Kiyoung Moon

Automated Human Recognition by Gait using Neural Network

We describe a new method for recognizing humans by their gait using back-propagation neural network. Here, the gait motion is described as rhythmic and periodic motion, and a 2D stick figure is extracted from gait silhouette by motion information with topological analysis guided by anatomical knowledge. A sequential set of 2D stick figures is used to represent the gait signature that is primitive data for the feature extraction based on motion parameters. Then, a back-propagation neural network algorithm is used to recognize humans by their gait patterns. In experiments, higher gait recognition performances have been achieved.

Performance evaluation of watermarking techniques for secure multimodal biometric systems

In this paper, we describe various watermarking techniques for secure user verification in the remote, multimodal biometric systems employing both fingerprint and face information, and compare their effects on user verification and watermark detection accuracies quantitatively. To evaluate the performance of watermarking for multimodal biometric systems, we first consider possible two scenarios – embedding facial features into a fingerprint image and embedding fingerprint features into a facial image. Additionally, to evaluate the performance of dual watermarking for secure biometric systems, we consider another two scenarios – with/without considering the characteristics of the fingerprint in embedding the dual watermark. Based on the experimental results, we confirm that embedding fingerprint features into a facial image can provide superior performance in terms of the user verification accuracy. Also, the dual watermarking with considering the characteristics of the fingerprint in embedding the dual watermark can provide superior performance in terms of the watermark detection accuracy.

Hiding biometric data for secure transmission

In this paper, we describe biometric watermarking techniques for secure user verification on the remote, multimodal biometric system employing both fingerprint and face information, and compare their effects on verification accuracy quantitatively. To hide biometric data with watermarking techniques, we first consider possible two scenarios. In the Scenario 1, we use a fingerprint image as a cover work and hide facial features into it. On the contrary, we hide fingerprint features into a facial image in the Scenario 2. Based on the experimental results, we confirm that the Scenario 2 is superior to the Scenario 1 in terms of the verification accuracy of the watermarked image.

Biometric Certificate Based Biometric Digital Key Generation with Protection Mechanism

The binding of the users identity and biometric feature data to an entity is provided by an authority through a digitally signed data structure called a biometric certificate. Therefore, the main goal (or contribution) of this work is to propose a simple method for generating biometric digital key with biometric certificate on fuzzy fingerprint vault mechanism. Biometric digital key from biometric data has many applications such as automatic identification, user authentication with message encryption, etc. Therefore, this work analysis the related existing scheme and proposes a simplified model where a general fuzzy fingerprint vault using biometric certificate with security consideration.

Certificate validation service using XKMS for computational grid

A computational grid is a hardware and software infrastructure capable of providing dependable, consistent, pervasive, and inexpensive access to high-end computational resource. There are many ways to access the resources of a computational grid, each with unique security requirements and implications for both the resource user and the resource provider. Current Grid security Infrastructure using PKI based on SSO. But open grid service Security Infrastructure in Global Grid Forum(GGF) will extend use of grid system or services up to business area using XML web services security technology. This paper describes a novel security approach on open grid service to validate certificate based on current globus toolkit environment using XKMS(XML Key Management Specification) and SAML(Security Assertion Markup Language), XACML(extensible Access Control Markup Language) in XML security.

Inverse operation and preimage attack on BioHashing

BioHashing generates a BioCode from a users biometric features by projecting them onto user-specific random vectors and then discritizes the projection coefficients into zero or one. Since biometric features are distorted by the non-invertible transforms and template matching is performed in a transformed state, it has been claimed that BioHashing is oneway and a BioCode is as secure as a hashed password. However, we disprove it by showing that even without a genuines private random vectors, a preimage of a BioCode is easily calculated from a lost BioCode and an attacker can gain an illegal access to a system.

Implementation of automatic fuzzy fingerprint vault

Biometric-based authentication can provide strong security guarantee about the identity of users. However, security of biometric data is particularly important as the compromise of the data will be permanent. To protect the biometric data, we need to store it in a non-invertible transformed version. Thus, even if the transformed version is compromised, the actual biometric data remains safe. In this paper, we implement the fuzzy fingerprint vault system combining fingerprint verification and fuzzy vault scheme to protect fingerprint templates. Fuzzy vault is a recently developed cryptographic construct to secure critical data with the fingerprint data in a way that only the authorized user can access the secret by providing the valid fingerprint. However, all the previous results assumed that fingerprint features were pre-aligned. To solve this problem, we perform the automatic alignment of fingerprint features by using the geometric hashing technique. Also, we implement a new RS decoding algorithm based on the Extended Euclidean algorithm proposed by Gao. Based on the experimental results, we confirm that the proposed approach can align fingerprint features automatically in the domain of the fuzzy vault and perform fingerprint verification with the protected template in real-time.

Real-Time Face Verification for Mobile Platforms

We propose a novel method for real-time face verification on mobile platforms such as PDAs and cell-phones. To implement the real-time system, a fixed-point arithmetic is used, and the face components are extracted by using a fast boosting algorithm. In addition, an image reduction method is adapted by using a pre-calculated look-up table, and integral image calculation method is modified to reduce the processing time. Also, the efficient valid coefficients of a DCT transformed image in the face region are calculated, and the face features are extracted by using the EP-LDA methods. In experiments, the usefulness of the proposed method has been demonstrated on a smart phone with high face verification performances.

Design of Embedded Multimodal Biometric Systems

The embedded devices in biometrics have gained increasing attention due to the demand for reliable and cost-effective personal identification systems. However, the current available embedded devices are not suitable for the real-time implementation of a biometric application system because of the limited computational resource and memory space. In this paper, we describe the design of embedded biometric systems that identify person by using face-fingerprint or iris-fingerprint multimodal biometrics technology. To implement real-time system, the biometric algorithms are efficiently enhanced for fixed-point representation and optimized for memory and computational capacity. In addition, the most time consuming components of each biometric algorithm are implemented in a field programmable gate arrays (FPGA).

One-Time Templates for Face Authentication

This paper proposes a novel scheme for one-time templates for face authentication. The suggested method changes templates after each completion of authentication like one-time passwords, thus the snapped templates cannot be reused. Matching between a gallery and a probe is performed by Euclidean distance and cosine function as in their primal form without recovering their original templates even though the templates are transformed. The suggested method does not require much modification of conventional face recognition methods and can be built on established systems as an add-on.