2D/3D image (facial) comparison using camera matching

A problem in forensic facial comparison of images of perpetrators and suspects is that distances between fixed anatomical points in the face, which form a good starting point for objective, anthropometric comparison, vary strongly according to the position and orientation of the camera. In case of a cooperating suspect, a 3D image may be taken using e.g. a laser scanning device. By projecting the 3D image onto a 2D image with the suspect's head in the same pose as that of the perpetrator, using the same focal length and pixel aspect ratio, numerical comparison of (ratios of) distances between fixed points becomes feasible. An experiment was performed in which, starting from two 3D scans and one 2D image of two colleagues, male and female, and using seven fixed anatomical locations in the face, comparisons were made for the matching and non-matching case. Using this method, the non-matching pair cannot be distinguished from the matching pair of faces. Facial expression and resolution of images were all more or less optimal, and the results of the study are not encouraging for the use of anthropometric arguments in the identification process. More research needs to be done though on larger sets of facial comparisons.     

Development and Validation of a Technique for Casting Anatomical Features and Toolmarks

Time may elapse between examination of marks inflicted on the body and comparison with a potential weapon. Two‐dimensional photographs may be inadequate for effective comparison of a three‐dimensional mark with a putative instrument. Taking a cast and producing a positive image results in a lasting three‐dimensional record. This project aimed to develop and demonstrate the accuracy of an easy technique for production of long‐lasting positive images (using plaster of Paris and dental alginate). Casts of facial features of embalmed cadavers were used to produce a positive image of the face (death mask). Measurements of distances between facial anatomical landmarks were compared with measurements of distances between the same landmarks on the death masks to assess accuracy of reproduction. There were no significant differences between cadaver and death mask in 6 of 9 measurements, indicating this technique has high accuracy with less mobile facial features, but produces deformation of pliable features.     

Photo identification: facial metrical and morphological features in South African males

Personal identification of individuals is very important in forensic sciences. Facial identification is becoming even more relevant with increasing crime rates, problems with access control and terrorist attacks. To make facial identification more accurate, an in depth knowledge of the common and rare facial characteristics seen in various populations is needed. This will be advantageous when comparing facial photographs. Currently very little data is available on the facial variation of South Africans. Therefore the aim of this study was to analyse the facial features of a group of South African Bantu-speaking men, to determine the common and rare facial features seen in the group. Facial photographs were taken for 200 volunteers from the Pretoria Police College, in the norma frontalis position. The subjects were between 20 and 40 years of age, with no facial deformities. Thirteen measurements were taken directly from the photographs and used in 12 indices. Eight morphological features were also analysed on each face. Each feature was divided into different categories, which described variants of that feature. The metrical and morphological data were then used to create various combinations of facial characteristics that described different regions of the face. The frequency of occurrence of these combinations was calculated for the study population. The most common features were oval or inverted trapezoid facial shapes, intermediate size noses with a down-turned septum tilt and intermediate size mouths with a flat V-shaped upper lip notch (cupid's bow). The eyes were mostly situated closely together. Some of the rare or absent features included round or square facial shapes and narrow noses with an upturned septum tilt. Matching these rare features on facial photographs will be useful during cases of disputed identification.     

The influence of camera-to-object distance and focal length on the representation of faces

When one thinks of the so-called barrel or wide-angle distortion, grotesquely warped faces may come to mind. For less extreme cases with primarily inconspicuous facial proportions, the question, however, still arises whether there may be a resulting impact on the identification of faces. In the first experiment, 3 test persons were photographed at a fixed camera-to-object distance of 2 m. In the second experiment, 18 test persons were each photographed at a distance of 0.5 m and 2.0 m. For both experiments photographs were taken from a fixed angle of view in alignment with the Frankfurt Plane. An isolated effect of the focal length on facial proportions could not be demonstrated. On the other hand, changes in the camera-to-object distance clearly influenced facial proportions and shape. A standardized camera-to-object distance for passport photos, as well as reconstruction of the camera-to-object distance from crime scene photos and the use of this same distance in taking photographs for comparison of suspects are called for. A proposal to refer to wide-angle distortion as the nearness effect is put forward.     

