Face Recognition with Multi-Resolution Spectral Feature Images

The one-sample-per-person problem has become an active research topic for face recognition in recent years because of its challenges and significance for real-world applications. However, achieving relatively higher recognition accuracy is still a difficult problem due to, usually, too few training samples being available and variations of illumination and expression. To alleviate the negative effects caused by these unfavorable factors, in this paper we propose a more accurate spectral feature image-based 2DLDA (two-dimensional linear discriminant analysis) ensemble algorithm for face recognition, with one sample image per person. In our algorithm, multi-resolution spectral feature images are constructed to represent the face images; this can greatly enlarge the training set. The proposed method is inspired by our finding that, among these spectral feature images, features extracted from some orientations and scales using 2DLDA are not sensitive to variations of illumination and expression. In order to maintain the positive characteristics of these filters and to make correct category assignments, the strategy of classifier committee learning (CCL) is designed to combine the results obtained from different spectral feature images. Using the above strategies, the negative effects caused by those unfavorable factors can be alleviated efficiently in face recognition. Experimental results on the standard databases demonstrate the feasibility and efficiency of the proposed method.     

Quantifying Plant Colour and Colour Difference as Perceived by Humans Using Digital Images

Human perception of plant leaf and flower colour can influence species management. Colour and colour contrast may influence the detectability of invasive or rare species during surveys. Quantitative, repeatable measures of plant colour are required for comparison across studies and generalisation across species. We present a standard method for measuring plant leaf and flower colour traits using images taken with digital cameras. We demonstrate the method by quantifying the colour of and colour difference between the flowers of eleven grassland species near Falls Creek, Australia, as part of an invasive species detection experiment. The reliability of the method was tested by measuring the leaf colour of five residential garden shrub species in Ballarat, Australia using five different types of digital camera. Flowers and leaves had overlapping but distinct colour distributions. Calculated colour differences corresponded well with qualitative comparisons. Estimates of proportional cover of yellow flowers identified using colour measurements correlated well with estimates obtained by measuring and counting individual flowers. Digital SLR and mirrorless cameras were superior to phone cameras and point-and-shoot cameras for producing reliable measurements, particularly under variable lighting conditions. The analysis of digital images taken with digital cameras is a practicable method for quantifying plant flower and leaf colour in the field or lab. Quantitative, repeatable measurements allow for comparisons between species and generalisations across species and studies. This allows plant colour to be related to human perception and preferences and, ultimately, species management.     

Species Identification of Food Contaminating Beetles by Recognizing Patterns in Microscopic Images of Elytra Fragments

A crucial step of food contamination inspection is identifying the species of beetle fragments found in the sample, since the presence of some storage beetles is a good indicator of insanitation or potential food safety hazards. The current pratice, visual examination by human analysts, is time consuming and requires several years of experience. Here we developed a species identification algorithm which utilizes images of microscopic elytra fragments. The elytra, or hardened forewings, occupy a large portion of the body, and contain distinctive patterns. In addition, elytra fragments are more commonly recovered from processed food products than other body parts due to their hardness. As a preliminary effort, we chose 15 storage product beetle species frequently detected in food inspection. The elytra were then separated from the specimens and imaged under a microscope. Both global and local characteristics were quantified and used as feature inputs to artificial neural networks for species classification. With leave-one-out cross validation, we achieved overall accuracy of 80% through the proposed global and local features, which indicates that our proposed features could differentiate these species. Through examining the overall and per species accuracies, we further demonstrated that the local features are better suited than the global features for species identification. Future work will include robust testing with more beetle species and algorithm refinement for a higher accuracy.     

Testing the Utility of a Data-Driven Approach for Assessing BMI from Face Images

Several lines of evidence suggest that facial cues of adiposity may be important for human social interaction. However, tests for quantifiable cues of body mass index (BMI) in the face have examined only a small number of facial proportions and these proportions were found to have relatively low predictive power. Here we employed a data-driven approach in which statistical models were built using principal components (PCs) derived from objectively defined shape and color characteristics in face images. The predictive power of these models was then compared with models based on previously studied facial proportions (perimeter-to-area ratio, width-to-height ratio, and cheek-to-jaw width). Models based on 2D shape-only PCs, color-only PCs, and 2D shape and color PCs combined each performed significantly and substantially better than models based on one or more of the previously studied facial proportions. A non-linear PC model considering both 2D shape and color PCs was the best predictor of BMI. These results highlight the utility of a “bottom-up”, data-driven approach for assessing BMI from face images.     

