Human age classification using facial skin aging features and artificial neural network

In this paper a novel method based on facial skin aging features and Artificial Neural Network (ANN) is proposed to classify the human face images into four age groups. The facial skin aging features are extracted by using Local Gabor Binary Pattern Histogram (LGBPH) and wrinkle analysis. The ANN classifier is designed by using two layer feedforward backpropagation neural networks. The proposed age classification framework is trained and tested with face images from PAL face database and shown considerable improvement in the age classification accuracy up to 94.17% and 93.75% for male and female respectively.     

Novel object detection and recognition system based on points of interest selection and SVM classification

Due to the progression in computer vision technology, object recognition systems have gained considerable research interest. Though there are numerous object recognition systems in the literature, there is always a constant demand for better object recognition systems. Taking this as a challenge, this work proposes a novel object recognition system based on points of interest and feature extraction. Initially, the points of interest of the image are selected by means of Derivative Kadir-Brady (DKB) detector and the neighbourhood pixels of a particular window size are selected for further processing. The gabor and curvelet features are extracted from the area of interest, followed by the Support Vector Machine (SVM) classification. The performance of the proposed object recognition system is evaluated against three analogous techniques in terms of accuracy, precision, recall and F-measure. On experimental analysis, it is proven that the proposed approach outperforms the existing approaches and the performance of the proposed work is satisfactory.     

Hierarchies of Self-Organizing Maps for action recognition

We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction and clustering of the feature space. It represents the dynamics of the stream of posture frames in action sequences as activity trajectories over time. The second layer in the hierarchy consists of another SOM which clusters the activity trajectories of the first-layer SOM and learns to represent action prototypes. The third- and last-layer of the hierarchy consists of a neural network that learns to label action prototypes of the second-layer SOM and is independent – to certain extent – of the camera’s angle and relative distance to the actor. The experiments were carried out with encouraging results with action movies taken from the INRIA 4D repository. In terms of representational accuracy, measured as the recognition rate over the training set, the architecture exhibits 100% accuracy indicating that actions with overlapping patterns of activity can be correctly discriminated. On the other hand, the architecture exhibits 53% recognition rate when presented with the same actions interpreted and performed by a different actor. Experiments on actions captured from different view points revealed a robustness of our system to camera rotation. Indeed, recognition accuracy was comparable to the single viewpoint case. To further assess the performance of the system we have also devised a behavioural experiments in which humans were asked to recognise the same set of actions, captured from different points of view. Results form such a behavioural study let us argue that our architecture is a good candidate as cognitive model of human action recognition, as architectural results are comparable to those observed in humans.     

Wild facial expression recognition based on incremental active learning

Facial expression recognition in a wild situation is a challenging problem in computer vision research due to different circumstances, such as pose dissimilarity, age, lighting conditions, occlusions, etc. Numerous methods, such as point tracking, piecewise affine transformation, compact Euclidean space, modified local directional pattern, and dictionary-based component separation have been applied to solve this problem. In this paper, we have proposed a deep learning–based automatic wild facial expression recognition system where we have implemented an incremental active learning framework using the VGG16 model developed by the Visual Geometry Group. We have gathered a large amount of unlabeled facial expression data from Intelligent Technology Lab (ITLab) members at Inha University, Republic of Korea, to train our incremental active learning framework. We have collected these data under five different lighting conditions: good lighting, average lighting, close to the camera, far from the camera, and natural lighting and with seven facial expressions: happy, disgusted, sad, angry, surprised, fear, and neutral. Our facial recognition framework has been adapted from a multi-task cascaded convolutional network detector. Repeating the entire process helps obtain better performance. Our experimental results have demonstrated that incremental active learning improves the starting baseline accuracy from 63% to average 88% on ITLab dataset on wild environment. We also present extensive results on face expression benchmark such as Extended Cohn-Kanade Dataset, as well as ITLab face dataset captured in wild environment and obtained better performance than state-of-the-art approaches.     

From Fragments to Geometric Shape: Changes in Visual Object Recognition Between 18 and 24 Months

ABSTRACT— Visual object recognition is foundational to processes of categorization, tool use, and real-world problem solving. Despite considerable effort across many disciplines and many specific advances, there is no comprehensive or well-accepted account of this ability. Moreover, none of the extant approaches consider how human object recognition develops. New evidence indicates a period of rapid change in toddlers' visual object recognition between 18 and 24 months that is related to the learning of object names and to goal-directed action. Children appear to shift from recognition based on piecemeal fragments to recognition based on geometric representations of three-dimensional shape. These findings may lead to a more unified understanding of the processes that make human object recognition as impressive as it is.     

Hybrid logic with the difference modality for generalisations of graphs

We discuss recent work generalising the basic hybrid logic with the difference modality to any reasonable notion of transition. This applies equally to both subrelational transitions such as monotone neighbourhood frames or selection function models as well as those with more structure such as Markov chains and alternating temporal frames. We provide a generic canonical cut-free sequent system and a terminating proof-search strategy for the fragment without the difference modality but including the global modality.     

