Thermal–Visible Face Recognition Based on CNN Features and Triple Triplet Configuration for On-the-Move Identity Verification

Abstract

Face recognition operating in visible domains exists in many aspects of our lives, while the remaining parts of the spectrum including near and thermal infrared are not sufficiently explored. Thermal–visible face recognition is a promising biometric modality that combines affordable technology and high imaging qualities in the visible domain with low-light capabilities of thermal infrared. In this work, we present the results of our study in the field of thermal–visible face verification using four different algorithm architectures tested using several publicly available databases. The study covers Siamese, Triplet, and Verification Through Identification methods in various configurations. As a result, we propose a triple triplet face verification method that combines three CNNs being used in each of the triplet branches. The triple triplet method outperforms other reference methods and achieves TAR @FAR 1% values up to 90.61%.

Modified CNN Model for Classifying Gender of Thermal Images Using Cloud Computing

“…Although these technologies have proven their great role in extracting the features of the images that were entered, the use of the convolution neural network (CNN) to extract the features from the images had a distinctive role in monitoring systems and people's gender identification systems. as well as we can based on other parts of the body rather than the face in adopting in classification mechanism is like the variations shown in the style of arrangement of hair, clothes, etc., whether in visual images or thermal images [9] [10]. A group of researchers was also able to propose a simple set of features to distinguish gender, which was extracted from thermal infrared images.…”

A Survey on Thermal to Visual Cross Domain Face Recognition

“…In [82], a cascaded refinement network is introduced for generating high-quality visiblelike coloured images from limited training data. In [127], proposed a triple triplet face verification method that combines three CNNs used in each triplet branch.…”

“…In [127], proposed a triple triplet face verification method that combines three CNNs being used in each of the triplet branches.…”

SF-YOLOv5: A Lightweight Small Object Detection Algorithm Based on Improved Feature Fusion Mode

“…It is a cross domain of computer vision, digital image processing, and machine vision. It always had high research and application value in face recognition [ 1 , 2 ], industrial defect detection [ 3 ], UAV aviation detection [ 4 , 5 ], traffic and vehicle detection [ 6 ], pedestrian detection and counting [ 7 ], and other fields.…”