Off-the-shelf Convolutional Neural Network (CNN) features for Automatic Face Quality Prediction
Nabila Saiyed1, Shikha Nema2, Akanksha Joshi3
1Nabila Saiyed*, Department of Electronics and Telecommunication Engineering, Usha Mittal Institute of Technology, SNDT University, Mumbai, India.
2Dr. Shikha Nema, Department of Electronics and Telecommunication Engineering, Usha Mittal Institute of Technology, SNDT University, Mumbai, India.
3Akanksha Joshi, CDAC, Mumbai, India.
Manuscript received on January 05, 2020. | Revised Manuscript received on January 25, 2020. | Manuscript published on January 30, 2020. | PP: 4117-4123 | Volume-8 Issue-5, January 2020. | Retrieval Number: D7665118419/2020©BEIESP | DOI: 10.35940/ijrte.D7665.018520
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Estimation of face image quality helps in correctly recognizing faces which in turn helps in many practical applications related to face. This paper presents a face quality prediction approach using Off-the-Shelf CNN features. Here we evaluated three image descriptors-binary patterns (LBP), Histogram of oriented gradients (HOG), Oriented Fast and Rotated Brief (ORB), and deep Convolution Neural Network (CNN) Networks pre-trained on ImageNet-VGG19, ResNet50, and VGG Small (4 layers) for feature extraction to detect face region image quality. Furthermore, to classify extracted features, we have evaluated three classifiers, that are different from each other in their own ways (SVM, DT and MLP) For experimental analysis, we created a face quality dataset by collecting images from web and publicly available face datasets and manually labeled images under seven categories-Good and six bad quality classes (e.g. Expression, Makeup, Pose, Occlusion, Illumination and Blur). The accuracy of face image classification using VGG19 along with MLP as a classifier was the highest (i.e.98.76%) followed by ResNet50 and MLP at 98.69% of accuracy. The lowest accuracy was obtained with LBP and SVM, this shows that deep features gives a better solution.
Keywords: About four key words or phrases in alphabetical order, separated by commas.
Scope of the Article: About Four Key Words or Phrases in Alphabetical Order, Separated By Commas.