Face hallucination is to reconstruct a high-resolution face image from a low-resolution one based on a set of highand low-resolution training image pairs. This paper proposes an example-based two-step face hallucination method through coefficient learning. Firstly, the low-resolution input image and the low-resolution training images are interpolated to the same high-resolution space. Minimizin...

A content–based coding scheme for the transmission of videophone sequences at very low bit rates conforming to the MPEG–4 standard is presented. The goal is to improve the image quality in the facial area of a person, at the expense of a lower quality in the remaining image, which is subjectively less important for the communication partner. In a first step, the face of the talking person is de...

State-of-the-art techniques in Generative Adversarial Networks (GANs) such as cycleGAN is able to learn the mapping of one image domain X to another image domain Y using unpaired image data. We extend the cycleGAN to Conditional cycleGAN such that the mapping from X to Y is subjected to attribute condition Z. Using face image generation as an application example, where X is a low resolution fac...

Skin color is a useful means for human face detection. In this paper, we propose an efficient color compensation method for skin color segmentation under varying lighting conditions. One of the major problems of using skin color is that a face region may not be detected under poor or uneven lighting conditions. Our approach considers the distribution of the color components of skin pixels and t...

The goal of this work is to find all occurrences of a particular person in a sequence of photographs taken over a short period of time. For identification, we assume each individual’s hair and clothing stays the same throughout the sequence. Even with these assumptions, the task remains challenging as people can move around, change their pose and scale, and partially occlude each other. We prop...

A three-stage scheme for real-time reliable face detection is presented. The proposed three-stage scheme is a feature-based method that is mainly based on skin color and facial features. Skin regions are obtained using a YCbCr skin-color model in the first stage. In the second stage, a face template measure is used to obtain face candidates and then a suitable face box is used to effectively re...

In this paper, we present a general framework for face modeling under varying lighting conditions. First, we show that a face lighting subspace can be constructed based on three or more training face images illuminated by non-coplanar lights. The lighting of any face image can be represented as a point in this subspace. Second, we show that the extreme rays, i.e. the boundary of an illumination...

In recent years face recognition has received substantial attention from both research communities and the market, but still remained very challenging in real applications. A lot of face recognition algorithms, along with their modifications, have been developed during the past decades. A number of typical algorithms are presented, being categorized into appearancebased and model-based schemes....

The classification reliability is an essential problem in biometric verification systems. In the presence of a possible mismatch between system’s training and testing conditions, a measure of that mismatch is necessary in order to estimate the degree of trust one can have in the classification decisions. In the case of face verification from plain images, there are many factors that can affect ...

In this paper a new approach to face recognition is presented that achieves double dimension reduction making the system computationally efficient with better recognition results. In pattern recognition techniques, discriminative information of image increases with increase in resolution to a certain extent, consequently face recognition results improve with increase in face image resolution an...