Age Estimation Using Bayesian Process

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 Subspace) 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.

Evaluation, Description and Invention: Paradigms for Human-Computer Interaction

Two-stages based facial demographic attributes combination for age estimation

The human face has biometric properties that are important for providing age information because of the aging process of the face. Automatic Age estimation is a difficult problem because the relationship between facial images and age is not very linear. Deep residual network (Resnet) is a neural network convolution architecture that was easier to optimize and can gain accuracy results from a considerably increasing depth. In this paper, we propose a new approach age estimation on convolution neural network (CNN) using the deep residual network (Resnet) model. Through the literature, Resnet achieves superior results when compared with other state-of-the-art image classifications. We compare a new generation of deep residual network called ResNeXt with Resnet and a basic linier regression model architecture.We user UTKFace dataset to evaluate the performance of residual network for age estimation of the range 1-100 years old. The result shows that the ResNeXt-50 (32×4d) architecture achieves a better age estimation results than Resnet-50 and linier regression.

In this paper, we investigate and exploit the influence of facial expressions on automatic age estimation. Different from existing approaches, our method jointly learns the age and expression by introducing a new graphical model with a latent layer between the age/expression labels and the features. This layer aims to learn the relationship between the age and expression and captures the face changes which induce the aging and expression appearance, and thus obtaining expression-invariant age estimation. Conducted on three age-expression datasets (FACES , Lifespan and NEMO ), our experiments illustrate the improvement in performance when the age is jointly learnt with expression in comparison to expression-independent age estimation. The age estimation error is reduced by 14.43, 37.75 and 9.30 percent for the FACES, Lifespan and NEMO datasets respectively. The results obtained by our graphical model, without prior-knowledge of the expressions of the tested faces, are better than the best reported ones for all datasets. The flexibility of the proposed model to include more cues is explored by incorporating gender together with age and expression. The results show performance improvements for all cues.

In this paper, we propose a novel method for facial expression recognition. The facial expression is extracted from human faces by an expression classifier that is learned from boosting Haar feature based look-up-table type weak classifiers. The expression recognition system consists of three modules, face detection, facial feature landmark extraction and facial expression recognition. The implemented system can automatically recognize seven expressions in real time that include anger, disgust, fear, happiness, neutral, sadness and surprise. Experimental results are reported to show its potential applications in human computer interaction.

Age progression is generally indicated by skin texture. The skin texture changes with age progression of a person. This paper provides a technique to estimate the age of a person by analysis of wrinkle on face images. Wrinkle areas are detected and features are extracted from face image. Based on feature values of each face image is clustered using fuzzy c-means. Each face image is assigned to a cluster based on its maximum membership value. Age estimation is done using their membership values and average ages of each cluster. Total 20 face images are taken for training the system and 120 face images are tested. The obtained results are significant and accuracy up to 87.5%

Automatic age estimation relying on human facial images is a key technology of many real-world applications, which is still a challenging task in the computer vision field. There are three cascade modules for facial age estimation: facial aging feature extraction, dimension reduction (or feature selection) and estimation method. Many existing literatures focus on the first or last module while for an age estimation system, it's also important to construct a reasonable framework. Our work focuses on creating an effective framework by selecting methods for these modules reasonably. Firstly, a BIM (bio-inspired model) is employed to extract facial aging features because it can not only capture discriminative local and global features, but also overcome interferences of some 2D deformations to some extent. Then, LDA (linear discriminant analysis) is used for reducing the BIF (bio-inspired features) to lower dimensions and extracting more discriminative information at the same time. Finally, CS-OHRank (cost-sensitive ordinal hyperplane rank), which tackles with sparse data well and reflects the cumulative attributes of aging, is applied as the estimation method. Experimental results on benchmark dataset FG-NET show that our framework combining BIF, LDA and CS-OHRank is competitive among the state of the art, with MAE (mean absolute error) = 4.72 years..

A remarkable process has been made in hand gesture recognition based on radar sensors, which has potential application in human-computer interaction. However, existing research is mostly conducted for only one hand gesture in the sensor's field of view, leading to limitations in some practical scenarios when multiple gestures exist simultaneously. In this paper, we propose a method to estimate the number of multiple gestures precisely in multi-person scenarios firstly, then separates the mixed blind source signals to acquire each motion signal. Finally, we extract multidimensional features for each separated gesture. Extensive experiments are carried out based on commer-cial frequency modulated continuous wave (FMCW) single-input multi-output (SIMO) millimeter-wave radar systems to verify the effectiveness of this approach.

