Anima Majumder

Emotion recognition from geometric facial features using self-organizing map

This paper presents a novel emotion recognition model using the system identification approach. A comprehensive data driven model using an extended Kohonen self-organizing map (KSOM) has been developed whose input is a 26 dimensional facial geometric feature vector comprising eye, lip and eyebrow feature points. The analytical face model using this 26 dimensional geometric feature vector has been effectively used to describe the facial changes due to different expressions. This paper thus includes an automated generation scheme of this geometric facial feature vector. The proposed non-heuristic model has been developed using training data from MMI facial expression database. The emotion recognition accuracy of the proposed scheme has been compared with radial basis function network, multi-layered perceptron model and support vector machine based recognition schemes. The experimental results show that the proposed model is very efficient in recognizing six basic emotions while ensuring significant increase in average classification accuracy over radial basis function and multi-layered perceptron. It also shows that the average recognition rate of the proposed method is comparatively better than multi-class support vector machine. HighlightsWe propose an emotion recognition model using system identification.Twenty six dimensional geometric feature vector is extracted using three different algorithms.Classification using an intermediate Kohonen self-organizing map layer.A comparative study with Radial basis function, Multi-layer perceptron and Support vector machine.Efficient recognition results with significant increase in average recognition accuracy over radial basis function and multi-layer perceptron. Marginal improvement over support vector machine.

Optimization of turning process parameters using Multi-objective Evolutionary algorithm

Machining parameters optimization is very crucial in any machining process. This research focuses on Multi-objective Evolutionary Algorithm based optimization technique, to determine optimal cutting parameters (cutting speed, feed, and depth of cut) in turning operation. Two conflicting objectives (operation time and tool life) with three constraints, which depends on the turning parameters, are optimized using Genetic algorithm (GAs). The Pareto-optimal front of the bi-objective problem is obtained using Non-dominated Sorting Genetic Algorithm (NSGA-II). The extreme and intermediate points of Pareto optimal front is verified using Real coded Genetic Algorithm (RGA) as well as ε-constraint method. The performance of NSGA-II is found to be more effective and efficient as compared to micro-GA. Innovization study carried out to correlate cutting parameters with the aforementioned objective functions. The effect of cutting speed is found more as compared to feed rate and depth of cut.

Automatic Facial Expression Recognition System Using Deep Network-Based Data Fusion

This paper presents a novel automatic facial expressions recognition system (AFERS) using the deep network framework. The proposed AFERS consists of four steps: 1) geometric features extraction; 2) regional local binary pattern (LBP) features extraction; 3) fusion of both the features using autoencoders; and 4) classification using Kohonen self-organizing map (SOM)-based classifier. This paper makes three distinct contributions. The proposed deep network consisting of autoencoders and the SOM-based classifier is computationally more efficient and performance wise more accurate. The fusion of geometric features with LBP features using autoencoders provides better representation of facial expression. The SOM-based classifier proposed in this paper has been improved by making use of a soft-threshold logic and a better learning algorithm. The performance of the proposed approach is validated on two widely used databases (DBs): 1) MMI and 2) extended Cohn–Kanade (CK+). An average recognition accuracy of 97.55% in MMI DB and 98.95% in CK+ DB are obtained using the proposed algorithm. The recognition results obtained from fused features are found to be distinctly superior to both recognition using individual features as well as recognition with a direct concatenation of the individual feature vectors. Simulation results validate that the proposed AFERS is more efficient as compared to the existing approaches.

Local binary pattern based facial expression recognition using Self-organizing Map

This paper presents an appearance feature based facial expression recognition system using Kohonen Self-Organizing Map (KSOM). Appearance features are extracted using uniform Local binary patterns (LBPs) from equally sub-divided blocks applied over face image. The dimensionality of the LBP feature vector is further reduced using principal component analysis (PCA) to remove the redundant data that leads to unnecessary computation cost. Using our proposed KSOM based classification approach, we train only 59 dimensional LBP features extracted from whole facial region. The classifier is designed to categorize six basic facial expressions (happiness, sadness, disgust, anger, surprise and fear). To validate the performance of the reduced 59 dimensional LBP feature vector, we also train the original data of dimension 944 using the KSOM. The results demonstrates, that with marginal degradation in overall recognition performance, the reduced 59 dimensional data obtains very good classification results. The paper also presents three more comparative studies based on widely used classifiers like; Support vector machine (SVM), Radial basis functions network (RBFN) and Multi-layer perceptron (MLP3). Our KSOM based approach outperforms all other classification methods with average recognition accuracy 69.18%. Whereas, the average recognition rated obtained by SVM, RBFN and MLP3 are 65.78%, 68.09% and 62.73% respectively.

