• Shweta Mishra
• Deepa Jilla
• Aditi Bansal
• Dr. Shikha Nema

Initially, three different biometric characteristics (finger print, iris and face) were identified for determining an individuals identity but finally face came to be regarded as the most suited to the practicalities of the real world. The only requirement is to make a facial image in compliance with a standard which is universal. The aim of this project is to design an automatic system which verifies compliance of images with ICAO standards (ISO/IEC 19794-5). This paper compares three classification model having feature extracted from Local Binary Pattern, Histogram of Oriented Gradients and a Deep Neural network model. An image analysis methodology using Support Vector Machine (SVM), Convolutional Neural Network (CNN) and K-Nearest Neighbors (KNN) was used to classify images.

Face image quality, face recognition, ICAO, ISO/IEC 19794-5, HOG, LBP, CNN, SVM, KNN.

"Face Quality Analysis Using Deep Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.619-625, May-2019, Available :http://www.jetir.org/papers/JETIR1905388.pdf

"Face Quality Analysis Using Deep Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp619-625, May-2019, Available at : http://www.jetir.org/papers/JETIR1905388.pdf