Determining the Dimensionality of Multidimensional Scaling Representations for Cognitive Modeling

Multidimensional scaling models of stimulus domains are widely used as a representational basis for cognitive modeling. These representations associate stimuli with points in a coordinate space that has some predetermined number of dimensions. Although the choice of dimensionality can significantly influence cognitive modeling, it is often made on the basis of unsatisfactory heuristics. To address this problem, a Bayesian approach to dimensionality determination, based on the Bayesian Information Criterion (BIC), is developed using a probabilistic formulation of multidimensional scaling. The BIC approach formalizes the trade-off between data-fit and model complexity implicit in the problem of dimensionality determination and allows for the explicit introduction of information regarding data precision. Monte Carlo simulations are presented that indicate, by using this approach, the determined dimensionality is likely to be accurate if either a significant number of stimuli are considered or a reasonable estimate of precision is available. The approach is demonstrated using an established data set involving the judged pairwise similarities between a set of geometric stimuli. Copyright 2001 Academic Press.     

Hierarchical growing grid networks for skeleton based action recognition

In this paper, a novel cognitive architecture for action recognition is developed by applying layers of growing grid neural networks. Using these layers makes the system capable of automatically arranging its representational structure. In addition to the expansion of the neural map during the growth phase, the system is provided with a prior knowledge of the input space, which increases the processing speed of the learning phase. Apart from two layers of growing grid networks the architecture is composed of a preprocessing layer, an ordered vector representation layer and a one-layer supervised neural network. These layers are designed to solve the action recognition problem. The first-layer growing grid receives the input data of human actions and the neural map generates an action pattern vector representing each action sequence by connecting the elicited activation of the trained map. The pattern vectors are then sent to the ordered vector representation layer to build the time-invariant input vectors of key activations for the second-layer growing grid. The second-layer growing grid categorizes the input vectors to the corresponding action clusters/sub-clusters and finally the one-layer supervised neural network labels the shaped clusters with action labels. Three experiments using different datasets of actions show that the system is capable of learning to categorize the actions quickly and efficiently. The performance of the growing grid architecture is compared with the results from a system based on Self-Organizing Maps, showing that the growing grid architecture performs significantly superior on the action recognition tasks.     

Role of the secondary visual cortex in HMAX model for object recognition

The models inspired by visual systems of life creatures (e.g., human, mammals, etc.) have been very successful in addressing object recognition tasks. For example, Hierarchical Model And X (HMAX) effectively recognizes different objects by modeling the V1, V4, and IT regions of the human visual system. Although HMAX is one of the superior models in the field of object recognition, its implementation has been limited due to some disadvantages such as the unrepeatability of the process under constant conditions, extreme redundancy, high computational load, and time-consuming. In this paper, we aim at revising the HMAX approach by adding the model of the secondary region (V2) in the human visual system which leads to removing the mentioned drawbacks of standard HMAX. The added layer selects repeatable and more informative features that increase the accuracy of the proposed method by avoiding the redundancy existing in the conventional approaches. Furthermore, this feature selection strategy considerably reduces the huge computational load. Another contribution of our model is highlighted when a small number of training images is available where our model can efficiently cope with this issue. We evaluate our proposed approach using Caltech5 and GRAZ-02 database as two famous benchmarks for object recognition tasks. Additionally, the results are compared with standard HMAX that validate and highlight the efficiency of the proposed method.     

Bayesian Model Averaging for Propensity Score Analysis

This article considers Bayesian model averaging as a means of addressing uncertainty in the selection of variables in the propensity score equation. We investigate an approximate Bayesian model averaging approach based on the model-averaged propensity score estimates produced by the R package BMA but that ignores uncertainty in the propensity score. We also provide a fully Bayesian model averaging approach via Markov chain Monte Carlo sampling (MCMC) to account for uncertainty in both parameters and models. A detailed study of our approach examines the differences in the causal estimate when incorporating noninformative versus informative priors in the model averaging stage. We examine these approaches under common methods of propensity score implementation. In addition, we evaluate the impact of changing the size of Occam’s window used to narrow down the range of possible models. We also assess the predictive performance of both Bayesian model averaging propensity score approaches and compare it with the case without Bayesian model averaging. Overall, results show that both Bayesian model averaging propensity score approaches recover the treatment effect estimates well and generally provide larger uncertainty estimates, as expected. Both Bayesian model averaging approaches offer slightly better prediction of the propensity score compared with the Bayesian approach with a single propensity score equation. Covariate balance checks for the case study show that both Bayesian model averaging approaches offer good balance. The fully Bayesian model averaging approach also provides posterior probability intervals of the balance indices.     

