Search

The present article proposes a geometry-based fuzzy relational technique for capturing gradual change in human emotion over time available from relevant face image sequences. As associated features, we make use of fuzzy membership arising out of five triangle signatures such as - (i) Fuzzy Isosceles Triangle Signature (FIS), (ii) Fuzzy Right Triangle Signature (FRS), (iii) Fuzzy Right Isosceles Triangle Signature (FIRS), (iv) Fuzzy Equilateral Triangle Signature (FES), and (v) Other Fuzzy Triangles Signature (OFS) to achieve the task of appropriate classification of facial transition from neutrality to one among the six expressions viz. anger (AN), disgust (DI), fear (FE), happiness (HA), sadness (SA) and surprise (SU). The effectiveness of the Multilayer Perceptron (MLP) classifier is tested and validated through 10 fold cross-validation method on three benchmark image sequence datasets namely Extended Cohn-Kanade (CK+), M&M Initiative (MMI), and Multimedia Understanding Group (MUG). Experimental outcomes are found to have achieved accuracy to the tune of 98.47%, 93.56%, and 99.25% on CK+, MMI, and MUG respectively vindicating the effectiveness by exhibiting the superiority of our proposed technique in comparison to other state-of-the-art methods in this regard.

Automatic recognition of facial expressions and modeling of human expressions are very essential in the field of affective computing. The authors have introduced a novel geometric and texture-based method to extract the shapio-geometric features from an image computed by landmarking the geometric locations of facial components using the active appearance model (AAM). Expression-specific analysis of facial landmark points is carried out to select a set of landmark points for each expression to identify features for each specific expression. The shape information matrix (SIM) is constructed the set salient landmark points assign to an expression. Finally, the histogram-oriented gradients (HoG) of SIM are computed which is used for classification with multi-layer perceptron (MLP). The proposed method is tested and validated on four well-known benchmark databases, which are CK+, JAFFE, MMI, and MUG. The proposed system achieved 98.5%, 97.6%, 96.4%, and 97.0% accuracy in CK+, JAFFE, MMI, and MUG database, respectively.

Video-based facial expression recognition is a potential alternative for detecting the transitional processes of human emotion. In this paper, we present the landmark triangulation-induced altitude signatures to depict gradual changes in human emotion from face video frames. In our proposed approach, we consider the geometry-based triangulation technique which results from the triangles formed by important landmark points on face images. In this work, we measure three altitudes from all triangles and generate three different variations of altitude signature viz. AS1, AS2 and AS3 for the classification of six basic emotions viz. anger (AN), disgust (DI), fear (FE), happiness (HA), sadness (SA) and surprise (SU) in several ways. The performance capability of our proposed recognition system is tested on three benchmark face video datasets: Extended Cohn–Kanade (CK+), M&M Initiative (MMI), and Multimedia Understanding Group (MUG) through the application of Multilayer Perceptron (MLP) classifier and also validated by tenfold cross-validation method. Experimental results, 98.77%, 93.06%, and 98.75% on CK+, MMI, and MUG, respectively, are found very impressive. System efficacy is vindicated by showing the superiority of the proposed technique over the other existing techniques.

Facial expression is directly related to the changes in the shape of a face. The Active Appearance Model (AAM) can be used to determine the geometrical position of basic components by earmarking landmark points. The landmark points which are congruent upon the basic facial expressions are considered for the generation of triangle set encompassing the face. In this context, the area of the triangle formed by connecting the Circumcenter, Incenter, and Centroid is considered as the key shape descriptor. This novel feature is learned with Multi-Layer Perceptron (MLP) for the classification of expressions in six atomic classes viz Anger, Disgust, Fear, Happiness, Sadness, and Surprise. The proposed system is tested on four well-known benchmark databases viz. I. The Extended Cohn–Kanade (CK+) II. Japanese Female Facial Expression (JAFFE) III. Multimedia Imaging (MMI) and, IV. Multimedia Understanding Group (MUG) database. Overwhelming impressive results on these four databases confirm the effectiveness and efficiency of our proposed method.

Usage of the system for human emotion recognition has been increased in various types of applications of affective computing fields such as human sign language understanding, identification of human mental disorder, and human-computer interaction. Here, we report a video frame-based procedure for the estimation of human emotional behavior. We introduce Circumradius-Incenter-Circumcenter combined geometric signature (CIC) induced from our proposed triangulation method. The method first includes the step of salient landmark identification from face image frames by using the Active Appearance Model (AAM). Here, we fetch geometric features from triangles drawn by landmark points, thereafter core triangles are found based on the CIC feature which plays an important role to get an interpretation of changing information of human emotions. In the end, the extracted core features from core triangles are employed into the Multilayer Perceptron (MLP) classifier to get recognition accuracy. The discrimination power of our proposed system is evaluated on well-known three benchmark video face frame databases, viz., CK+, MMI, and MUG. Moreover, the performance of the proposed procedure is validated by presenting the comparison task with other existing methods.

Facial expression recognition system provides us enormous scope for studying characteristics of different human facial expression. Basic expressions (anger, disgust, fear, happiness, sadness, and surprise) can be distinguished from one another with minimum overlapping features between them. A human facial emotion can be represented uniquely if we are able to capture such features having high discrimination power. In this paper, we propose a method for recognizing facial expression by using salient landmark-induced gradient signature derived from the line segment joining circumcenter and incenter pair of a triangle obtained by joining relevant landmark points. We use appearance-based models to detect essential landmark points on face. We are considering only those landmark points situated at eyes, lips, eyebrows, and nose to get geometric feature. This landmark-based geometric facial feature has been used to describe changes in emotion from neutral through basic expression. We examine our proposed method on Chon-Kanade (CK+), MMI, and MUG benchmark image sequence databases and compare its performance under different motion image databases. In our experiment, dynamic behavior of every individual expression has been recognized with impressive recognition rate of accuracy.

