Maurits Diephuis

Towards reproducible results in authentication based on physical non-cloneable functions: The forensic authentication microstructure optical set (FAMOS)

Nowadays, the field of physical object security based on surface microstructures lacks common and shared data for the development, testing and fair benchmarking of new identification and authentication technologies. To our knowledge, most published results are based on proprietary data that also often lacks the necessary size for statistically significant results and conclusions. Therefore, in this paper, we introduce the first publicly available documented database for the investigation of physical object authentication based on non-cloneable surface microstructure images. We have built an automatic system suitable for massive acquisition of microstructure images from flat surfaces under different light conditions and with different cameras. The samples are acquired several times, and resulting images are aligned, labelled and online available to the public for further investigation and benchmarking of new methods. In this paper, we present the statistical properties for the images originating from 5000 unique carton packages acquired 6 times each with two different cameras. Furthermore, we derive statistical authentication frameworks for the original, the random projected and binarized domains presented together with all empirical results.

Physical object identification based on FAMOS microstructure fingerprinting: Comparison of templates versus invariant features

In this paper, we address the problem of physical object identification based on optical non-cloneable surface microstructure images. Physical object identification is an emerging problem raised in mobile multimedia applications that interact with physical objects as well as in physical world security applications for which there is a great need for reliable, fast and secure object verification. One of the most crucial problems in the design of identification systems is optimal feature selection and extraction which are characterised by their high distinguishability and robustness to lightening variations and geometrical transforms. Not less an important aspect of feature selection is their vulnerability to counterfeiting or physical cloning that we refer to as physical security. Since the geometric de-synchronization represents one of the most significant challenges in the design of reliable physical object identification/authentication systems, we will investigate this problem using two techniques that are well established in computer vision applications and compare the performance of both systems. In particular, we consider two different strategies based on special graphical marks present on physical objects such as packaging or watches which can be considered as templates and microstructure features extracted based on the popular SIFT descriptors. To evaluate the performance of both approaches we use the FAMOS database which contains 5000 unique carton packages acquired 6 times each with two different cameras. The performance of the systems is evaluated based on the empirically ascertained probabilities of miss and false acceptance.

DCT sign based robust privacy preserving image copy detection for cloud-based systems

In this paper we propose an architecture for message-privacy preserving copy detection and content identification for images based on the signs of the Discrete Cosine Transform (DCT) coefficients. The architecture allows for searching in encrypted data and places the computational burden on the server. Sign components of the low frequency DCT coefficients of an image are used to generate a dual set of keys that in turn are used to encrypt the source image and serve as a robust hash that can be queried for content identification. The statistical properties of these DCT sign vectors are modelled and we analyse their robustness against real world image distortions. Finally, the trade-off between the discriminative power of such vectors, the offered security and the resilience against errors is demonstrated.

On accuracy, robustness, and security of bag-of-word search systems

In this paper, we present a statistical framework for the analysis of the performance of Bag-of-Words (BOW) systems. The paper aims at establishing a better understanding of the impact of different elements of BOW systems such as the robustness of descriptors, accuracy of assignment, descriptor compression and pooling and finally decision making. We also study the impact of geometrical information on the BOW system performance and compare the results with different pooling strategies. The proposed framework can also be of interest for a security and privacy analysis of BOW systems. The experimental results on real images and descriptors confirm our theoretical findings. Notation: We use capital letters to denote scalar random variables X and X to denote vector random variables, corresponding small letters x and x to denote the realisations of scalar and vector random variables, respectively. We use X ~pX(x) or simply X ~p(x) to indicate that a random variable X is distributed according to pX(x). N(μ, σ 2 X ) stands for the Gaussian distribution with mean μ and variance σ2 X . B(L, Pb) denotes the binomial distribution with sequence length L and probability of success Pb. ║.║denotes the Euclidean vector norm and Q(.) stands for the Q-function. D(.║.) denotes the divergence and E{.} denotes the expectation.

