Stuart J. Gibson

Synthesis of Photographic Quality Facial Composites using Evolutionary Algorithms

A facial composite system is described for use in criminal investigations which has distinct advantages over current methods. Unlike traditional feature based methods, our approach uses both local and global facial models, allowing a witness to evolve plausible, photo-realistic face images in an intuitive way. The basic method combines random sampling from a facial appearance model (AM) with an evolutionary algorithm (EA) to drive the search procedure to convergence. Three variants of the evolutionary algorithm have been explored and their performance measured using a computer simulation of a human witness (virtual witness). Further system functionality, provided by local appearance models and transformations of the appearance space which respectively allow both local features and semantic facial attributes to be manipulated, is presented. Preliminary examples of composites generated with our system are presented which demonstrate the potential superiority of the evolutionary approach to composite generation.

A person-specific, rigorous aging model of the human face

We present a statistically rigorous approach to the aging of digitised images of the human face. Our methodology is based on the calculation of optimised aging trajectories in a model space and aged images can be obtained through a fast, semi-automatic procedure. In addition, person-specific information about the subject at previous ages is included, allowing aging to proceed in the most appropriate direction in the model space. The theoretical basis is introduced and experimental results from our implementation are presented and discussed.

New methodology in facial composite construction: from theory to practice

Existing commercial, computerised techniques for constructing facial composites generated from eyewitness memory are essentially electronic versions of the original, mechanical feature-based systems such as PhotoFIT and Identikit. The effectiveness of this feature-based approach is fundamentally limited by the witnesss ability to recall and verbalise accurate descriptions of facial features from memory. Recent advances in facial composite methodology have led to software systems that do not rely on this process but instead exploit a cognitively less demanding process of recognition. We provide a technical overview of the EFIT-V system, currently being used by a number of police services in the UK.

Evolving and combining facial composites: Between-witness and within-witness morphs compared.

Student participant-witnesses produced 4 composites of unfamiliar faces with a system that uses a genetic algorithm to evolve appearance of artificial faces. Morphs of 4 composites produced by different witnesses (between-witness morphs) were judged better likenesses (Experiment 1) and were more frequently named (Experiment 2) by participants who were familiar with the target actors than were morphs of 4 composites produced by a single witness (within-witness morphs). Within-witness morphs were judged better likenesses and more frequently named than the best or the first-produced individual composites. The same results for likeness judgments were observed after possible artifacts in the comparison of between- and within-witness morphs were eliminated (Experiment 3). Experiment 4 showed that both internal and external features were better represented in morphs than in the original composites, although the representation of internal features improved more. The results suggest that morphing improves the representation of faces by reducing random error. Between-witness morphs yield more benefit than within-witness morphs by reducing consistent but idiosyncratic errors of individual witnesses. The experiments provide the first demonstration of an advantage for within-witness morphs produced using a single system. Experiment 2 provides the first demonstration of a reliable advantage for between-witness morphs in the most forensically relevant task: naming a composite of a familiar person produced by a witness who was unfamiliar with the target. Morphing would enhance the recognition of facial composites of criminals. Within-witness morphing provides a methodology for use in crimes in which the victim is the only witness.

Interactive evolutionary generation of facial composites for locating suspects in criminal investigations

Statistical appearance models have previously been used for computer face recognition applications in which an image patch is synthesized and morphed to match a target face image using an automated iterative fitting algorithm. Here we describe an alternative use for appearance models, namely for producing facial composite images (sometimes referred to as E-FIT or PhotoFIT images). This application poses an interesting real-world optimization problem because the target face exists in the mind of the witness and not in a tangible form such as a digital image. To solve this problem we employ an interactive evolutionary algorithm that allows the witness to evolve a likeness to the target face. A system based on our approach, called EFIT-V, is used frequently by three quarters of UK police constabularies.