Facial Expression Recognition with Regional Features Using Local Binary Patterns

This paper presents a simple yet efficient and completely automatic approach to recognize six fundamental facial expressions using Local Binary Patterns LBPs texture features. A system is proposed that can automatically locate four important facial regions from which the uniform LBPs features are extracted and concatenated to form a 236 dimensional enhanced feature vector to be used for six fundamental expressions recognition. The features are trained using three widely used classifiers: Naive bayes, Radial Basis Function Network RBFN and three layered Multi-layer Perceptron MLP3. The notable feature of the proposed method is the use of few preferred regions of the face to extract the LBPs features as opposed to the use of entire face. The experimental results obtained from MMI database show proficiency of the proposed features extraction method.

Facial expressions recognition system using Bayesian inference

The paper presents a facial expressions recognition system using Bayesian network. We train the network using probabilistic modeling that draws relationship between facial features, action units and finally recognizes six basic emotions. We propose features extraction methods to get geometric feature vector containing angular informations and appearance feature vector containing moments extracted after applying gabor filter over certain facial regions. Both the feature vectors are further used to draw relationships among Action Units (AUs). The angular informations are directly extracted from the facial landmark points. The geometric features extraction approach contains only 22 dimensional angular informations against direct facial landmarks based approach that contains 136 dimensional feature vector. Facial activities are represented by three distinct layers. Bottom level contains landmark measurement data with angular features. Middle level has facial AUs those are coded in facial action coding system (FACS) and the top level, represents emotion node. We also propose a method using k-means clustering to automatically define the states of nodes in anatomical layer that draws relationship among AUs and measurement data. Extended Cohn Kanade Database is being used for our experimental purposes. An average emotion recognition accuracy of 95.7% is achieved using proposed Bayesian network based approach for 22 dimensional angular feature vector. To verify the performance of the proposed approach we apply three different classifiers such as, Support vector machine, Decision tree and Radial basis functions network. The confusion matrices show that the Bayesian network based classification approach outperforms all other applied approaches. The experimental results illustrates the effectiveness of the proposed model.

Image processing algorithms for improved character recognition and components inspection

The importance of inspection process has been magnified by the requirements of the modern manufacturing environment. A variety of approaches for automatic inspection of machine parts have been reported over last two decades. In this work it is targeted to develop an automated machine vision software system, which is used to inspect automotive parts like PE pumps after assembly of different components. Inspection is carried out to detect missing components, misalignment of components and out of tolerance of components. This work proposes some methodologies for Optical Character Recognition (OCR) and feature extraction. An improved Local Mean-Gradient thresholding algorithm[1] is proposed and implanted to recognize the characters like type number and serial number printed on the automotive parts like PE-PUMP, irrespective of the variation in background colors, industrial noises like dust particles, oily surfaces etc. The proposed methodologies have been implemented and explained here with some generic examples which overcome various industrial constraints. In this work, it is proved that automatic selection of threshold based on the background colors has improved the OCR performance to 100% recognition. The second part focuses on the extraction of suitable features in order to obtain a good pattern matching result even under various industrial constraints. Laplacian method of edge which is based on difference in gray level is more sensitive to noise. The second part gives an improved edge detection method using laplacian operator.

GMR based pain intensity recognition using imbalanced data handling techniques

The presence of imbalanced data distribution is evident in most real-life datasets. The problem of learning from imbalanced data is a challenging task due to presence of underrepresented data and severe class distribution skews. In this paper we recognizes 15 different levels of shoulder pain intensities based on facial expressions using UNBC-McMaster Shoulder Pain Expression Archive database which has highly imbalanced data distribution among its classes. A 22 dimensional geometric features are extracted from detected facial landmarks. The feature set is balanced using Synthetic Minority Oversampling Technique (SMOTE) and also using Adaptive Synthetic Sampling (ADASYN). A recognition technique is developed using Gaussian Mixture Regression (GMR) to recognize the fifteen different intensity levels. Comprehensive experiments with various settings show that the proposed pain intensity recognition system using SMOTE and GMR yields stable and promising recognition results.

Shoulder pain intensity recognition using Gaussian mixture models

Automatic recognition of pain intensity has an important medical application. The approach of automatic pain assessment boosts the psychological comfort of patients. It could be a direct help to children, mentally challenged people, very elderly people, patients in postoperative care, or people with transient state of consciousness. Since pain is a subjective phenomenon, it is quite difficult to have an automatic pain measuring device. The research is relatively new in this field and is constantly evolving. In this paper we propose a completely automatic shoulder pain intensity recognition system. A very small dimensional directional displacement geometric feature vector is extracted automatically from prominent facial regions. To classify the features into sixteen levels of intensities Gaussian Mixture Model (GMM) and Support Vector Machines (SVM) are used. The UNBC-McMaster Shoulder Pain Expression Archive Database is used for the experimentation. The database has various challenges associated with it including the problem of head orientation which is also addressed in this work. We achieve an average recognition accuracy of 82.1% using GMM and 87.43% using SVM classifier.