Computer-assisted skull identification system using video superimposition

This system consists of two main units, namely a video superimposition system and a computer-assisted skull identification system. The video superimposition system is comprised of the following five parts: a skull-positioning box having a monochrome CCD camera, a photo-stand having a color CCD camera, a video image mixing device, a TV monitor and a videotape recorder. The computer-assisted skull identification system is composed of a host computer including our original application software, a film recorder and a color printer. After the determination of the orientation and size of the skull to those of the facial photograph using the video superimposition system, the skull and facial photograph images are digitized and stored within the computer, and then both digitized images are superimposed on the monitor. For the assessment of anatomical consistency between the digitized skull and face, the distance between the landmarks and the thickness of soft tissue of the anthropometrical points are semi-automatically measured on the monitor. The wipe images facilitates the comparison of positional relationships between the digitized skull and face. The software includes the polynomial functions and Fourier harmonic analysis for evaluating the match of the outline such as the forehead and mandibular line in both the digitized images.     

Computer-assisted facial image identification system using a 3-D physiognomic range finder

This system consists of a 3-D physiognomic range finder and a computer-assisted facial image superimposition unit. The 3-D range finder is composed of a detector for measuring facial surface and its control computer. The detector has two sinusoidal grating projection devices and two CCD cameras. The computer-assisted facial image superimposition unit consists of a host computer including a proprietary software, a flat surface color display and a color image scanner for inputting 2-D facial images of a criminal. The 3-D facial shape and texture of a suspect is obtained by using the range finder. To make the comparison between the 3-D facial image and the 2-D facial image, the 3-D facial image is first reproduced on a display of the host computer from a MO disk and then the 2-D facial image is taken with the color image scanner and reproduced on the display. The 3-D facial image is exactly adjusted to match the orientation and size of the 2-D facial image under the fine framework mode, and then the fine framework mode of 3-D facial image is converted to the fine texture image. The shape and positional relationships of facial components between the 3-D and 2-D facial images are examined by the fade-out or wipe image mode. The distance between the selected two points and angle among the selected three points on the 3-D and 2-D facial images are automatically measured for the assessment of anthropometrical data between both images. For evaluating the fit between the anthropometrical points on the 3-D and 2-D facial images, the reciprocal point-to-point difference between both images is compared.     

Image conditions for machine-based face recognition of juvenile faces

Machine-based facial recognition could help law enforcement and other organisations to match juvenile faces more efficiently. It is especially important when dealing with indecent images of children to minimise the workload, and deal with moral and stamina challenges related to human recognition. With growth related changes, juvenile face recognition is challenging. The challenge not only relates to the growth of the child’s face, but also to face recognition in the wild with unconstrained images. The aim of the study was to evaluate how different conditions (i.e. black and white, cropped, blur and resolution reduction) can affect machine-based facial recognition of juvenile age progression. The study used three off-the-shelf facial recognition algorithms (Microsoft Face API, Amazon Rekognition, and Face++) and compared the original images and the age progression images under the four image conditions against an older image of the child. The results showed a decrease in facial similarity with an increased age gap, in comparison to Microsoft; Amazon and Face++ showed higher confidence scores and are more resilient to a change in image condition. The image condition ‘black and white’ and ‘cropped’ had a negative effect across all three APIs. The relationship between age progression images and the younger original image was explored. The results suggest manual age progression images are no more useful than the original image for facial identification of missing children, and Amazon and Face++ performed better with the original image.     

A new experimental approach to computer-aided face/skull identification in forensic anthropology

The present study introduces a new approach to computer-assisted face/skull matching used for personal identification purposes in forensic anthropology.In this experiment, the authors formulated an algorithm able to identify the face of a person suspected to have disappeared, by comparing the respective person's facial image with the skull radiograph. A total of 14 subjects were selected for the study, from which a facial photograph and skull radiograph were taken and ultimately compiled into a database, saved to the hard drive of a computer. The photographs of the faces and corresponding skull radiographs were then drafted using common photographic software, taking caution not to alter the informational content of the images. Once computer generated, the facial images and menu were displayed on a color monitor. In the first phase, a few anatomic points of each photograph were selected and marked with a cross to facilitate and more accurately match the face with its corresponding skull. In the second phase, the above mentioned cross grid was superimposed on the radiographic image of the skull and brought to scale. In the third phase, the crosses were transferred to the cranial points of the radiograph. In the fourth phase, the algorithm calculated the distance of each transferred cross and the corresponding average. The smaller the mean value, the greater the index of similarity between the face and skull.A total of 196 cross-comparisons were conducted, with positive identification resulting in each case. Hence, the algorithm matched a facial photograph to the correct skull in 100% of the cases.     

