Hasimah Ali

Facial emotion recognition using empirical mode decomposition

A new approach of using EMD and KLFDA for facial emotion recognition is presented.Dimension reduction by PCA+LDA, LFDA and KLFDA can improve the performance.Recognition rate of 99.75% was achieved by IMF1+KLFDA using ELM classifier. This paper proposes a new method of using empirical mode decomposition (EMD) technique for facial emotion recognition. The EMD algorithm can decompose any nonlinear and non-stationary signal into a number of intrinsic mode functions (IMFs). In this method, the facial signal obtained from successive projection of Radon transform of 2-D image is decomposed using EMD into oscillating components called IMFs. The first IMF (IMF1) was extracted and considered as features to recognize the facial emotions. Three dimensionality reduction algorithms: Principal Component Analysis (PCA)+Linear Discriminant Analysis (LDA), PCA+Local Fisher Discriminant Analysis (LFDA), and Kernel LFDA (KLFDA) were independently applied on EMD-based features for dimensionality reduction. These dimensionality reduced features were fed to the k-Nearest Neighbor (k-NN), Support Vector machine (SVM) and Extreme Learning Machines with Radial Basis Function (ELM-RBF) classifiers for classification of seven universal facial expressions. The proposed method was evaluated using two benchmark databases JAFFE and CK. The experimental results on both facial expression databases demonstrate the effectiveness of the proposed algorithm.

Iris recognition system by using support vector machines

In recent years, with the increasing demands of security in our networked society, biometric systems for user verification are becoming more popular. Iris recognition system is a new technology for user verification. In this paper, the CASIA iris database is used for individual userpsilas verification by using support vector machines (SVMs) which based on the analysis of iris code as feature extraction is discussed. This feature is then used to recognize authentic users and to reject impostors. Support Vector Machines (SVMs) technique was used for the classification process. The proposed method is evaluated based upon False Rejection Rate (FRR) and False Acceptance Rate (FAR) and the experimental result show that this technique produces good performance.

Keystroke pressure based typing biometrics authentication system by combining ANN and ANFIS-based classifiers

Security of an information system depends to a large extent on its ability to authenticate legitimate users as well as to withstand attacks of various kinds. Confidence in its ability to provide adequate authentication is, however, waning. This is largely due to the wrongful use of passwords by many users. In this paper, the design and development of keystroke pressure-based typing biometrics for individual users verification which based on the analysis of habitual typing of individuals is discussed. The paper examines the use of maximum pressure exerted on the keyboard and time latency between keystrokes as features to create typing patterns for individual users. Combining both an Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are adopted as classifiers to verify the authorized and unauthorized users based on extracted features of typing biometric. The effectiveness of the proposed system is evaluated based upon False Reject Rate (FRR) and False Accept Rate (FAR). A series of experiment shows that the proposed system that used combined classifiers produces promising result for both FAR and FRR.

Iris Recognition System Using Support Vector Machines

In recent years, with the increasing demands of security in our networked society, biometric systems for user verification are becoming more popular. Iris recognition system is a new technology for user verification. In this paper, the CASIA iris database is used for individual user’s verification by using support vector machines (SVMs) which based on the analysis of iris code as feature extraction is discussed. This feature is then used to recognize authentic users and to reject impostors. Support Vector Machines (SVMs) technique was used for the classification process. The proposed method is evaluated based upon False Rejection Rate (FRR) and False Acceptance Rate (FAR) and the experimental result show that this technique produces good performance.

Development of vision-based sensor of smart gripper for industrial applications

In recent years, robotic gripper is widely used for different tasks in various fields. Grippers operate with industrial robots for handling and manipulation of objects. Grippers also operate with hard automation for assembling; micro assembling, machining and packaging. This paper aims to develop vision-based sensor of smart gripper which integrates together with its robotic arm for industrial applications. This system incorporates a camera by means vision sensor to automatically detect and recognize the object that having different weight and shapes and send the information to the robot for next task. Gripper with two fingers has been proposed. This finger is designed to move in translational mode where one finger moves and the other is fixed. This smart gripper adopts force sensor that mounted into the finger tip in order to control the force applied when working with wide range of objects that having different weight without crushed or damaged it. Four servo motors are used to drive the four degree of freedom (D. O. F) of a robotic arm. Basic Stamp 2 microcontroller (BS2) is used as a controller unit to control the position and the movement of the smart gripper. A series of experiment shows that the proposed system is able to detect and recognize the object and then send the information/command directly to the robot to execute grasping and lifting phase of the object to the desired location that has been assigned.

