Illumination Normalization of Face Image Based on Illuminant Direction Estimation and Improved Retinex

Illumination normalization of face image for face recognition and facial expression recognition is one of the most frequent and difficult problems in image processing. In order to obtain a face image with normal illumination, our method firstly divides the input face image into sixteen local regions and calculates the edge level percentage in each of them. Secondly, three local regions, which meet the requirements of lower complexity and larger average gray value, are selected to calculate the final illuminant direction according to the error function between the measured intensity and the calculated intensity, and the constraint function for an infinite light source model. After knowing the final illuminant direction of the input face image, the Retinex algorithm is improved from two aspects: (1) we optimize the surround function; (2) we intercept the values in both ends of histogram of face image, determine the range of gray levels, and stretch the range of gray levels into the dynamic range of display device. Finally, we achieve illumination normalization and get the final face image. Unlike previous illumination normalization approaches, the method proposed in this paper does not require any training step or any knowledge of 3D face and reflective surface model. The experimental results using extended Yale face database B and CMU-PIE show that our method achieves better normalization effect comparing with the existing techniques.     

Protein subcellular localization prediction using a hybrid of similarity search and error-correcting output code techniques that produces interpretable results

In silico prediction of protein subcellular localization based on amino acid sequence can reveal valuable information about the protein's innate roles in the cell. Unfortunately, such prediction is made difficult because of complex protein sorting signals. Some prediction methods are based on searching for similar proteins with known localization, assuming that known homologs exist. However, it may not perform well on proteins with no known homolog. In contrast, machine learning-based approaches attempt to infer a predictive model that describes the protein sorting signals. Alas, in doing so, it does not take advantage of known homologs (if they exist) by doing a simple "table lookup". Here, we capture the best of both worlds by combining both approaches. On a dataset with 12 locations, similarity-based and machine learning independently achieve an accuracy of 83.8% and 72.6%, respectively. Our hybrid approach yields an improved accuracy of 85.9%. We compared our method with three other methods' published results. For two of the methods, we used their published datasets for comparison. For the third we used the 12 location dataset. The Error Correcting Output Code algorithm was used to construct our predictive model. This algorithm gives attention to all the classes regardless of number of instances and led to high accuracy among each of the classes and a high prediction rate overall. We also illustrated how the machine learning classifier we use, built over a meaningful set of features can produce interpretable rules that may provide valuable insights into complex protein sorting mechanisms.     

Enhanced Localization of Genetic Samples through Linkage-Disequilibrium Correction

Characterizing the spatial patterns of genetic diversity in human populations has a wide range of applications, from detecting genetic mutations associated with disease to inferring human history. Current approaches, including the widely used principal-component analysis, are not suited for the analysis of linked markers, and local and long-range linkage disequilibrium (LD) can dramatically reduce the accuracy of spatial localization when unaccounted for. To overcome this, we have introduced an approach that performs spatial localization of individuals on the basis of their genetic data and explicitly models LD among markers by using a multivariate normal distribution. By leveraging external reference panels, we derive closed-form solutions to the optimization procedure to achieve a computationally efficient method that can handle large data sets. We validate the method on empirical data from a large sample of European individuals from the POPRES data set, as well as on a large sample of individuals of Spanish ancestry. First, we show that by modeling LD, we achieve accuracy superior to that of existing methods. Importantly, whereas other methods show decreased performance when dense marker panels are used in the inference, our approach improves in accuracy as more markers become available. Second, we show that accurate localization of genetic data can be achieved with only a part of the genome, and this could potentially enable the spatial localization of admixed samples that have a fraction of their genome originating from a given continent. Finally, we demonstrate that our approach is resistant to distortions resulting from long-range LD regions; such distortions can dramatically bias the results when unaccounted for.     

Two lipid-packing sensor motifs contribute to the sensitivity of ArfGAP1 to membrane curvature

ArfGAP1 (Arf GTPase activating protein 1) controls the cycling of the COPI coat on Golgi membranes by catalyzing GTP hydrolysis in the small G protein Arf1. ArfGAP1 contains a central motif named ALPS (ArfGAP1 lipid-packing sensor) that adsorbs preferentially onto highly curved membranes. This motif allows coupling of the rate of GTP hydrolysis in Arf1 with membrane curvature induced by the COPI coat. Upon membrane adsorption, the ALPS motif folds into an amphipathic alpha-helix. This helix contrasts from a classical membrane-adsorbing helix in the abundance of S and T residues and the paucity of charged residues in its polar face. We show here that ArfGAP1 contains a second motif with similar physicochemical properties. This motif, ALPS2, also forms an amphipathic alpha-helix at the surface of small vesicles and contributes to the Golgi localization of ArfGAP1 in vivo. Using several quantitative assays, we determined the relative contribution of the two ALPS motifs in the recognition of liposomes of defined curvature and composition. Our results show that ALPS1 is the primary determinant of the interaction of ArfGAP1 with lipid membranes and that ALPS2 reinforces this interaction 40-fold. Furthermore, our results suggest that depending on the engagement of one or two functional ALPS motifs, ArfGAP1 can respond to a wide range of membrane curvature and can adapt to lipid membranes of various acyl chain compositions.     