We introduce a novel procedure for obtaining cross-validated predictive estimates for Bayesian hierarchical regression models (BHRMs). BHRMs are popular for modeling complex dependence structures (e.g., Gaussian processes and Gaussian Markov random fields) but can be computationally expensive to run. Cross-validation (CV) is, therefore, not a common practice to evaluate the predictive performance of BHRMs. Our method circumvents the need to rerun computationally costly estimation methods for each cross-validation fold and makes CV more feasible for large BHRMs. We shift the CV problem from probability-based sampling to a familiar and straightforward optimization problem by conditioning on the variance-covariance parameters. Our approximation applies to leave-one-out CV and leave-one-cluster-out CV, the latter of which is more appropriate for models with complex dependencies. In many cases, this produces estimates equivalent to full CV. We provide theoretical results, demonstrate the efficacy of our method on publicly available data and in simulations, and compare the model performance with several competing methods for CV approximation. Code and other supplementary materials available online.

Human age estimation framework using different facial parts

In recent years, flexible sensors based on laser-induced graphene (LIG) have played an important role in areas such as smart healthcare, smart skin, and wearable devices. This paper presents the fabrication of flexible sensors based on LIG technology and their applications in human-computer interaction (HCI) systems. Firstly, LIG with a sheet resistance as low as 4.5 Ω per square was generated through direct laser interaction with commercial polyimide (PI) film. The flexible sensors were then fabricated through a one-step method using the as-prepared LIG. The applications of the flexible sensors were demonstrated by an HCI system, which was fabricated through the integration of the flexible sensors and a flexible glove. The as-prepared HCI system could detect the bending motions of different fingers and translate them into the movements of the mouse on the computer screen. At the end of the paper, a demonstration of the HCI system is presented in which words were typed on a computer screen through the bending motion of the fingers. The newly designed LIG-based flexible HCI system can be used by persons with limited mobility to control a virtual keyboard or mouse pointer, thus enhancing their accessibility and independence in the digital realm.

Smart cameras are becoming more popular in human computer interaction (HCI). One of HCI research areas, multimodal user interface (MMUI) allows user to interact with a computer by using his or her natural communication modalities, such as speech, pen, touch, gestures, eye gaze, and facial expression. This paper presents the hardware and software co-design and implementation of KLT (Kanade Lucas Tomasi) tracking algorithm in a FPGA-based smart camera prototype for recognize simple hand gestures consisting of a CMOS image sensor capture unit and FPGA main video processor. This tracking system uses face and hand detections as a tool to detect and track gesture (face and hand motion). This gesture tracking system that are based on Harris Keypoint Detection algorithm and KLT tracking algorithm has been successfully implemented in FPGA and shows promising result in real time performance.

In recent years, activity recognition in smart homes is an active research area. It is an important problem of Human Computer Interaction (HCI), and has many applications in HCI, such as assistive living and healthcare. Recognition of users’ common behaviors allows an environment to provide personalized service. Unlike activity recognition in computer vision which uses cameras, it studies activities by embedded sensors in smart homes. In this paper, we propose a method to extract latent features from sensor data by Beta Process Hidden Markov Model (BP-HMM). The contributions of our method are twofold: 1, we extend BP-HMM by dependent Beta process, and integrate state constraints of sensors into the sampling process of BP-HMM. 2, we extract latent features automatically by our dependent BP-HMM, and train a structural support vector machine (SVM) by these features in a supervised way for activity recognition. To evaluate the proposed method, we performed experiments on the real-world smart home datasets. Our results suggest that extracting latent features from sensor data leads to good performance for activity recognition.

Hand posture recognition has been a wide region of applications in Human Computer Interaction and Computer Vision for many years. The problem arises mainly due to the high dexterity of hand and self-occlusions created in the limited view of the camera or illumination variations. To remedy these problems, a hand posture recognition method using 3-D point cloud is proposed to explicitly utilize 3-D information from depth maps in this paper. Firstly, hand region is segmented by a set of depth threshold. Next, hand image normalization will be performed to ensure that the extracted feature descriptors are scale and rotation invariant. By robustly coding and pooling 3-D facets, the proposed descriptor can effectively represent the various hand postures. After that, SVM with Gaussian kernel function is used to address the issue of posture recognition. Experimental results based on posture dataset captured by Kinect sensor (from 1 to 10) demonstrate the effectiveness of the proposed approach and the average recognition rate of our method is over 96%.