Journals / Electronic Letters on Science and Engineering / 2006 / Cilt: 2 - Sayı: 1

Human Face Recognition

Pages
1–12
Publication Date
2006-04-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Thanks to that qualifications, 92% truth proportion has been reached as result of the tests that were carried out on data.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In that study, it is carried out to confirm the image that includes a face or not by using technique of image processing and back-propagation artificial neural networks, to find face places on the picture and to operate face recognition.
📊
Key Findings & Data:These 3 different operations are working free from each other in plan system.
💡
Conclusion & Impact:Thanks to that qualifications, 92% truth proportion has been reached as result of the tests that were carried out on data.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Yüz Bulma · Yüz Tanıma · Yapay Sinir Ağları

Abstract

In that study, it is carried out to confirm the image that includes a face or not by using technique of image processing and back-propagation artificial neural networks, to find face places on the picture and to operate face recognition. These 3 different operations are working free from each other in plan system. While carrying out these operations firstly the images have been normalized to threshold for destroying images and dirties which were at background, the color-plates of the images have been formed and the qualifications that will be used training of artificial neural networks have obtained. Thanks to that qualifications, 92% truth proportion has been reached as result of the tests that were carried out on data.

Özet

Bu çalışmada, görüntü işleme teknikleri ve geri yayılımlı yapay sinir ağı kullanılarak bir görüntünün yüz içerip içermediğinin testipi, resim üzerinde yüz yerlerini saptama ve yüz tanıma işlemleri gerçekleştirilmiştir. Tasarlanan sistemde bu üç farklı işlem birbirinden bağımsız olarak çalıştırılmıştır. Bu işlemler gerçekleştirilirken, öncelikle görüntüler normalize edilmiş ve arka planda oluşan gürültü ve kirlilikleri gidermek için eşiklenmiş, ardından görüntülerin renk matrisleri oluşturulmuş ve bir yapay sinir ağı eğitiminde kullanılacak özellikler elde edilmiştir. Bu özellikler sayesinde örnek veri tabanında yapılan testler sonucu % 92’lik bir doğruluk oranına ulaşıldığı görülmüştür.

🔖

Cite This Article

ER, O., TEMURTAS, F. (2006). Human Face Recognition. Electronic Letters on Science and Engineering, Cilt: 2 - Sayı: 1, 1–12. https://ajindex.com/articles/133701

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...