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.     

Automatic individual recognition of wild Crested Ibis based on hybrid method of self-supervised learning and clustering

Automatic individual recognition of wild Crested Ibis is challenged by two factors: the lack of labeled data and an unpredictable number of individuals. In this paper, we propose a hybrid method of self-supervised learning and clustering to automatically recognize wild Crested Ibis based on vocalizations. To address the first challenge, we enhance the Bootstrap Your Own Latent for Audio (BYOL-A) model by using an improved augmentation module and Spatial Group-wise Enhance (SGE) attention module to create the self-supervised learning model BYOL-AIS. This model aims to extract a more discriminative representation of Crested Ibis vocalizations. To handle the second challenge, we introduce a clustering method that combines Uniform Manifold Approximation and Projection (UMAP) and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to distinguish the representation of Crested Ibis vocalizations. We evaluate our proposed method using vocalizations collected from 10 Crested Ibis individuals and achieve a recognition accuracy of 0.864. This accuracy is comparable to the performance of commonly used supervised methods. Our results suggest that our proposed method is a feasible method for wild bird recognition in the absence of labeled data and has the potential to be an analytical tool for processing huge amounts of monitoring data.     

Portraits and perception: configural information in creating and recognizing face images

Configural information has long been considered important for face recognition. However, traditional portraiture instruction encourages the artist to use a 'generic' configuration for faces rather than attempting to replicate precise feature positions. We examine this intriguing paradox with two tasks designed to test the extent to which configural information is incorporated into face representations. In Experiment 1, we use a simplified face production task to examine how accurately feature configuration can be incorporated in the generated likenesses. In Experiment 2, we ask if the 'portraits' created in Experiment 1 are discriminable from veridical images. The production and recognition results from these experiments show a consistent pattern. Subjects are quite poor at arranging facial features (eyes, nose and mouth) in their correct locations, and at distinguishing erroneous configurations from correct ones. This seeming insensitivity to configural relations is consistent with artists' practice of creating portraits based on a generic geometric template. Interestingly, the frame of reference artists implicitly use for this generic template - the external face contour - emerges as a significant modulator of performance in our experimental results. Production errors are reduced and recognition performance is enhanced in the presence of outer contours. We discuss the implications of these results for face recognition models, as well as some possible perceptual reasons why portraits are so difficult to create.     

Visual exploration and object recognition by lattice deformation

Mechanisms of explicit object recognition are often difficult to investigate and require stimuli with controlled features whose expression can be manipulated in a precise quantitative fashion. Here, we developed a novel method (called "Dots"), for generating visual stimuli, which is based on the progressive deformation of a regular lattice of dots, driven by local contour information from images of objects. By applying progressively larger deformation to the lattice, the latter conveys progressively more information about the target object. Stimuli generated with the presented method enable a precise control of object-related information content while preserving low-level image statistics, globally, and affecting them only little, locally. We show that such stimuli are useful for investigating object recognition under a naturalistic setting--free visual exploration--enabling a clear dissociation between object detection and explicit recognition. Using the introduced stimuli, we show that top-down modulation induced by previous exposure to target objects can greatly influence perceptual decisions, lowering perceptual thresholds not only for object recognition but also for object detection (visual hysteresis). Visual hysteresis is target-specific, its expression and magnitude depending on the identity of individual objects. Relying on the particular features of dot stimuli and on eye-tracking measurements, we further demonstrate that top-down processes guide visual exploration, controlling how visual information is integrated by successive fixations. Prior knowledge about objects can guide saccades/fixations to sample locations that are supposed to be highly informative, even when the actual information is missing from those locations in the stimulus. The duration of individual fixations is modulated by the novelty and difficulty of the stimulus, likely reflecting cognitive demand.     

