Svyatoslav Voloshynovskiy

Information-theoretical analysis of private content identification

In recent years, content identification based on digital fingerprinting attracts a lot of attention in different emerging applications. At the same time, the theoretical analysis of digital fingerprinting systems for finite length case remains an open issue. Additionally, privacy leaks caused by fingerprint storage, distribution and sharing in a public domain via third party outsourced services cause certain concerns in the cryptographic community. In this paper, we perform an information-theoretic analysis of finite length digital fingerprinting systems in a private content identification setup and reveal certain connections between fingerprint based content identification and Forneys erasure/list decoding [1]. Along this analysis, we also consider complexity issues of fast content identification in large databases on remote untrusted servers.

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.

Secure Representation of Images Using Multi-layer Compression

We analyze the privacy preservation capabilities of a previously introduced multi-stage image representation framework where blocks of images with similar statistics are decomposed into different codebooks (dictionaries). There it was shown that at very low rate regimes, the method is capable of compressing images that come from the same family with results superior to those of the JPEG2000 codec. We consider two different elements to be added to the discussed approach to achieve a joint compression-encryption framework. The first visual scrambling is the random projections were the random matrix is kept secret between the encryption and decryption sides. We show that for the second approach, scrambling in the DCT domain, we can even slightly increase the compression performance of the multi-layer approach while making it safe against de-scrambling attacks. The experiments were carried out on the ExtendedYaleB database of facial images.

Sign-magnitude decomposition of mutual information with polarization effect in digital identification

Content identification based on digital fingerprinting attracts a lot of attention in different emerging applications. In this paper, we consider digital identification based on the sign-magnitude decomposition of fingerprint codewords and analyze the achievable rates for each component. We introduce a channel splitting approach and reveal certain interesting phenomena related to channel polarization. It is demonstrated that under certain conditions almost all rate in the sign channel is concentrated in reliable components, this can be of interest for complexity and security in various content identification applications. The envisioned extensions cover applications where the input and output alphabets of the channel are different at the encoding and decoding stages. Additionally, the reduction of the input data dimensionality at the encoding/enrollment stage can increase the cryptographic protection in terms of privacy leakage and simplify the decoding algorithms in biometric applications.

Robust human face recognition based on locality preserving sparse over complete block approximation

Compressive Sensing (CS) has become one of the standard methods in face recognition due to the success of the family of Sparse Representation based Classification (SRC) algorithms. However it has been shown that in some cases, the locality of the dictionary codewords is more essential than the sparsity. Also sparse coding does not guarantee to be local which could lead to an unstable solution. We therefore consider the statistically optimal aspects of encoding that guarantee the best approximation of the query image to a dictionary that incorporates varying acquisition conditions. We focus on the investigation, analysis and experimental validation of the best robust classifier/predictor and consider frontal face image variability induced by noise, lighting, expression, pose, etc.. We compare two image representations using a pixel-wise approximation and an overcomplete block-wise approximation with two types of sparsity priors. In the first type we consider all samples from a single subject and in the second type we consider all samples from all subjects. The experiments on a publicly available dataset using low resolution images showed that several per subject sample sparsity prior approximations are as good as the results presented from SCR and that our simple overcomplete block-wise approximation provides superior performance in comparison to the SRC and WSRC algorithm.

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.

Content identification: binary content fingerprinting versus binary content encoding

In this work, we address the problem of content identification. We consider content identification as a special case of multiclass classification. The conventional approach towards identification is based on content fingerprinting where a short binary content description known as a fingerprint is extracted from the content. We propose an alternative solution based on elements of machine learning theory and digital communications. Similar to binary content fingerprinting, binary content representation is generated based on a set of trained binary classifiers. We consider several training/encoding strategies and demonstrate that the proposed system can achieve the upper theoretical performance limits of content identification. The experimental results were carried out both on a synthetic dataset with different parameters and the FAMOS dataset of microstructures from consumer packages.

Geometrically robust perceptual fingerprinting : an asymmetric case

In this paper, the problem of multimedia object identification in channels with asymmetric desynchronizations is studied. First, we analyze the achievable rates attainable in such protocols within digital communication framework. Secondly, we investigate the impact of the fingerprint length on the error performance of these protocols relaxing the capacity achieving argument and formulating the identification problem as multi class classification.

PharmaPack: Mobile fine-grained recognition of pharma packages

We consider the problem of fine-grained physical object recognition and introduce a dataset PharmaPack containing 1000 unique pharma packages enrolled in a controlled environment using consumer mobile phones as well as several recognition sets representing various scenarios. For performance evaluation, we extract two types of recently proposed local feature descriptors and aggregate them using popular tools. All enrolled raw and pre-processed images, extracted and aggregated descriptors are made public to promote reproducible research. To evaluate the baseline performance, we compare the methods based on aggregation of local descriptors with methods based on geometrical matching.

Identification in desynchronization channels

In this paper we analyze the problem of object identification in channels with desynchronization. In our analysis we assume that the identification system is designed using a pilot-based re-synchronization mechanism that assists desynchro-nization compensation with a certain accuracy. We demonstrate how the accuracy of re-synchronization impacts the information-theoretic limits of identification system performance.