Partially Covered Face Detection in Presence of Headscarf for Surveillance Applications

Hoda, Qezavati; Majidi, Babak; Manzuri, Mohammad Taghi

doi:10.1109/pria.2019.8786004

Cited by 22 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Qezavati et al [15] worked on partially covered face detection in low resolution surveillance videos of traditional Middle Eastern clothing such as headscarf, using a Haar cascade and Local Binary Patterns Histogram (LBPH) for feature extraction and the Support Vector Machine (SVM) for face classification.…”

Section: Many Work Have Targeted the Analysis Of Training Ofmentioning

confidence: 99%

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Mutneja¹,

Singh²

2021

IJATEE

View full text Add to dashboard Cite

Haar features have been used in most of the works in literature as key components in the task of object as well as face detection. Training of Haar features is an important step in the development of overall machine learning based face detection system. In this work, we have done investigation in the variations of a number of training parameters during AdaBoost based machine learning of Haar features with respect to size of training images. A number of observations have been drawn based on the variations of these parameters during training process. Training parameters True Detection Rate and Figure of Merit have been used as weighing parameter in formation of detection cascade for improvement in original AdaBoost framework used for machine learning of Haar features. Statistical analysis based on variations of training parameters has been done for selection of efficient learners from a large pool of available features which further are cascaded to make the strong classifiers.we have been able to achieve the maximum percentage reduction in training time of 47.20 corresponding to training images size 25x25 pixels with the help of statistical screening of Haar features prior to AdaBoost. The proposed system has been developed using training dataset from CBCL and successfully tested on facial images from datasets WIDER FACE a Face Detection Benchmark dataset, Annotated Faces in the Wild (AFW) and Face Detection Data Set and Benchmark (FDDB). and been able to achieve promising results in terms of training time computedin range of 0.31-2.83hrs, maximum detection rate 96.21% and minimum detection time16.95ms.

show abstract

Section: Many Work Have Targeted the Analysis Of Training Ofmentioning

confidence: 99%

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Mutneja¹,

Singh²

2021

IJATEE

View full text Add to dashboard Cite

show abstract

“…Aplikasi pengenalan wajah sebagian besar berorientasi pada penguatan sistem keamanan dan pemantauan. Sebagian diaplikasikan pada keamanan smart home [1][2][3][4][5], identifikasi [6][7][8][9][10][11][12], dan pemantauan [13][14][15][16][17]. Contoh penerapan pengenalan wajah dalam menguatkan sistem keamanan smart home dengan menggunakan data latih dari sosial media untuk meningkatkan ketepatan klasifikasinya [3], mengaplikasikan pengenalan wajah dalam identifikasi tindak kejahatan [6,9], dan aplikasi pengenalan wajah untuk pemantuan kehadiran siswa di kelas [16].…”

Section: Pendahuluanunclassified

Penguatan Ketepatan Pengenalan Wajah Viola-Jones Dengan Pelacakan

Florestiyanto

Pratomo

Sari

2020

teknika

View full text Add to dashboard Cite

Aplikasi pengenalan wajah sebagian besar berorientasi pada penguatan sistem keamanan dan pemantauan. Aplikasi-aplikasi tersebut banyak dikembangkan akibat adanya kajian penguatan ketepatan pengenalan wajah yang dikembangkan terus-menerus oleh peneliti. Variasi fitur wajah setiap orang yang kompleks dan perubahannya dari waktu ke waktu, bahkan dalam waktu yang singkat menjadikan optimalisasi ketepatan pengenalannya semakin rumit. Studi ini bertujuan untuk meningkatkan performa metode Viola-Jones pada target yang bergerak dengan integrasi algoritma tracking. Algoritma tracking yang diintegrasikan adalah algoritma Continuously Adaptive Mean Shift (Camshift). Algoritma ini merupakan pengembangan dari algoritma Mean Shift yang secara terus menerus melakukan adaptasi atau penyesuaian terhadap distribusi probabilitas warna yang selalu berubah tiap pergantian frame dari sebuah sequence video. Integrasi tracking dengan Viola-Jones signifikan meningkatkan ketepatan pengenalan wajah dibandingkan tanpa tracking yaitu sebesar 96%.

show abstract

“…A large dataset of a crowded office environment in the Middle East is collected and used for evaluation of their system. [14]However, in the proposed system to detect partially covered faces authors will use the facial landmarks detection-based approach because that approach is less weight and the performance of the application is also increased.…”

Section: Literature Reviewmentioning

confidence: 99%

Armed and Partially Covered Face Related Robberies Alerting System Using Computer Vision

Mahima¹,

Ginige²

2020

AJCT

View full text Add to dashboard Cite

Robbery is the completed or attempted theft, directly from a person, of property or cash by force or threat of force, with or without a weapon, and with or without injury. Armed robbery is a serious crime that can traumatically that emotionally and mentally profoundly traumatize its victims. Armed robbery is usually motivated by a desire to acquire money, which is then commonly used to buy drugs. [1] However, some armed robbers are associated with the crime.[2] In the current decade, armed robbery is one of the major issues in society. According to Statista research department, there were more than 0.25 million armed robberies happened in the USA in 2018. [3] Moreover, these robberies accounted for an estimated $438 million in losses. [2] . Moreover is the USA there were more than 10000 murders, victims, by weapons in 2018. [4]When analyzing most of these armed robberies have happened locations are Banks, Gas or Service stations, and commercial houses in the USA. To monitor and act accordingly to the issue still, there is no proper method. Present in most places there are several security officers to monitor these robberies within 24H using CCTV cameras. In this research, the authors propose a novel approach to prevent this issue using a computer vision-based armed robberies alerting system. Here this system is able to detect the weapons of the robbers. Since most of the time robbers come with partially covered faces. In this research, the proposed system is able to detect partially covered faces also. When the system identified weapons or a partially covered face in a bank or a commercial house, it will send an alert by notifying the risk of the robbery to the in house security officers and relevant authorities. The proposed solution used an object detection model and a facial landmark identification based approach to detect robbers. Because of this system, no longer the security officers need to monitor CCTV cameras by themselves Keywords -

show abstract

Partially Covered Face Detection in Presence of Headscarf for Surveillance Applications

Cited by 22 publications

References 12 publications

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Penguatan Ketepatan Pengenalan Wajah Viola-Jones Dengan Pelacakan

Armed and Partially Covered Face Related Robberies Alerting System Using Computer Vision

Contact Info

Product

Resources

About