AAIndexLoc: predicting subcellular localization of proteins based on a new representation of sequences using amino acid indices

Identifying a protein's subcellular localization is an important step to understand its function. However, the involved experimental work is usually laborious, time consuming and costly. Computational prediction hence becomes valuable to reduce the inefficiency. Here we provide a method to predict protein subcellular localization by using amino acid composition and physicochemical properties. The method concatenates the information extracted from a protein's N-terminal, middle and full sequence. Each part is represented by amino acid composition, weighted amino acid composition, five-level grouping composition and five-level dipeptide composition. We divided our dataset into training and testing set. The training set is used to determine the best performing amino acid index by using five-fold cross validation, whereas the testing set acts as the independent dataset to evaluate the performance of our model. With the novel representation method, we achieve an accuracy of approximately 75% on independent dataset. We conclude that this new representation indeed performs well and is able to extract the protein sequence information. We have developed a web server for predicting protein subcellular localization. The web server is available at http://aaindexloc.bii.a-star.edu.sg .     

Quaternion-based discriminant analysis method for color face recognition

Pattern recognition techniques have been used to automatically recognize the objects, personal identities, predict the function of protein, the category of the cancer, identify lesion, perform product inspection, and so on. In this paper we propose a novel quaternion-based discriminant method. This method represents and classifies color images in a simple and mathematically tractable way. The proposed method is suitable for a large variety of real-world applications such as color face recognition and classification of the ground target shown in multispectrum remote images. This method first uses the quaternion number to denote the pixel in the color image and exploits a quaternion vector to represent the color image. This method then uses the linear discriminant analysis algorithm to transform the quaternion vector into a lower-dimensional quaternion vector and classifies it in this space. The experimental results show that the proposed method can obtain a very high accuracy for color face recognition.     

Modeling Inter‐Subject Variability in fMRI Activation Location: A Bayesian Hierarchical Spatial Model

Summary The aim of this article is to develop a spatial model for multi‐subject fMRI data. There has been extensive work on univariate modeling of each voxel for single and multi‐subject data, some work on spatial modeling of single‐subject data, and some recent work on spatial modeling of multi‐subject data. However, there has been no work on spatial models that explicitly account for inter‐subject variability in activation locations. In this article, we use the idea of activation centers and model the inter‐subject variability in activation locations directly. Our model is specified in a Bayesian hierarchical framework which allows us to draw inferences at all levels: the population level, the individual level, and the voxel level. We use Gaussian mixtures for the probability that an individual has a particular activation. This helps answer an important question that is not addressed by any of the previous methods: What proportion of subjects had a significant activity in a given region. Our approach incorporates the unknown number of mixture components into the model as a parameter whose posterior distribution is estimated by reversible jump Markov chain Monte Carlo. We demonstrate our method with a fMRI study of resolving proactive interference and show dramatically better precision of localization with our method relative to the standard mass‐univariate method. Although we are motivated by fMRI data, this model could easily be modified to handle other types of imaging data.     

Relational Memory Is Evident in Eye Movement Behavior despite the Use of Subliminal Testing Methods

While it is generally agreed that perception can occur without awareness, there continues to be debate about the type of representational content that is accessible when awareness is minimized or eliminated. Most investigations that have addressed this issue evaluate access to well-learned representations. Far fewer studies have evaluated whether or not associations encountered just once prior to testing might also be accessed and influence behavior. Here, eye movements were used to examine whether or not memory for studied relationships is evident following the presentation of subliminal cues. Participants assigned to experimental or control groups studied scene-face pairs and test trials evaluated implicit and explicit memory for these pairs. Each test trial began with a subliminal scene cue, followed by three visible studied faces. For experimental group participants, one face was the studied associate of the scene (implicit test); for controls none were a match. Subsequently, the display containing a match was presented to both groups, but now it was preceded by a visible scene cue (explicit test). Eye movements were recorded and recognition memory responses were made. Participants in the experimental group looked disproportionately at matching faces on implicit test trials and participants from both groups looked disproportionately at matching faces on explicit test trials, even when that face had not been successfully identified as the associate. Critically, implicit memory-based viewing effects seemed not to depend on residual awareness of subliminal scene cues, as subjective and objective measures indicated that scenes were successfully masked from view. The reported outcomes indicate that memory for studied relationships can be expressed in eye movement behavior without awareness.     

