SUMMARY Face image hashing is an emerging method used in bio-metric verification systems. In this paper, we propose a novel face image hashing method based on a new technique called discriminative projection selection. We apply the Fisher criterion for selecting the rows of a random projection matrix in a user-dependent fashion. Moreover, another contri-bution of this paper is to employ a bimodal Gaussian mixture model at the quantization step. Our simulation results on three different databases demonstrate that the proposed method has superior performance in com-parison to previously proposed random projection based methods. key words: face image hashing, biometric security, privacy 1
International audienceFace identification is an important research topic due to areas such as its ap...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...
The binary quantization method which is used in random projection based biometric hashing systems re...
Face-based biometrics approach has proved to be robust and efficient for verification systems (compa...
In this paper, we address capacity analysis of biometric hashing methods. We propose an information ...
This paper presents a cancelable biometric system for face authentication by exploiting the convolut...
Abstract. In this paper, we introduce a concept to counter the current weakness of robust hashing wi...
In this paper, we introduce a concept to counter the current weakness of robust hashing with respect...
This paper presents a new approach to generate biometric hash values based on statistical features i...
We propose a face recognition approach based on hashing. The approach yields comparable recognition ...
In the last few years, the research growth in many research and commercial fields are due to the ado...
Local Zernike moments (LZM) is a recently proposed image representation scheme that is shown to be s...
Traditional methods of identity recognition are based on the knowledge of a password or a PIN, or po...
Part 1: Research PapersInternational audienceOne of the most important requirements on a biometric v...
International audienceFace identification is an important research topic due to areas such as its ap...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...
The binary quantization method which is used in random projection based biometric hashing systems re...
Face-based biometrics approach has proved to be robust and efficient for verification systems (compa...
In this paper, we address capacity analysis of biometric hashing methods. We propose an information ...
This paper presents a cancelable biometric system for face authentication by exploiting the convolut...
Abstract. In this paper, we introduce a concept to counter the current weakness of robust hashing wi...
In this paper, we introduce a concept to counter the current weakness of robust hashing with respect...
This paper presents a new approach to generate biometric hash values based on statistical features i...
We propose a face recognition approach based on hashing. The approach yields comparable recognition ...
In the last few years, the research growth in many research and commercial fields are due to the ado...
Local Zernike moments (LZM) is a recently proposed image representation scheme that is shown to be s...
Traditional methods of identity recognition are based on the knowledge of a password or a PIN, or po...
Part 1: Research PapersInternational audienceOne of the most important requirements on a biometric v...
International audienceFace identification is an important research topic due to areas such as its ap...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...
Within a forensic examination of a computer for illegal image content, robust hashing can be used to...