Evaluation of anthropometric accuracy and reliability using different three-dimensional scanning systems

The aim of this study was to evaluate the accuracy and reliability of standard anthropometric linear measurements made with three different three-dimensional scanning systems namely laser surface scanning (Minolta Vivid 900), cone beam computed tomography (CBCT), 3D stereo-photogrammetry (Di3D system) and to compare them to physical linear measurements. The study sample consisted of seven cadaver heads. The reliability and accuracy were assessed by means of a series of 21 standardized, linear facial measurements derived from 15 landmarks taken both directly on the face with a set of digital callipers and indirectly from a three-dimensional (3D) soft tissue surface models derived from CBCT, laser surface scans and 3D photographs. Statistical analysis for the reliability was done by means of intraclass correlation coefficients (ICCs). Accuracy was determined by means of the absolute error (AE) and absolute percentage error (APE) by comparison of the 3D measurements to the physical anthropometrical measurements. All the 3D scanning systems were proved to be very reliable (ICC>0.923-0.999) when compared to the physical measurements (ICC; 0.964-0.999). Only one CBCT measurement (t-g) and one Di3D measurement (t-sn left) had a mean AE of more than 1.5mm. There are clear potential benefits of using 3D measurements appose to direct measurements in the assessment of facial deformities. Measurements recorded by the three 3D systems appeared to be both sufficiently accurate and reliable enough for research and clinical use.     

Failure of anthropometry as a facial identification technique using high-quality photographs

Anthropometry can be used in certain circumstances to facilitate comparison of a photograph of a suspect with that of the potential offender from surveillance footage. Experimental research was conducted to determine whether anthropometry has a place in forensic practice in confirming the identity of a suspect from a surveillance video. We examined an existing database of photographic lineups, where one video image was compared against 10 photographs, which has previously been used in psychological research. Target (1) and test (10) photos were of high quality, although taken with a different camera. The anthropometric landmarks of right and left ectocanthions, nasion, and stomion were chosen, and proportions and angle values between these landmarks were measured to compare target with test photos. Results indicate that these measurements failed to accurately identify targets. There was also no indication that any of the landmarks made a better comparison than another. It was concluded that, for these landmarks, this method does not generate the consistent results necessary for use as evidence in a court of law.     

Photographs of the human face and broken projective symmetry

The exact projective symmetry manifested in photographs is broken if the object is not flat. It has been found that front view perspectives of the human face, photographed with limited variations in camera angle (within 30 degrees) show a breaking projective symmetry sufficiently small to be considered for accurate comparison. As a practical implementation of this new approach, a computer-controlled video camera superimposition technique has been developed and demonstrated in the identification of a disguised human face.     

A Preliminary Study of the Reliability of Anatomical Facial Landmarks Used in Facial Comparison

Anatomical landmarks are considered the most objective indicators for use in forensic facial comparisons. Therefore, accurately identifying and locating these landmarks is the beginning of reliable facial comparison. This study evaluated the accuracy with which facial landmarks are located and examined their reliability according to type of landmark, head posture, and image quality. Nine operators located a series of landmarks on prepared facial images used to produce comparison images. Then, the average distances between the reciprocal landmarks (ADRL) on the reference and the comparison images were measured as indicators of landmark reliability. We found that a set of landmarks had higher or lower reliability as a function of the head angle and image quality. More reliable landmarks were associated with certain head postures and degrees of image quality. These should be used for facial comparison analysis depending on various head and image conditions.     