A Fast and Accurate Method for Glaucoma Screening from Smartphone-Captured Fundus Images

The glaucoma is an eye disease that causes blindness when it progresses in an advanced stage. Early glaucoma diagnosis is essential to prevent the vision loss. However, early detection is not covered due to the lack of ophthalmologists and the limited accessibility to retinal image capture devices.In this paper, we present an automated method for glaucoma screening dedicated for Smartphone Captured Fundus Images (SCFIs). The implementation of the method into a smartphone associated to an optical lens for retina capturing leads to a mobile aided screening system for glaucoma. The challenge consists in insuring higher performance detection despite the moderate quality of SCFIs, with a reduced execution time to be adequate for the clinical use. The main idea consists in deducing glaucoma based on the vessel displacement inside the Optic Disk (OD), where the vessel tree remains sufficiently modeled on SCFIs. Within this objective, our major contribution consists in proposing: (1) a robust processing for locating vessel centroids in order to adequately model the vessel distribution, and (2) a feature vector that relevantly reflect two main glaucoma biomarkers in terms of vessel displacement. Furthermore, all processing steps are carefully chosen based on lower complexity, to be suitable for fast clinical screening.A first evaluation of our method is performed using the two public DRISHTI-DB and DRIONS-DB databases, where 99% and 95% accuracy, 96.77% and 97,5% specificity and 100% and 95% sensitivity are respectively achieved. Thereafter, the method is evaluated using two fundus image databases respectively captured through a smartphone and retinograph for the same persons. We achieve 100% accuracy using both databases which assesses the robustness of our method. In addition, the detection is performed on 0.027 and 0.029 second when executed respectively on the Samsung-M51 on the Samsung-A70 smartphone devices. Our proposed smartphone app provides a cost-effective and widely accessible mobile platform for early screening of glaucoma in remote clinics or areas with limited access to fundus cameras and ophthalmologists.     

Recognizing Age-Separated Face Images: Humans and Machines

Humans utilize facial appearance, gender, expression, aging pattern, and other ancillary information to recognize individuals. It is interesting to observe how humans perceive facial age. Analyzing these properties can help in understanding the phenomenon of facial aging and incorporating the findings can help in designing effective algorithms. Such a study has two components - facial age estimation and age-separated face recognition. Age estimation involves predicting the age of an individual given his/her facial image. On the other hand, age-separated face recognition consists of recognizing an individual given his/her age-separated images. In this research, we investigate which facial cues are utilized by humans for estimating the age of people belonging to various age groups along with analyzing the effect of one''s gender, age, and ethnicity on age estimation skills. We also analyze how various facial regions such as binocular and mouth regions influence age estimation and recognition capabilities. Finally, we propose an age-invariant face recognition algorithm that incorporates the knowledge learned from these observations. Key observations of our research are: (1) the age group of newborns and toddlers is easiest to estimate, (2) gender and ethnicity do not affect the judgment of age group estimation, (3) face as a global feature, is essential to achieve good performance in age-separated face recognition, and (4) the proposed algorithm yields improved recognition performance compared to existing algorithms and also outperforms a commercial system in the young image as probe scenario.     

Biologically Inspired Scene Context for Object Detection Using a Single Instance

This paper presents a novel object detection method using a single instance from the object category. Our method uses biologically inspired global scene context criteria to check whether every individual location of the image can be naturally replaced by the query instance, which indicates whether there is a similar object at this location. Different from the traditional detection methods that only look at individual locations for the desired objects, our method evaluates the consistency of the entire scene. It is therefore robust to large intra-class variations, occlusions, a minor variety of poses, low-revolution conditions, background clutter etc., and there is no off-line training. The experimental results on four datasets and two video sequences clearly show the superior robustness of the proposed method, suggesting that global scene context is important for visual detection/localization.     

New robust face recognition methods based on linear regression

Nearest subspace (NS) classification based on linear regression technique is a very straightforward and efficient method for face recognition. A recently developed NS method, namely the linear regression-based classification (LRC), uses downsampled face images as features to perform face recognition. The basic assumption behind this kind method is that samples from a certain class lie on their own class-specific subspace. Since there are only few training samples for each individual class, which will cause the small sample size (SSS) problem, this problem gives rise to misclassification of previous NS methods. In this paper, we propose two novel LRC methods using the idea that every class-specific subspace has its unique basis vectors. Thus, we consider that each class-specific subspace is spanned by two kinds of basis vectors which are the common basis vectors shared by many classes and the class-specific basis vectors owned by one class only. Based on this concept, two classification methods, namely robust LRC 1 and 2 (RLRC 1 and 2), are given to achieve more robust face recognition. Unlike some previous methods which need to extract class-specific basis vectors, the proposed methods are developed merely based on the existence of the class-specific basis vectors but without actually calculating them. Experiments on three well known face databases demonstrate very good performance of the new methods compared with other state-of-the-art methods.     