Intelligent recognition of human emotion is an emerging field of affective computing that emphasizing the capability of a computer to understand the emotional state of humans. Gradual changes in human emotion can be displayed through understanding the nature of the transition of six basic facial expressions viz. anger(AN), disgust(DI), fear(FE), happiness(HA), sadness(SA), and surprise(SU). Here, we report a framework for the identification of transition from one emotional state to another as reflected in human faces and available in video sequences. we introduce the triangulation process to achieve the goal that uses salient landmark points extracted from video frames and produces a geometric feature describing the transition of basic emotion. For the classification of basic facial expressions, Multilayer Perceptron (MLP) uses a barycentre-orthocentre paired distance signature produced by the triangulation process. Our proposed approach shows impressive recognition results on different benchmark video datasets viz. Extended Cohn-Kanade Dataset (CK+), MMI, and MUG with average accuracy 97.55%, 92.07%, and 98.50% respectively.

Human face emotions are generally classified in six different expressions such as Anger, Disgust, Fear, Happiness, Sadness, and Surprise. The authors propose a novel method for selecting an expression specific set of salient landmark points out of 68 landmark points produced by applying an Active Appearance Model (AAM) on an input face image. The salient Landmark points are selected by training a MultiLayer Perceptron network using a Histogram oriented Gradient (HoG) feature of neighboring pixels of a Landmark point. Next, a shape signature vector is constructed by forming triangulation using those salient landmarks for each expression. This is trained with six Multilayered Perceptron (MLP) network for classification of each of the six basic expressions. The suggested algorithm is tested on CK+, JAFFE, MMI, and MUG database. The outcomes are found extremely promising.

Human emotion reflected in facial expression is generated by coordinated operation of muscular movement of facial tissue which associates with the emotional state of the human subject. Facial expression is one of the most significant non-articulated forms of social communication and it is highly adopted by scientific community for the purpose of automated emotion analysis. In the present scope, a triangular structure is induced with three points, viz., circumcenter, incenter, and centroid are considered as the geometric primitive for extraction of relevant features. Information extracted from such features is utilized for the purpose of discrimination of one expression from another using MultiLayer Perceptron (MLP) classifier in images containing facial expressions available in various benchmark databases. Results obtained by applying this method found to be extremely encouraging.

Intelligent recognition of human emotions from face images is a challenging proposition in the field of affective computing which becomes even more difficult when one has to deal with characterizing the nature of transition of human emotion from a relevant sequence of face images. In the present scope, we considered a triangulation mechanism derived from the landmark points of the face images. Resulting in a number of triangle formulations which are found to be sensitive to different emotions like anger, disgust, fear, happiness, sadness, and surprise. Accordingly a pair of circles, viz, incircle and circumcircle corresponding to these triangles are taken into account and geometric features arising out of such pair are utilized for classification of different emotional transitions from various face image sequences. Results of the proposed method obtained by application on various benchmark image databases are found to be quite impressive and encouraging compared to existing state-of-the-art technique.

Methods Here, we designed disulfide-stabilized recombinant HIV1 subtype B (SF162) envelope glycoproteins (Env), gp120 and gp140, by insertion of site-specific cysteine pairs between two layers (layer 1 and 2) in inner domain of gp120. In addition, we identified a novel adjuvant approach using Carbopol 971P, a cross-linked polyanionic carbomer, in combination with the Novartis proprietary oil-in water adjuvant, MF59, to augment humoral immune responses to the Env glycoprotein. We performed thorough in vitro analysis of the disulfide-stabilized Env glycoprotein followed by in vivo evaluations of the adjuvanted-Env glycoprotein boost in rabbits.

Results We evaluated systemic and mucosal immune responses in mice and rabbits using the SAMTM platform expressing HIV-1 gp140 (HIV-SAMTM vaccine) prime, protein/MF59 vaccine boost regimen for both HIV-1 Clade B and C Env antigens. In mice, the primed Env-specific IgG response to 1 μg of the HIV-SAMTM vaccine was comparable to a 10 μg dose of an identically formulated DNA vaccine, 10(7) IU of VRP, and 10 μg protein/MF59 vaccines. The HIVSAMTM vaccine primed response could be boosted robustly by a protein/MF59 vaccine and resulted in a balanced IgG1, IgG2a subclass response, similar to that seen with the VRP vaccine, but unlike the dominant IgG1 response to protein/MF59 only vaccinations. Both Envspecific CD4+ and CD8+ T-cell responses were detectable after two HIV-SAMTM vaccinations. A TH1 type (IFNg+, IL-5-) profile was demonstrable for the HIV-SAMTM vaccine primed, protein boosted CD4+ T-cell response, similar to that seen with the DNA or VRP primed protein boosted responses, in contrast to a TH2 type (IFNglow, IL-5+) response seen with protein/MF59 vaccination. In rabbits, priming with the 25 or 50 μg of the formulated HIV-SAMTM vaccine induced robust and avid Env-binding IgG and HIV neutralizing antibodies that were superior to 500 μg of an unformulated DNA vaccine and comparable to VRP and protein/MF59 vaccines. In addition, protein/ MF59 boostable Env-specific vaginal wash Ig was consistently demonstrable in both mice and rabbits immunized with the HIV-SAMTM.