Face Detection Using an Implementation Running in a Web Browser

2020 ◽  
Author(s):  
Halyna Klym ◽  
Ivanna Vasylchyshyn
Keyword(s):  
Face Detection ◽  
Web Browser

PROTOTYPE ALAT PEMANTAU SALURAN AIR BAWAH TANAH DENGAN MENGGUNAKAN WEBCAM C170 BERBASIS RASPBERRY PI

2015 ◽  
Vol 1 (1) ◽  
pp. 37-45
Author(s):  
Irwansyah Irwansyah ◽  
Hendra Kusumah ◽  
Muhammad Syarif
Keyword(s):  
Real Time ◽  
Monitoring System ◽  
Public Awareness ◽  
Underground Water ◽  
Raspberry Pi ◽  
Laptop Computer ◽  
Web Browser ◽  
Disaster Monitoring ◽  
The Times ◽  
Human Desire

Along with the times, recently there have been found tool to facilitate human’s work. Electronics is one of technology to facilitate human’s work. One of human desire is being safe, so that people think to make a tool which can monitor the surrounding condition without being monitored with people’s own eyes. Public awareness of the underground water channels currently felt still very little so frequent floods. To avoid the flood disaster monitoring needs to be done to underground water channels.This tool is controlled via a web browser. for the components used in this monitoring system is the Raspberry Pi technology where the system can take pictures in real time with the help of Logitech C170 webcam camera. web browser and Raspberry Pi make everyone can control the devices around with using smartphone, laptop, computer and ipad. This research is expected to be able to help the users in knowing the blockage on water flow and monitored around in realtime.

Face Detection for AIBO Using RBF Network

2010 ◽  
Vol 130 (11) ◽  
pp. 2031-2038
Author(s):  
Kohki Abiko ◽  
Hironobu Fukai ◽  
Yasue Mitsukura ◽  
Minoru Fukumi ◽  
Masahiro Tanaka
Keyword(s):  
Face Detection ◽  
Rbf Network

Speaker Identity Recognition by Acoustic and Visual Data Fusion through Personal Privacy for Smart Care and Service Applications

2020 ◽  
Vol 64 (4) ◽  
pp. 40404-1-40404-16
Author(s):  
I.-J. Ding ◽  
C.-M. Ruan
Keyword(s):  
Face Detection ◽  
Speaker Recognition ◽  
Visual Information ◽  
Classification Tree ◽  
Gaussian Mixture ◽  
Recognition Method ◽  
Indoor Space ◽  
Identity Recognition ◽  
Visual Identity ◽  
Speaker Classification

Abstract With rapid developments in techniques related to the internet of things, smart service applications such as voice-command-based speech recognition and smart care applications such as context-aware-based emotion recognition will gain much attention and potentially be a requirement in smart home or office environments. In such intelligence applications, identity recognition of the specific member in indoor spaces will be a crucial issue. In this study, a combined audio-visual identity recognition approach was developed. In this approach, visual information obtained from face detection was incorporated into acoustic Gaussian likelihood calculations for constructing speaker classification trees to significantly enhance the Gaussian mixture model (GMM)-based speaker recognition method. This study considered the privacy of the monitored person and reduced the degree of surveillance. Moreover, the popular Kinect sensor device containing a microphone array was adopted to obtain acoustic voice data from the person. The proposed audio-visual identity recognition approach deploys only two cameras in a specific indoor space for conveniently performing face detection and quickly determining the total number of people in the specific space. Such information pertaining to the number of people in the indoor space obtained using face detection was utilized to effectively regulate the accurate GMM speaker classification tree design. Two face-detection-regulated speaker classification tree schemes are presented for the GMM speaker recognition method in this study—the binary speaker classification tree (GMM-BT) and the non-binary speaker classification tree (GMM-NBT). The proposed GMM-BT and GMM-NBT methods achieve excellent identity recognition rates of 84.28% and 83%, respectively; both values are higher than the rate of the conventional GMM approach (80.5%). Moreover, as the extremely complex calculations of face recognition in general audio-visual speaker recognition tasks are not required, the proposed approach is rapid and efficient with only a slight increment of 0.051 s in the average recognition time.

Efficient Face Detection on Epiphany Multicore Processor

2017 ◽  
Vol 1 (1) ◽  
pp. 113-127 ◽  
Author(s):  
A. A. Sukhinov ◽  
◽  
G. B. Ostrobrod ◽  
Keyword(s):  
Face Detection ◽  
Multicore Processor

Recognizing Human-Object Using Genetic Algorithm for Face Detection in Natural Driving Environment

2012 ◽  
Vol 7 (2) ◽  
pp. 10-18
Author(s):  
B. Mallikarjuna ◽  
◽  
K.V. Ramanaiah ◽  
P. Mohanaiah ◽  
V. Vijaya Kumar Reddy ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Face Detection ◽  
Human Object

Pengembangan Sistem VOIP Menggunakan Server Issabel Versi 4.0 dan Tunnel EOIP pada OMNI Hospital Alam Sutera

2018 ◽  
Vol 18 (1) ◽  
pp. 13-20
Author(s):  
Elly Mufida ◽  
David Wardana Agus Rahayu
Keyword(s):  
Operating System ◽  
Open Source ◽  
End Of Life ◽  
Communication System ◽  
Communication Protocol ◽  
The Internet ◽  
Migration Process ◽  
Web Browser ◽  
Backup Path ◽  
E Mail

The VoIP communication system at OMNI Hospital Alam Sutera uses the Elastix 2.5 server with the Centos 5.11 operating system. Elastix 2.5 by the developer has been declared End of Life. The server security system is a serious concern considering that VoIP servers can be accessed from the internet. Iptables and fail2ban applications are applications that are used to limit and counteract those who try to attack the VoIP server. One application that can be used as an open source VoIP server is the Issabel Application version 4.0. The migration process from Elastix 2.5 application to Issabel 4.0 by backing up all configurations in the Elastix 2.5 application through a web browser including the configuration of endpoints, fax, e-mail, asterisk. After the backup file is downloaded then upload the backup file to the Issabel 4.0 application then run the migration process. Adding a backup path as a failover connection is needed because the VoIP communication protocol between the OMNI Hospitals Group still uses one path so that when there is a problem in the connection path, the communication protocol will stop. The tunnel EoIP is a protocol used as a backup path between the OMNI Hospitals Group site.