Hybrid feature extraction for facial emotion recognition

In recent advances of technology, the application of facial emotion recognition for human-computer interaction (HCI) is becoming an emerging trend. This HCI depends to a large extent on its ability to recognise the facial expression and ability to withstand various kinds of noise. However, confidence in its ability in providing adequate recognition remains challenging due to subtlety, complexity, and variability of facial expression. Therefore, this paper proposes hybrid feature extraction using 2D discrete wavelet transform (DWT), principal component analysis (PCA), and linear discriminant analysis (LDA) for seven (angry, disgust, fear, happy, neutral, sad, and surprise) different facial emotion recognition from static images. The reduced features are tested using k-nearest-neighbour classifier to recognise the facial emotion. The proposed method is evaluated based on two different databases, namely Japanese female facial expression and Cohn-Kanade database. The proposed method gives promising recognition rates of 100% for JAFFE and 97.52% for Cohn-Kanade. The effect of different wavelet families on the classification performance is also investigated.

Facial Expression Recognition in the Presence of Partially Occluded Images Using Higher Order Spectra

Facial expression recognition (FER) still be ongoing research and considered as a challenging task largely because of uncontrolled environmental conditions, for example, the presence of partially occluded images (masks or sunglasses) on the human face. To address the issue, this paper proposed a new approach of using higher order spectra (HOS) to improve recognition performance of FER under partial occlusions. HOS or second-order statistics the so-called bispectrum is used to reconstruct the occluded texture feature based on the configuration and visual properties of the human face. The bispectrum could capture a contour (shape) and texture information of the facial emotion whose enable the effective implementation algorithm in FER. In this framework, first the 2D facial spatial images are projected into 1D signal by means of Radon transform. The Radon transform has properties of rotation and translational invariants; thus, it can preserve any variation in pixel intensities. Then, the projected 1D signal was analysed using HOS to obtain bispectrum magnitude plot whose exhibit the behaviour of different emotions. A set of bispectral statistic features were extracted from the bispectrum plot and used as informative features to recognize the emotions. Linear discriminant analysis (LDA) was adopted to reduce the data features before fed as input to Support Vector Machines. A series of experiments have been conducted on CK database. The obtained results show that the recognition rates of occlusion of the upper face give the accuracy of 93.1%; thus, it is promising.

Feature extraction using Radon transform and Discrete Wavelet Transform for facial emotion recognition

This paper presents a new pattern framework of using Radon and wavelet transform for facial emotion recognition. The Radon transform is translation and rotation invariants, hence it preserves the variations in pixel intensities. In this work, Radon transform has been used to project the 2D image into Radon space before subjected to Discrete Wavelet Transform (DWT). In DWT framework, the approximate coefficients (cA2) at second level decomposition are extracted and used as informative features to recognize the facial emotion. Since there are a large number of coefficients, hence the principal component analysis (PCA) is applied on the extracted features. The k-nearest neighbor classifier is adopted as classifier to classify seven (anger, disgust, fear, happiness, neutral, sadness and surprise) facial emotions. To evaluate the effectiveness of the proposed method, the JAFFE database has been employed. Based on the results obtained, the proposed method demonstrates the recognition rate of 91.3%, thus it is promising.

Facial emotion recognition under partial occlusion using Empirical Mode Decomposition

One of the challenges in automatic facial emotion recognition nowadays is the ability to handle with complicated environment conditions such as in the presence of partial occlusions of facial images. To address this issue, therefore this paper proposed to investigate the effect of facial emotion recognition in the presence of partially occluded images using empirical mode decomposition (EMD). EMD a multi-resolution technique which is adaptively decomposed non-stationary and nonlinear data into a small set of frequency component known as intrinsic mode functions (IMFs). In this work, the face image is firstly projected into 1D signal using the Radon transform. The projected 1D signal is subjected to EMD to extract the significant features based on IMFs. The obtained IMFs features are further reduced using PCA plus LDA to reduce the dimension of the features. Then, the reduced feature vector is used as input to Support Vector Machines (SVM) classifier for recognizing seven facial emotions. A series of experiments has been conducted on the CK database under four different modes of occlusion such as right face occlusion, left face occlusion, upper face occlusion and lower face occlusion. The experimental results show that the upper face occlusion contributes the highest recognition rate which is 93.91%, thus the proposed method demonstrates the promising results.

Facial emotion recognition under noisy environment using empirical mode decomposition

One of the challenges faced by automatic facial emotion recognition nowadays is the ability to deal with complicated environmental conditions such as noisy environments. In order to solve this problem, this paper aims to examine facial emotion recognition under noisy environment using empirical mode decomposition (EMD). EMD is a multiresolution technique which is adaptively decomposed nonstationary and nonlinear data into a small set of frequency component known as intrinsic mode functions (IMFs). First, the image is subjected to radon transform to convert into 1D projection signal followed by EMD algorithm. Then, the extracted IMFs features are subjected to a dimension reduction technique, namely Principle Component Analysis plus Linear Discriminant Analysis (PCA plus LDA). The reduced feature vector is used as input to Support Vector Machines (SVM) and k-Nearest Neighbor (k-NN) classifier for recognizing seven facial emotions. A series of experiments has been conducted on CK database. The experimental results show that facial emotion recognition under noisy environment using EMD technique enables to minimize the effect of the noise in classifying the facial emotion, thus demonstrates promising results.