The ideal subject distance for passport pictures

In an age of global combat against terrorism, the recognition and identification of people on document images is of increasing significance. Experiments and calculations have shown that the camera-to-subject distance - not the focal length of the lens - can have a significant effect on facial proportions. Modern passport pictures should be able to function as a reference image for automatic and manual picture comparisons. This requires a defined subject distance. It is completely unclear which subject distance, in the taking of passport photographs, is ideal for the recognition of the actual person. We show here that the camera-to-subject distance that is perceived as ideal is dependent on the face being photographed, even if the distance of 2m was most frequently preferred. So far the problem of the ideal camera-to-subject distance for faces has only been approached through technical calculations. We have, for the first time, answered this question experimentally with a double-blind experiment. Even if there is apparently no ideal camera-to-subject distance valid for every face, 2m can be proposed as ideal for the taking of passport pictures. The first step would actually be the determination of a camera-to-subject distance for the taking of passport pictures within the standards. From an anthropological point of view it would be interesting to find out which facial features allow the preference of a shorter camera-to-subject distance and which allow the preference of a longer camera-to-subject distance.     

Background correction in forensic photography. II. Photography of blood under conditions of non-uniform illumination or variable substrate color--practical aspects and limitations

The combination of photographs taken at wavelengths at and bracketing the peak of a narrow absorbance band can lead to enhanced visualization of the substance causing the narrow absorbance band. This concept can be used to detect putative bloodstains by division of a linear photographic image taken at or near 415 nm with an image obtained by averaging linear photographs taken at or near 395 and 435 nm. Nonlinear images can also be background corrected by substituting subtraction for the division. This paper details experimental applications and limitations of this technique, including wavelength selection of the illuminant and at the camera. Characterization of a digital camera to be used in such a study is also detailed. Detection limits for blood using the three wavelength correction method under optimum conditions have been determined to be as low as 1 in 900 dilution, although on strongly patterned substrates blood diluted more than twenty-fold is difficult to detect. Use of only the 435 nm photograph to estimate the background in the 415 nm image lead to a twofold improvement in detection limit on unpatterned substrates compared with the three wavelength method with the particular camera and lighting system used, but it gave poorer background correction on patterned substrates.     

Background correction in forensic photography. I. Photography of blood under conditions of non-uniform illumination or variable substrate color--theoretical aspects and proof of concept

The combination of photographs taken at two or three wavelengths at and bracketing an absorbance peak indicative of a particular compound can lead to an image with enhanced visualization of the compound. This procedure works best for compounds with absorbance bands that are narrow compared with "average" chromophores. If necessary, the photographs can be taken with different exposure times to ensure that sufficient light from the substrate is detected at all three wavelengths. The combination of images is readily performed if the images are obtained with a digital camera and are then processed using an image processing program. Best results are obtained if linear images at the peak maximum, at a slightly shorter wavelength, and at a slightly longer wavelength are used. However, acceptable results can also be obtained under many conditions if non-linear photographs are used or if only two wavelengths (one of which is at the peak maximum) are combined. These latter conditions are more achievable by many "mid-range" digital cameras. Wavelength selection can either be by controlling the illumination (e.g., by using an alternate light source) or by use of narrow bandpass filters. The technique is illustrated using blood as the target analyte, using bands of light centered at 395, 415, and 435 nm. The extension of the method to detection of blood by fluorescence quenching is also described.     

Photographic Image Comparison of Vegetation

Images and videos are common types of evidence in crime scene investigations and laboratory analysis. Images may be taken by the suspect and/or by crime scene investigators and may serve as crucial elements in forensic laboratory analysis. Forensic photographic image comparison is the process of comparing one or more objects or persons in photographs/images when at least one image is known to be related to a crime. The forensic examiner usually compares the images in order to determine whether or not an association between the exhibits in the images can be made. This paper proposes an extension to the currently prevalent photographic image examination method. The extension introduces comparison of landscape and vegetation over time. It is revealed that similarities between images may still be found between the period of time the suspect photograph was taken and the period the crime scene investigator took the photograph from the same area. In this case report, two suspects to be involved in growing a marijuana field were arrested by the police. The forensic experts were asked to examine images taken by the crime scene investigators and to compare them to the images found in the suspects’ phones. They then tried to determine whether the suspects could be linked to the specific locations. While applying techniques derived from morphological comparison methodologies, the plants at the scene provided significant additional information. A tree trunk, branches, and twigs on a hedge in the photographs revealed specific individual characteristics that led the examiner to reach a conclusive decision.     