Geometric cues,reference frames,and the equivalence of experienced-aligned and novel-aligned views in human spatial memory

Spatial memories are often organized around reference frames, and environmental shape provides a salient cue to reference frame selection. To date, however, the environmental cues responsible for influencing reference frame selection remain relatively unknown. To connect research on reference frame selection with that on orientation via environmental shape, we explored the extent to which geometric cues were incidentally encoded and represented in memory by evaluating their influence on reference frame selection. Using a virtual environment equipped with a head-mounted-display, we presented participants with to-be-remembered object arrays. We manipulated whether the experienced viewpoint was aligned or misaligned with global (i.e., the principal axis of space) or local (i.e., wall orientations) geometric cues. During subsequent judgments of relative direction (i.e., participants imagined standing at one object, facing a second object, and pointed toward a third object), we show that performance was best when imagining perspectives aligned with these geometric cues; moreover, global geometric cues were sufficient for reference frame selection, global and local geometric cues were capable of exerting differential influence on reference frame selection, and performance from experienced-imagined perspectives was equivalent to novel-imagined perspectives aligned with geometric cues. These results explicitly connect theory regarding spatial reference frame selection and spatial orientation via environmental shape and indicate that spatial memories are organized around fundamental geometric properties of space.     

Intrinsic frames of reference in haptic spatial learning

It has been proposed that spatial reference frames with which object locations are specified in memory are intrinsic to a to-be-remembered spatial layout (intrinsic reference theory). Although this theory has been supported by accumulating evidence, it has only been collected from paradigms in which the entire spatial layout was simultaneously visible to observers. The present study was designed to examine the generality of the theory by investigating whether the geometric structure of a spatial layout (bilateral symmetry) influences selection of spatial reference frames when object locations are sequentially learned through haptic exploration. In two experiments, participants learned the spatial layout solely by touch and performed judgments of relative direction among objects using their spatial memories. Results indicated that the geometric structure can provide a spatial cue for establishing reference frames as long as it is accentuated by explicit instructions (Experiment 1) or alignment with an egocentric orientation (Experiment 2). These results are entirely consistent with those from previous studies in which spatial information was encoded through simultaneous viewing of all object locations, suggesting that the intrinsic reference theory is not specific to a type of spatial memory acquired by the particular learning method but instead generalizes to spatial memories learned through a variety of encoding conditions. In particular, the present findings suggest that spatial memories that follow the intrinsic reference theory function equivalently regardless of the modality in which spatial information is encoded.     

Optimal selection of E‐learning websites using multiattribute decision‐making approaches

A computational quantitative model based on weighted Euclidean distance‐based approximation and complex proportional assessment has been developed for the evaluation, selection, and ranking of various E‐learning websites in ascending or descending order based on their Euclidean distance value from the optimal website. The E‐learning website with rank 1 is considered the optimal selection on the particular dataset under consideration. The problem of the E‐learning website Selection, Evaluation and Ranking is modeled as a multiattribute decision‐making problem in which various interrelated attributes collectively termed as ranking criteria are identified to make the evaluation of available alternatives. In this research, 5 most popular E‐learning websites related to the C programming language for the software development have been considered to show the utility of developed model. Further, the concept of methodology validation strengthens this research by comparing the obtained results with the existing multiattribute decision‐making approach as analytical hierarchy process method.     

How birds identify species information in song: A pattern recognition approach

Pattern recognition theory (PRT) is a diverse array of models concerned with the recognition of spatial and temporal patterns by humans and machines. We have sought to use the theory to help us understand how passerines identify species information in conspecific song. In this paper, application of PRT provided (a) a tentative model for song recognition, (b) an improved methodology for song playback experiments, and (c) a theoretical analysis of the representation of the temporal structure of song. In each instance, PRT suggested better experiments and more detailed analyses than had been available previously.     

Reverse production effect: children recognize novel words better when they are heard rather than produced

This research investigates the effect of production on 4.5‐ to 6‐year‐old children's recognition of newly learned words. In Experiment 1, children were taught four novel words in a produced or heard training condition during a brief training phase. In Experiment 2, children were taught eight novel words, and this time training condition was in a blocked design. Immediately after training, children were tested on their recognition of the trained novel words using a preferential looking paradigm. In both experiments, children recognized novel words that were produced and heard during training, but demonstrated better recognition for items that were heard. These findings are opposite to previous results reported in the literature with adults and children. Our results show that benefits of speech production for word learning are dependent on factors such as task complexity and the developmental stage of the learner.     

Pedestrian detection using a moving camera: A novel framework for foreground detection

While background subtraction techniques have been widely applied to detect moving objects in a video stream captured by a static camera, detecting moving objects using a moving camera still represents a challenging task. In this context, pedestrian detection using a camera placed on the top of a vehicle’s windshield has been rarely investigated. This is mainly due to the background ego-motion. Since the scene captured by the camera seems in motion, it is very difficult to distinguish the moving pedestrians from the others that belong to the static part of the scene. For this reason, a compensation step is needed to suppress the ego-motion. This paper presents a study on the main challenges facing pedestrian detection systems as well as methods proposed to handle these challenges. A novel trajectory classification framework for detecting pedestrians even in challenging real-world environments is proposed. The proposed method models the background motion between two consecutive frames in order to compensate the camera motion. Then, it defines a classification process that differentiates between the background and the foreground in the frame. Using the defined foreground, we consequently identify the presence of pedestrians in the scene. The proposed method was validated on a public benchmark dataset: CVC-14 containing both visible and far infrared video sequences in day and night times. Experimental results confirm the effectiveness of the proposed approach in capturing the dynamic aspect between frames and therefore detecting the presence of pedestrians in the scene.