Learning from facial aging patterns for automatic age estimation

Age Specific Human-Computer Interaction (ASHCI) has vast potential applications in daily life. However, automatic age estimation technique is still underdeveloped. One of the main reasons is that the aging effects on human faces present several unique characteristics which make age estimation a challenging task that requires non-standard classification approaches. According to the speciality of the facial aging effects, this paper proposes the AGES (AGing pattErn Sub-space) method for automatic age estimation. The basic idea is to model the aging pattern, which is defined as a sequence of personal aging face images, by learning a representative subspace. The proper aging pattern for an unseen face image is then determined by the projection in the subspace that can best reconstruct the face image, while the position of the face image in that aging pattern will indicate its age. The AGES method has shown encouraging performance in the comparative experiments either as an age estimator or as an age range estimator.

Automatic age estimation based on facial aging patterns

While recognition of most facial variations, such as identity, expression, and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial variations, aging variation presents several unique characteristics which make age estimation a challenging task. This paper proposes an automatic age estimation method named AGES (AGing pattErn Subspace). The basic idea is to model the aging pattern, which is defined as the sequence of a particular individual's face images sorted in time order, by constructing a representative subspace. The proper aging pattern for a previously unseen face image is determined by the projection in the subspace that can reconstruct the face image with minimum reconstruction error, while the position of the face image in that aging pattern will then indicate its age. In the experiments, AGES and its variants are compared with the limited existing age estimation methods (WAS and AAS) and some well-established classification methods (kNN, BP, C4.5, and SVM). Moreover, a comparison with human perception ability on age is conducted. It is interesting to note that the performance of AGES is not only significantly better than that of all the other algorithms, but also comparable to that of the human observers.

syn-Facial hetero-bridged [n]polynorbornanes : a new class of polarofacial framework molecules composed of fused 7-oxa- and 7-azanorbornanes

New oxygen-bridged norbornane-fused cyclobutene epoxides and bis-(cyclobutene epoxides) are described and shown to react stereoselectively with 7-azanorbornenes to produce syn-facial N,O-bridged polynorbornanes and stereorandomly with 7-oxanorbornenes to produce O,O-bridged polynorbornanes as mixtures of syn-facial and anti-facial products.[1] Polarofacial systems containing up to six syn-facial norbornane bridges are described, while systems with seven co-facial oxygen atoms have been prepared by incorporating terminal epoxide rings to O5-[5]polynorbornanes. Ester-substituted 1,3,4-oxadiazoles are shown to be useful reagents for coupling 7-oxanorbornanes and produce predominantly syn-facial O-bridged polarofacial systems together with their anti-facial isomers.

Constructing artificial images of facial expressions

This paper presents a method for construction of artificial images of facial expressions. The proposed fractal-based synthesis procedure called pixel-based correspondence works on 2D images and does not require any depth information. This method can generate artificial images of an object when only a single image is given. Using the proposed method, effective example-based facial analysis systems can be trained and utilised in various applications.

Facial age estimation by nonlinear aging pattern subspace

Human age estimation by face images is an interesting yet challenging research topic emerging in recent years. This paper extends our previous work on facial age estimation (a linear method named AGES). In order to match the nonlinear nature of the human aging progress, a new algorithm named KAGES is proposed based on a nonlinear subspace trained on the aging patterns, which are defined as sequences of individual face images sorted in time order. Both the training and test (age estimation) processes of KAGES rely on a probabilistic model of KPCA. In the experimental results, the performance of KAGES is not only better than all the compared algorithms, but also better than the human observers in age estimation. The results are sensitive to parameter choice however, and future research challenges are identified.

Pixel-based correspondence for facial images

A pixel-based correspondence method is presented for representation of facial images. The proposed method consists of two modules: face-image matching and face-image morphing. In the face-image matching module, the correspondence between two images are calculated for all pixel locations. A novel area-based matching method is proposed that makes use of the concept of the fractal dimension, and develops a non-parametric local transform as a basis for establishing correspondence between two face images. In the face-image morphing module, a mapping is performed for deformation of the source face image onto the target face image. This is done to map the pixels in the source face image to the location of their corresponding pixels in the target image.

Facial image analysis

This thesis focuses on novel technologies for facial image analysis, which involves three topics: face recognition under uncontrolled conditions, automatic facial age estimation, and context-aware fusion of face and gait. They are either key issues bridging laboratorial research and real applications, or innovative problems that have barely been studied before.

Facial affect recognition and schizotypal personality characteristics

Aim: Deficits in facial affect recognition are well established in schizophrenia, yet relatively little research has examined facial affect recognition in hypothetically psychosis-prone or ‘schizotypal’ individuals. Those studies that have examined social cognition in psychosis-prone individuals have paid little attention to the association between facial emotion recognition and particular schizotypal personality features. The present study therefore sought to investigate relationships between facial emotion recognition and the different aspects of schizotypy.

Methods: Facial affect recognition accuracy was examined in 50 psychiatrically healthy individuals assessed for level of schizotypy using the Schizotypal Personality Questionnaire. This instrument provides a multidimensional measure of schizophrenia proneness, encompassing ‘cognitive-perceptual’, ‘interpersonal’ and ‘disorganized’ features of schizotypy. It was hypothesized that the cognitive-perceptual and interpersonal aspects of schizotypy would be associated with difficulties identifying facial expressions of emotion during a forced-choice recognition task using a standardized series of colour photographs.

Results: As predicted, interpersonal aspects of schizotypy (particularly social anxiety) were associated with reduced accuracy on the facial affect recognition task, but there was no association between affect recognition accuracy and cognitive-perceptual features of schizotypy.

Conclusions: These results suggest that subtle deficits in facial affect recognition in otherwise psychiatrically healthy individuals may be related to the vulnerability for interpersonal communication difficulties, as seen in schizophrenia.

Low cost multimodal facial recognition via kinect sensors

This paper presents a novel low cost 3D facial recognition using gaming sensors such as Kinect™. The paper describes the hardware, calibration and infrared noise and pattern interference challenges of integrating multiple Kinect sensors. The preliminary results show a promising trend for low cost solutions that can be populated in crowded facilities such as malls and airports.

Evolution of a contagious cancer: epigenetic variation in devil facial tumour disease

The emergence of Devil Facial Tumour Disease (DFTD), a highly contagious cancer, is driving Tasmanian devils (Sarcophilus harrisii) to extinction. The cancer is a genetically and chromosomally stable clonal cell line which is transmitted by biting during social interactions. In the present study, we explore the Devil Facial Tumour (DFT) epigenome and the genes involved in DNA methylation homeostasis. We show that tumour cells have similar levels of methylation to peripheral nerves, the tissue from which DFTD originated. We did not observe any strain or region-specific epimutations. However, we revealed a significant increase in hypomethylation in DFT samples over time (p < 0.0001). We propose that loss of methylation is not because of a maintenance deficiency, as an upregulation of DNA methyltransferase 1 gene was observed in tumours compared with nerves (p < 0.005). Instead, we believe that loss of methylation is owing to active demethylation, supported by the temporal increase in MBD2 and MBD4 (p < 0.001). The implications of these changes on disease phenotypes need to be explored. Our work shows that DFTD should not be treated as a static entity, but rather as an evolving parasite with epigenetic plasticity. Understanding the role of epimutations in the evolution of this parasitic cancer will provide unique insights into the role of epigenetic plasticity in cancer evolution and progression in traditional cancers that arise and die with their hosts.