Individual identification of disguised faces by morphometrical matching

The reliability of a morphometrical matching method for identifying disguised faces was examined experimentally using a computer-assisted facial image identification system. The 2D right oblique facial images of three target persons disguised with sunglasses, cap and gauze mask were each compared with each of the 3D facial images of 100 subjects, yielding 900 face-to-face superimpositions. The average perpendicular distance between the facial outlines and the average point-to-point distance of the corresponding landmarks in the 2D image of the disguised face and the 3D facial image, were calculated. As a matching criterion, the sum of the values of the average perpendicular difference of the facial outlines and the average point-to-point difference between the corresponding landmarks was used (abbreviation: average difference).The range of the average difference was 2.3-2.8mm for the same person (a match) and 4.0-14.6mm for different (non-matching) people, respectively. The ranges for matching and non-matching faces did not overlap. Even the 3D facial images of the non-matching person showing the closest value of average difference to the average difference for the matching person could be excluded easily. It was concluded that the morphometrical matching method can reliably identify disguised faces and the results produced by this method could be easily understandable by a court of law.     

Accuracy of facial soft tissue thickness measurements in personal computer-based multiplanar reconstructed computed tomographic images

The purpose of this study was to determine the precision and accuracy of facial soft tissue measurement using personal computer (PC)-based multiplanar reconstructed (MPR) computed tomography (CT) images and to evaluate the effect of the various CT scanning protocols on the facial soft tissue thickness measurement. Thirteen different CT imaging protocols were used to image a cadaver head. MPR reformations and three-dimensional (3D) reconstructions viewed on a laptop PC were used to make measurements at six specific sites on each set of images. These measurements were compared to physical measurements at the same sites. Increasing the slice thickness resulted in decreased image quality. Within the same slice thickness, increasing the pitch ratio in the spiral mode, resulted in decreasing image quality. The image quality of conventional CT scanning was relatively poorer than that of the spiral CT scanning. However, the mean deviation from the physical measurement was within 0.43 mm in every instance. This mean deviation was quite small and clinically acceptable for measuring the soft tissue thickness of the facial area. PC-based MPR CT images of the face using routine scanning CT protocols can be used to accurately measure soft tissue thickness in the facial region. However, for more fine and accurate data collection, scanning protocols with slice thicknesses less than 5mm, and a spiral/helical mode pitch less than 2:1 are recommended.     

Human Identification Using Automatic and Semi‐Automatically Detected Facial Marks

Continuing advancements in the field of digital cameras and surveillance imaging devices have led law enforcement and intelligence agencies to use analysis of images and videos for the investigation and prosecution of crime. When determining identity from photographic evidence, forensic analysts perform comparison of visible facial features manually, which is inefficient. In this study, we will address research efforts to use facial marks as biometric signatures to distinguish between individuals. We propose two systems to assist forensic analysts during photographic comparison: an improved multiscale facial mark system in which facial marks are detected automatically, and a semi‐automatic facial mark system that integrates human knowledge within the improved multiscale facial mark system. Experiment results employ a high‐resolution time‐elapsed dataset acquired at the University of Notre Dame between 2009 and 2011. The results indicate that the geometric distributions of facial mark patterns can be used to distinguish between individuals.     

Facial Age Synthesis Using Sparse Partial Least Squares (The Case of Ben Needham)

Automatic facial age progression (AFAP) has been an active area of research in recent years. This is due to its numerous applications which include searching for missing. This study presents a new method of AFAP. Here, we use an active appearance model (AAM) to extract facial features from available images. An aging function is then modelled using sparse partial least squares regression (sPLS). Thereafter, the aging function is used to render new faces at different ages. To test the accuracy of our algorithm, extensive evaluation is conducted using a database of 500 face images with known ages. Furthermore, the algorithm is used to progress Ben Needham's facial image that was taken when he was 21 months old to the ages of 6, 14, and 22 years. The algorithm presented in this study could potentially be used to enhance the search for missing people worldwide.