Linkage Disequilibrium in Humans: Models and Data

In this review, we describe recent empirical and theoretical work on the extent of linkage disequilibrium (LD) in the human genome, comparing the predictions of simple population-genetic models to available data. Several studies report significant LD over distances longer than those predicted by standard models, whereas some data from short, intergenic regions show less LD than would be expected. The apparent discrepancies between theory and data present a challenge-both to modelers and to human geneticists-to identify which important features are missing from our understanding of the biological processes that give rise to LD. Salient features may include demographic complications such as recent admixture, as well as genetic factors such as local variation in recombination rates, gene conversion, and the potential segregation of inversions. We also outline some implications that the emerging patterns of LD have for association-mapping strategies. In particular, we discuss what marker densities might be necessary for genomewide association scans.     

Perfect Order: Recognizing Complexity in Bali

Perfect Order: Recognizing Complexity in Bali . J. Stephen Lansing. Princeton: Princeton University Press, 2006. 225 pp.     

Yawning: Relation to Sleeping and Stretching in Humans

The temporal relations among yawning, sleeping, and stretching were investigated by having undergraduate college students record the occurrences of these behaviors during a one-week period. Yawning was most frequent during the hour before sleeping and after waking. In contrast, stretching was common only during the hour after waking. Concurrent yawning and stretching were common but stretching was accompanied more often by yawning than vice-versa. The temporal proximity of yawning to sleep and waking times is probably the basis for yawning as a paralinguistic signal for drowsiness. The role of contagious yawning in synchronizing the behavior and physiological state of a group is considered.     

Recognizing Gay and Lesbian Speech

Beyond the Lavender Lexicon: Authenticity, Imagination, and Appropriation in Lesbian and Gay Languages. William L. Leap. ed. Luxembourg: Gordon and Breach, 1995. 360 pp.
Word's Out: Gay Men's English. William L. Leap. Minneapolis: University of Minnesota Press, 1996. 181 pp.     

Recognizing and remodeling the nucleosome

The X-ray structure of the nucleosome core particle (NCP) has been a major milestone in the structural biology of chromatin. Since, our understanding how NCPs interact with multiple partners has been extending from single chromatin-binding domains recognizing post-translational modifications (PTMs) in histone tails towards the recognition of higher-order chromatin structure by multi-subunit chromatin remodeling complexes. The current review summarizes recent progress in the structural biology of nucleosome-recognition from chromatin-binding domains to multi-protein remodeling complexes.     

FR-CAPTCHA: CAPTCHA Based on Recognizing Human Faces

A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is designed to distinguish humans from machines. Most of the existing tests require reading distorted text embedded in a background image. However, many existing CAPTCHAs are either too difficult for humans due to excessive distortions or are trivial for automated algorithms to solve. These CAPTCHAs also suffer from inherent language as well as alphabet dependencies and are not equally convenient for people of different demographics. Therefore, there is a need to devise other Turing tests which can mitigate these challenges. One such test is matching two faces to establish if they belong to the same individual or not. Utilizing face recognition as the Turing test, we propose FR-CAPTCHA based on finding matching pairs of human faces in an image. We observe that, compared to existing implementations, FR-CAPTCHA achieves a human accuracy of 94% and is robust against automated attacks.     

Recognizing death: liver phagocytosis of apoptotic cells

Apoptosis impacts on nearly all areas of cell biology and continues to draw increasing numbers of investigators to join in the multifaceted race to understand it. Within the study of cell death the area that has less benefited from the fast advances has been the study of the phagocytic process of apoptotic cells. But finally this field is now converging the attention and the studies of an increasing number of researchers that are highlighting its importance. This review deals with removal of apoptotic cells; in particular, the liver cell mediated removal of apoptotic blood cells will be considered. The involvement of carbohydrate-specific receptors of liver cells in the recognition and engulfment of apoptotic cells has been tested using three different experimental approaches: i- in vivo induction of apoptosis; ii- in vitro phagocytosis; iii- in situ adhesion experiments. All three main cell liver types are able to recognize and internalize apoptotic cells mainly by means of carbohydrate-specific receptors (galactose and mannose). By up-regulating the cell surface expression of mannose receptors of the endothelial cells, the recognition and the internalization of apoptotic lymphocytes can be increased. Of note is the discrimination in the recognition of apoptotic lymphocytes by the sinusoidal cells: only homologous cells are rapidly and efficiently deleted from the circulation.