IMPLEMENTASI QUICK RESPONSE (QR) CODE PADA APLIKASI VALIDASI DOKUMEN MENGGUNAKAN PERANCANGAN UNIFIED MODELLING LANGUAGE (UML)

2016 ◽  
Vol 10 (1) ◽  
Author(s):  
Novan Adi Musthofa, Siti Mutrofin, Mohamad Ali Murtadho
Keyword(s):  
Qr Code ◽  
Quick Response ◽  
Uniform Resource Locator ◽  
Modelling Language ◽  
Web Browser ◽  
Unified Modelling Language

Dengan berkembangnya teknologi informasi, sering sekali terjadi penyelewengan dokumen terutama pada dokumen-dokumen cetak. Dokumen merupakan salah satu data yang sangat penting, karena dokumen merupakan sumber informasi yang diperlukan oleh suatu instansi, organisasi, negara, maupun individu. Tanpa dokumen, maka seseorang akan kehilangan data-data yang diperlukan untuk kegiatan di masa yang akan datang. Pemalsuan dokumen sangat mudah dilakukan dengan cara meniru bentuk serta isi dari suatu dokumen. Penelitian sebelumnya pernah dilakukan, namun dalam objek yang berbeda. Pemalsuan dokumen dapat diatasi dengan menggunakan Quick Response (QR) Code. QR Code mampu menyimpan semua jenis data, seperti data angka/numerik, alphanumeric, biner, kanji/kana. Selain itu QR Code memiliki tampilan yang lebih kecil daripada barcode. Untuk dapat membuat QR Code suatu dokumen maka dibuatlah sebuah aplikasi yaitu aplikasi Validasi Dokumen. Aplikasi Validasi Dokumen dirancang dengan menggunakan metode waterfall serta menggunakan perancangan Unified Modelling Language (UML). Bahasa pemrograman yang digunakan yaitu bahasa pemrograman PHP: Hypertext Preprocessor (PHP) dengan database MySQL. Sebelum QR Code dibuat, terlebih dahulu data dokumen dienkripsi dan kemudian dijadikan QR Code. Hasil pemindaian QR Code berupa Uniform Resource Locator (URL) yang mengarah pada data dokumen. Ketika URL dijalankan pada web browser, sistem melakukan deskripsi pada URL, kemudian dicocokkan dengan database, dan selanjutnya ditampilkan ke web browser. Hasil akhir aplikasi Validasi Dokumen berupa QR Code yang digunakan untuk menyimpan URL yang  menunjukkan bahwa dokumen memang benar-banar dokumen yang resmi (bukan ilegal) dari suatu instansi. Pada uji coba penelitian ini juga dilakukan perbandingan kinerja dengan 3 aplikasi yang sejenis, 3 aplikasi pembanding tersebut dipilih karena memiliki hasil visual QR Code yang hampir mirip, namun jika dilakukan scanning memiliki hasil yang berbeda, karena fiturnya juga berbeda. Berdasarkan hasil pengujian dengan 3 pembanding aplikasi yang sejenis, dengan menggunakan aplikasi yang diusulkan dalam penelitian ini, pemalsuan dokumen dapat dihindari dengan menggunakan aplikasi Validasi Dokumen selama tidak ada ikut campur orang dalam (superadmin/admin) dalam melakukan praktik pemalsuan dokumen. Pada penelitian selanjutnya dapat dilakukan perbaikan kelemahan aplikasi ini, yaitu agar tidak menampilkan URL, namun hasil pemindai QR Code, langsung dapat menampilkan detail isi dokumen.

Evaluasi Aksesibilitas Learning Object Berdasarkan Web Content Accessibility Guidelines 2.0

2017 ◽  
Vol 9 (2) ◽  
pp. 67-71
Author(s):  
Herru Darmadi ◽  
Yan Fi ◽  
Hady Pranoto
Keyword(s):  
Learning Objects ◽  
Authoring Tool ◽  
Learning Object ◽  
Web Content ◽  
Web Browser ◽  
E Learning ◽  
Index Terms ◽  
Accessibility Guidelines ◽  
Content Accessibility

Learning Object (LO) is a representation of interactive content that are used to enrich e-learning activities. The goals of this case study were to evaluate accessibility and compatibility factors from learning objects that were produced by using BINUS E-learning Authoring Tool. Data were compiled by using experiment to 30 learning objects by using stratified random sampling from seven faculties in undergraduate program. Data were analyzed using accessibility and compatibility tests based on Web Content Accessibility Guidelines 2.0 Level A. Results of the analysis for accessibility and compatibility tests of Learning Objects was 90% better than average. The result shows that learning objects is fully compatible with major web browser. This paper also presents five accessibility problems found during the test and provide recommendation to overcome the related problems. It can be concluded that the learning objects that were produced using BINUS E-learning Authoring Tool have a high compatibility, with minor accessibility problems. Learning objects with a good accessibility and compatibility will be beneficial to all learner with or without disabilities during their learning process. Index Terms—accessibility, compatibility, HTML, learning object, WCAG2.0, web

Sign in / Sign up

Export Citation Format

Share Document