Dorsal premotor neurons encode the relative position of the hand, eye, and goal during reach planning

When reaching to grasp an object, we often move our arm and orient our gaze together. How are these movements coordinated? To investigate this question, we studied neuronal activity in the dorsal premotor area (PMd) and the medial intraparietal area (area MIP) of two monkeys while systematically varying the starting position of the hand and eye during reaching. PMd neurons encoded the relative position of the target, hand, and eye. MIP neurons encoded target location with respect to the eye only. These results indicate that whereas MIP encodes target locations in an eye-centered reference frame, PMd uses a relative position code that specifies the differences in locations between all three variables. Such a relative position code may play an important role in coordinating hand and eye movements by computing their relative position.     

Site localization of membrane-bound proteins on whole cell level using atomic force microscopy

This study presents molecular recognition method, which is based on specific force measurements between modified AFM (atomic force microscopy) tip and mammalian cell. The presented method allows recognition of specific cell surface proteins and receptor sites by nanometer accuracy level. Here we demonstrate specific recognition of membrane-bound Osteopontin (OPN) sites on preosteogenic cell membrane. By merging specific force detection map of the proteins and topography image of the cell, we create a new image (recognition image), which demonstrates the exact locations of the proteins relative to the cell membrane. The recognition results indicate the strong affinity between the modified tip and the target molecules, therefore, it enables the use of an AFM as a remarkable nanoscale tracking tool on the whole cell level.     

Probing the role of interfacial waters in protein–DNA recognition using a hybrid implicit/explicit solvation model

When proteins bind to their DNA target sites, ordered water molecules are often present at the protein–DNA interface bridging protein and DNA through hydrogen bonds. What is the role of these ordered interfacial waters? Are they important determinants of the specificity of DNA sequence recognition, or do they act in binding in a primarily nonspecific manner, by improving packing of the interface, shielding unfavorable electrostatic interactions, and solvating unsatisfied polar groups that are inaccessible to bulk solvent? When modeling details of structure and binding preferences, can fully implicit solvent models be fruitfully applied to protein–DNA interfaces, or must the individualistic properties of these interfacial waters be accounted for? To address these questions, we have developed a hybrid implicit/explicit solvation model that specifically accounts for the locations and orientations of small numbers of DNA‐bound water molecules, while treating the majority of the solvent implicitly. Comparing the performance of this model with that of its fully implicit counterpart, we find that explicit treatment of interfacial waters results in a modest but significant improvement in protein side‐chain placement and DNA sequence recovery. Base‐by‐base comparison of the performance of the two models highlights DNA sequence positions whose recognition may be dependent on interfacial water. Our study offers large‐scale statistical evidence for the role of ordered water for protein–DNA recognition, together with detailed examination of several well‐characterized systems. In addition, our approach provides a template for modeling explicit water molecules at interfaces that should be extensible to other systems. Proteins 2013; 81:1318–1329. © 2013 Wiley Periodicals, Inc.     

Application of 3-Dimensional Printing Technology to Construct an Eye Model for Fundus Viewing Study

Objective

To construct a life-sized eye model using the three-dimensional (3D) printing technology for fundus viewing study of the viewing system.

Methods

We devised our schematic model eye based on Navarro''s eye and redesigned some parameters because of the change of the corneal material and the implantation of intraocular lenses (IOLs). Optical performance of our schematic model eye was compared with Navarro''s schematic eye and other two reported physical model eyes using the ZEMAX optical design software. With computer aided design (CAD) software, we designed the 3D digital model of the main structure of the physical model eye, which was used for three-dimensional (3D) printing. Together with the main printed structure, polymethyl methacrylate(PMMA) aspherical cornea, variable iris, and IOLs were assembled to a physical eye model. Angle scale bars were glued from posterior to periphery of the retina. Then we fabricated other three physical models with different states of ammetropia. Optical parameters of these physical eye models were measured to verify the 3D printing accuracy.

Results

In on-axis calculations, our schematic model eye possessed similar size of spot diagram compared with Navarro''s and Bakaraju''s model eye, much smaller than Arianpour''s model eye. Moreover, the spherical aberration of our schematic eye was much less than other three model eyes. While in off- axis simulation, it possessed a bit higher coma and similar astigmatism, field curvature and distortion. The MTF curves showed that all the model eyes diminished in resolution with increasing field of view, and the diminished tendency of resolution of our physical eye model was similar to the Navarro''s eye. The measured parameters of our eye models with different status of ametropia were in line with the theoretical value.

Conclusions

The schematic eye model we designed can well simulate the optical performance of the human eye, and the fabricated physical one can be used as a tool in fundus range viewing research.