Application of Raman spectroscopy for the differentiation of lipstick traces

This study demonstrates that Raman spectroscopy is a valuable tool for discriminating between lipstick samples under a range of forensically relevant situations. Trace amounts of lipstick smears deposited on textile fibres, cigarette butts and paper tissues were analysed. Differentiation of lipstick smears could be achieved with little or no interference from the underlying medium. Lipstick smears on glass slides, cigarette butts and tissues could also be analysed and identified in situ through evidence bags. Using a range of excitation frequencies (473, 633 and 784 nm) was effective in overcoming problems with fluorescent lipstick samples. The majority of the spectra of deposited lipstick samples remained unchanged over a period of up to two years. In some of the aged lipstick spectra, the (CC) band at 1655 cm−1 and the (CH) band at 3011 cm−1 were found to decrease in intensity and disappear over time. The use of chemometrics for the characterisation of large numbers of lipstick spectra was explored. Thirty spectra each from ten different lipsticks were analysed by Principal Components Analysis (PCA) and classified using the k-Nearest Neighbours (kNN) classifier. Up to 98.7% correct classification was achieved. Spectra from trace amounts of lipstick smears deposited on fibres were also analysed and classified using the same technique. 100% correct classification of these samples was achieved.

Computer assisted age progression

A computer assisted method for altering the perceived age of a human face is presented. Our technique is based on calculating a trajectory or axis within a multi-dimensional space that captures the changes in large scale facial structure, shading and complexion associated with aging. Fine facial details associated with increasing age, such as wrinkles, are added to the aged face using a variation on a standard image processing technique called high boost filtering. The method is successfully applied to two-dimensional photographic images exhibiting uncontrolled variations in pose and illumination. Unlike our previous work on automated age progression, here the objective is to allow a certain degree of manual control over the process by the adjustment of three key progression-control-parameters. In the future this work may form the basis for a software tool to be used by forensic artists.

No Bot Expects the DeepCAPTCHA! Introducing Immutable Adversarial Examples, With Applications to CAPTCHA Generation

Recent advances in deep learning (DL) allow for solving complex AI problems that used to be considered very hard. While this progress has advanced many fields, it is considered to be bad news for Completely Automated Public Turing tests to tell Computers and Humans Apart (CAPTCHAs), the security of which rests on the hardness of some learning problems. In this paper, we introduce DeepCAPTCHA, a new and secure CAPTCHA scheme based on adversarial examples, an inherit limitation of the current DL networks. These adversarial examples are constructed inputs, either synthesized from scratch or computed by adding a small and specific perturbation called adversarial noise to correctly classified items, causing the targeted DL network to misclassify them. We show that plain adversarial noise is insufficient to achieve secure CAPTCHA schemes, which leads us to introduce immutable adversarial noise—an adversarial noise that is resistant to removal attempts. In this paper, we implement a proof of concept system, and its analysis shows that the scheme offers high security and good usability compared with the best previously existing CAPTCHAs.

Graphite furnace atomic absorption elemental analysis of ecstasy tablets.

Six metals (copper, magnesium, barium, nickel, chromium and lead) were determined in two separate batches of seized ecstasy tablets by graphite furnace atomic absorption spectroscopy (GFAAS) following digestion with nitric acid and hydrogen peroxide. Large intra-batch variations were found as expected for tablets produced in clandestine laboratories. For example, nickel in batch 1 was present in the range 0.47-13.1 parts per million (ppm) and in batch 2 in the range 0.35-9.06 ppm. Although batch 1 had significantly higher 3,4-methylenedioxy-N-methamphetamine (MDMA) content than batch 2, barium was the only element which discriminated between the two ecstasy seizures (batch 1: 0.19-0.66 ppm, batch 2: 3.77-5.47 ppm).

A Comparison of Individual and Morphed Facial Composites Created Using Different Systems

An evaluation of individual and morphed composites created using the E-FIT and EFIT-V production systems was conducted. With the assistance of trained police staff, composites of unfamiliar targets were constructed from memory following a Cognitive Interview. EFIT-V composite production followed either a two-day delay, or on the same day as viewing a video of the target. E-FIT composites were created on the same day as viewing the target video. Morphs were produced from merging either two, or three composites created by the same witness, but with the assistance of a different operator. Participants familiar with the targets supplied similarity-to-target photograph ratings. No differences were found in the rated quality of composites created using E-FIT or EFIT-V, although a two-day delay in production resulted in inferior images. Morphs were rated as better likenesses than individual composites, although the benefits were greater with EFIT-Vs. Encouraging witnesses to create more than one composite image for subsequent morphing might enhance the likelihood of recognition of facial composites of criminals.