SketchPrint: Physical object micro-structure identification using mobile phones

This paper addresses the identification of physical objects based on their physical non-cloneable surface structures. These micro-structures are optically acquired using a hand held non-modified consumer mobile phone. Object identification is done with the SketchPrint descriptor, which combines fingerprint-like properties while having reasonable invariance to geometrical and lighting distortions due to its semi-local nature. Crucially, objects can be identified without any geometrical matching or final re-ranking procedure.

Local active content fingerprinting: Optimal solution under linear modulation

This papers presents an analysis on Active Content Fingerprint (aCFP) for local (patch based) image descriptors. A generalization is proposed, the reduction of the aCFP with linear modulation to a constrained projection problem is shown and the optimal solution is given. The constrained projection problem addresses the linear modulation by a constraint on the properties of the resulting local descriptor. A computer simulation using local image patches, extracted from publicly available data sets is provided, demonstrating the advantages under several signal processing distortions.

Supervised Transform Learning for Face Recognition

In this paper we investigate transform learning and apply it to face recognition problem. The focus is to find a transformation matrix that transforms the signal into a robust to noise, discriminative and compact representation. We propose a method that finds an optimal transform under the above constrains. The non-sparse variant of the presented method has a closed form solution whereas the sparse one may be formulated as a solution to a sparsity regularized problem. In addition we give a generalized version of the proposed problem and we propose a prior on the data distribution across the dimensions in the transform domain.

Robust Face Recognition by Group Sparse Representation That Uses Samples from List of Subjects

In this paper we consider group sparsity for robust face recognition. We propose a model for inducing group sparsity with no constraints on the definition of the structure of the group, coupled with locality constrained regularization. We formulate the problem as bounded distance regularized L 2 norm minimization with group sparsity inducing, non-convex constrains. We apply convex relaxation and a branch and bound strategy to find an approximation to the original problem. The empirical results confirm that with this approach of deploying a very simple non-overlapping group structure we outperform several state-of-the-art sparse coding based image classification methods.

Physical object identification using micro-structure images

A micro-structure is the common name for all fine-surface details and material properties visible when a physical object is examined at close range or under magnification. In its most basic form, the micro-structure image serves as a unique, non-cloneable identifier for that object (see Figure 1). It is non-cloneable as the current level of material science technology cannot practically produce a physical object with the precision required to clone a specific micro-structure. This protection scheme is attractive and highly competitive for large-scale, mass-market applications because of the noninvasive character of the protection and its easy, fast verification by non-experts using a mobile device. Applications include security documents, luxury items, spare aviation parts, and electronics. The non-cloneable character and uniqueness also mean that the deployed processing chain as well as the identification and authentication technologies share many elements with existing biometrics systems. We focused our micro-structure architecture elements on extracting the correct image patch, selecting robust or invariant features, dimensionality reduction, and quantization, resulting in a binary representation of the original image (see Figure 2). The acquired samples contain a printed mark used as a guide to extract the correct image patch from a fixed, determined position containing the micro-structure. This extraction needs to be vastly more precise than, for example, computer vision stitching applications. Extracted micro-patches without any geometrical distortions can be successfully modeled as Gaussian i.i.d realizations with additive white noise. This makes analytical analysis of the rest of the processing chain possible, including dimensionality reduction and quantization.1 Identification systems based on micro-structure fingerprints are elegant and fast. Figure 1. (a) A handheld mobile acquisition of a SPIE Certificate and (b-c) two extracted patches of an identical sample without any special equipment or lighting. Histogram equalization was used for visualization purposes.

Local Active Content Fingerprint: Solutions for general linear feature maps

This paper presents solutions to the local patch based Active Content Fingerprint (aCFP) with linear modulation, general linear feature map and convex constraints on the properties of the local feature descriptor. A direct approximation of the linear feature map such that the image distortion is as small as possible and the approximate linear feature map is as close as possible to the original map is proposed. Then an explicit regularization of the trade-off between the modulation distortion and the robustness of the local feature is introduced trough a novel problem formulation. A computer simulation using local image patches, extracted from publicly available data set is provided, demonstrating the advantages under: additive white Gaussian noise (AWGN), lossy JPEG compression and projective geometrical transform distortions.