Millimetre wave person recognition: Hand-crafted vs learned features

Abstract

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: AbstractImaging using millimeter waves (mmWs) has many advantages including ability to penetrate obscurants such as clothes and polymers. Although conceal weapon detection has been the predominant mmW imaging application, in this paper, we aim to gain some insight about the potential of using mmW images for person recognition. We report experimental results using the mmW TNO database consisting of 50 individuals based on both hand-crafted and learned features from Alexnet and VGG-face pretrained CNN models. Results suggest that: i) mmW torso region is more discriminative than mmW face and the entire body, ii) CNN features produce better results compared to hand-crafted features on mmW faces and the entire body, and iii) hand-crafted features slightly outperform CNN features on mmW torso.

Exploring Body Texture From mmW Images for Person Recognition

“…In this work, we present further insight about the potential of use of mm W images for person recognition, after our first work on this line [10]. As mmW waves have the ability to pass through clothes, person recognition may be achieved not only through face information, but also through other parts of the body such as the torso or even the whole body.…”

“…In this case the source task is object recognition for Alexnet and face recognition for VGG-face and the target task is person recognition through mm W texture information using the mm W TNO as the target dataset. For more details regarding the training parameters, see [10].…”

“…As mmW waves have the ability to pass through clothes, person recognition may be achieved not only through face information, but also through other parts of the body such as the torso or even the whole body. The main contributions of this work in comparison with our previous work [10] are the following:…”

Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks

“…Even though these methods are able to address many challenges and have even achieved human-expert level performance on challenging databases such as the low-resolution, pose variation and illumination variation to some extent [58], [42], [4], [8], [45], they are specifically designed for recognizing face images that are collected in the visible spectrum. Hence, they often do not perform well on the face im-ages captured from other domains such as thermal [49], [76], [17], [18], infrared [27], [37], [63] or millimeter wave [11], [12] due to significant phenomenological differences as well as a lack of sufficient training data. Fig.…”

Generative adversarial network-based synthesis of visible faces from polarimetrie thermal faces

“…Even though these methods are able to address many challenges such as the low-resolution, pose variation and illumination variation to some extent, they are specifically designed for recognizing face images that are collected near-visible spectrum. They often do not perform well on the face images captured from other domains such as polarimetric [6,20,23], infrared [11,16] or millimeter wave [3] due to significant phenomenological differences as well as a lack of sufficient training data. Distributional change between thermal and visible images makes thermal-to-visible face recognition very challenging.…”