Recognition System ◽

Research Paper ◽

Facial Features ◽

Image Information ◽

Public Crisis ◽

Face Recognition System ◽

Face Detection And Recognition ◽

Detection And Recognition

Face Recognition System is popular topic in the biometric world .This system provide Features to detect the person’s face and identify on basis of existing records in database .The aim of this study is to described how to show various facial features of an image. Face Recognition system, based on Biometric AI, uniquely finds out a person by analyzing the person's facial textures and shape. In this paper, our aim is to study various face detect and recognition techniques such as Harr Like Feature Algorithm resulting to retort criminality and public crisis. Also, some facial recognition approaches PCA and LDA have been discussed in the research paper for abstracting the image information.

Download Full-text

Class Monitoring System Tools MTCNN and Haarcascade Classifier

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i3.12.17609 ◽

2018 ◽

Vol 7 (3.12) ◽

pp. 951

Author(s):

Aditya Vikram Bhattacharya ◽

Mrinalini Khanna ◽

Akshay Tripathi ◽

S Murugaveni

Keyword(s):

Face Recognition ◽

Monitoring System ◽

Face Detection ◽

Cognitive Tools ◽

Time Stamp ◽

Time Stamps ◽

Face Detection And Recognition ◽

Further Development ◽

Detection And Recognition

The project aims towards the assistance of teachers at the time of taking attendance. The system solely focuses on face detection and recognition. The tools used to device the system are API’s offered by Python 3.6, Open CV(for detection) and a few cognitive tools provided by Azure.The basic idea behind the project is face recognition linked to a database backend. The information of the student attending the class is stored here. The entire attendance is associated with two types of time stamps incorporated at the server end. The time stamp helps to keep a track of the hour conducted and the time for which number of people attended the class. Exceptions in the time stamp would be incorporated in order to cater for the students leaving the class or trying to bunk the class. In case of further exceptionsin the time stamp will be scope of further development of the system. All queries or conditions of the students will be answered by the system on communication with the admin. If the admin finds that the system was at fault then it can always be fixed by the admin for smooth functioning of the class monitoring system.

Download Full-text

Video Summarization Based on Human Face Detection and Recognition

Video Data Management and Information Retrieval ◽

10.4018/978-1-59140-571-9.ch015 ◽

2011 ◽

pp. 347-378

Author(s):

Hong-Mo Je ◽

Daijin Kim ◽

Sung-Yang Bang

Keyword(s):

Face Recognition ◽

Face Detection ◽

Video Summarization ◽

Human Face ◽

The Real ◽

Facial Information ◽

Human Face Detection ◽

Face Detection And Recognition ◽

Summarization System ◽

Detection And Recognition

In this chapter, we deal with video summarization using human facial information by face detection and recognition. Many methods of face detection and face recognition are introduced as both theoretical and practical aspects. Also, we describe the real implementation of the video summarization system based on face detection and recognition

Download Full-text

Sparse Neural Network for horse face detection in a Smart Riding Club Biometric System

10.36227/techrxiv.16698940.v1 ◽

2021 ◽

Author(s):

Islem Jarraya ◽

Wael Ouarda ◽

Fatma BenSaid ◽

Adel Alimi

Keyword(s):

Neural Network ◽

Face Detection ◽

Detection System ◽

Recognition Rate ◽

Biometric System ◽

Training Time ◽

Face Detection And Recognition ◽

Global And Local ◽

Sparse Features ◽

Detection And Recognition

Horses and breeders need to be safe on the farm and the riding club. On account of the great value of the horse, the breeder needs to protect it from theft and disease. In this context, it is important to detect and to recognize the identity of each horse for security reasons. In fact, this paper proposes a Smart Riding Club Biometric System (SRCBS) consisting in automatically detecting and recognizing horses as well as humans. The proposed system is based on the facial biometrics for a horse and the gait biometrics for a human due to their simplicity and intuitiveness in an uncontrolled environment. The present work focuses mainly on horse face detection and recognition. Animal face detection is still extremely difficult given the fact that face textures and shapes are grossly diverse. In addition, recent detectors require a huge dataset for training and represent a huge number of parameters and layers, leading to so much training time. For resolving these problems and also for a useful detection system, this paper proposes a Sparse Neural Network (SNN) based on sparse features for horse face detection.<br>Different global and local features were performed to identify horses and humans for the recognition process. Due to the unavailability of horse databases, this paper presents a new benchmark for horse detection and recognition in order to evaluate our proposed system. This system achieved an average precision equal to 90% for horse face detection and a recognition rate equal to 99.89% for horse face identification.

Download Full-text

SINGLE-SHOT FACE DETECTION AND RECOGNITION BASED ON CNN

Vestnik komp iuternykh i informatsionnykh tekhnologii ◽

10.14489/vkit.2021.04.pp.011-020 ◽

2021 ◽

pp. 11-20

Author(s):

Yu. V. Vizilter ◽

V. S. Gorbatsevich ◽

A. S. Moiseenko

Keyword(s):

Face Recognition ◽

Face Detection ◽

Input Image ◽

Fine Tuning ◽

Single Shot ◽

Face Database ◽

Face Images ◽

Face Detection And Recognition ◽

Number Of Faces ◽

Detection And Recognition

The paper proposes an architecture and training method of a deep convolutional neural network for simultaneous face detection and recognition. The implemented approach combines the ideas of SSD (Single Shot Detector) and Faster R-CNN (Region proposal Convolutional Neural Networks) algorithms. Face detection is performed similarly to single-stage detection algorithms, and then a biometric template is built by employing RoI (Region of Interest) pooling layers and using the separate branch of the neural network. Training process includes three stages: pretraining of thebasic CNN for face recognition on face images, fine-tuning by using RoI pooling on in painted face images, adding SSD layers and fine-tuning on face detection. Wherein, at the latter stage, training is performed by using shared layers technology for two databases simultaneously. The main feature of the algorithm is high processing speed, which does not depend on the number of faces in the input image. For example, in case of using ResNet-34 as the core architecture for the algorithm, the required time for detecting faces and building biometric templates on an image with 100 faces is less than 13 ms. For training purposes we use CASIA-WebFace for face recognition task and Wider Face for face detection task. Testing is performed on FDDB (Face Detection Dataset and Benchmark), since this database is closer to practical applications than Wider. As long as the main practical task the developed method is intended for is face reidentification, we use Fei Face DataBase for face recognition quality testing. We obtain TPR (True Positive Rate) = 0.928@1000 on FDDB Face DataBase and FAR (Face Acceptance Rate) = 0.03309@FRR (Face Rejection Rate) = 10–4. Therefore, the proposed algorithm allows solving face detection and reidentification tasks in real time with any number of faces on an input image.

Download Full-text