• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.155-161
• /
• 2024

In this paper, we propose a new model by adding landmark information as a feature vector to the existing CNN-based facial emotion classification model. Facial emotion classification research using CNN-based models is being studied in various ways, but the recognition rate is very low. In order to improve the CNN-based models, we propose algorithms that improves facial expression classification accuracy by combining the CNN model with a landmark-based fully connected network obtained by ASM. By including landmarks in the CNN model, the recognition rate was improved by several percent, and experiments confirmed that further improved results could be obtained by adding FACS-based action units to the landmarks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.512-517
• /
• 2011

In this paper, we propose an Active Shape Model (ASM) and Lucas-Kanade (LK) optical flow-based feature extraction and analysis method for analyzing the emotional features from facial images. Considering the facial emotion feature regions are described by Facial Action Coding System, we construct the feature-related shape models based on the combination of landmarks and extract the LK optical flow vectors at each landmarks based on the centre pixels of motion vector window. The facial emotion features are modelled by the combination of the optical flow vectors and the emotional states of facial image can be estimated by the probabilistic estimation technique, such as Bayesian classifier. Also, we extract the optimal emotional features that are considered the high correlation between feature points and emotional states by using common spatial pattern (CSP) analysis in order to improvise the operational efficiency and accuracy of emotional feature extraction process.

• Journal of Information Science Theory and Practice
• /
• v.7 no.2
• /
• pp.32-39
• /
• 2019

A convolutional neural network (CNN) has been widely used in facial expression recognition (FER) because it can automatically learn discriminative appearance features from an expression image. To make full use of its discriminating capability, this paper suggests a simple but effective method for CNN based FER. Specifically, instead of an original expression image that contains facial appearance only, the expression image with facial geometry visualization is used as input to CNN. In this way, geometric and appearance features could be simultaneously learned, making CNN more discriminative for FER. A simple CNN extension is also presented in this paper, aiming to utilize geometric expression change derived from an expression image sequence. Experimental results on two public datasets (CK+ and MMI) show that CNN using facial geometry visualization clearly outperforms the conventional CNN using facial appearance only.

• Korean Journal of Head & Neck Oncology
• /
• v.26 no.2
• /
• pp.253-255
• /
• 2010

Identification and protection of the facial nerve is very important in the proper operation of the parotid tumor. Posterior approach which finds main trunk of the facial nerve by surgical landmark such as tragal pointer, tympanomastoid suture, and posterior belly of digastric muscle is most commonly used. In case of posterior located tumor, inferior approach may be used, in which the retromandibular vein is followed from the neck and inferior branch of the facial nerve is located. In general, the facial nerve lies superficial to the retromandibular vein. But we experienced the anomalous relationship of the facial nerve and the retromandibular vien. We report this case with a literature review.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.163-170
• /
• 2022

This paper introduces a method of extracting facial features due to unrefined inputs in real life and improving the problem of not guaranteeing the ideal performance and speed of the object recognition model through a storage algorithm through weight summation. Many facial recognition processes ensure accuracy in ideal situations, but the problem of not being able to cope with numerous biases that can occur in real life is drawing attention, which may soon lead to serious problems in the face recognition process closely related to security. This paper presents a method of quickly and accurately recognizing faces in real time by comparing feature points extracted as input with a small number of feature points that are not overfit to multiple biases, using that various variables such as picture composition eventually take an average form.

• The korean journal of orthodontics
• /
• v.49 no.1
• /
• pp.32-40
• /
• 2019

Objective: Precise identification of landmarks on posteroanterior (PA) cephalograms is necessary when evaluating lateral problems such as facial asymmetry. The aim of the present study was to investigate whether the use of lateral (LA) cephalograms can reduce errors in landmark identification on PA cephalograms. Methods: Five examiners identified 16 landmarks (Cg, N, ANS, GT, Me, RO, Lo, FM, Z, Or, Zyg, Cd, NC, Ms, M, and Ag) on 32 PA cephalograms with and without LA cephalograms at the same time. The positions of the landmarks were recorded and saved in the horizontal and vertical direction. The mean errors and standard deviation of landmarks location according to the use of LA cephalograms were compared for each landmark. Results: Relatively small errors were found for ANS, Me, Ms, and Ag, while relatively large errors were found for N, GT, Z, Or, and Cd. No significant difference was found between the horizontal and vertical errors for Z and Or, while large vertical errors were found for N, GT, and Cd. The value of identification error was lower when the landmarks were identified using LA cephalograms. Statistically significant error reductions were found at N and Cd with LA cephalograms, especially in the vertical direction. Conclusions: The use of LA cephalograms during identification of landmarks on PA cephalograms could help reduce identification errors.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.34 no.6
• /
• pp.622-627
• /
• 2008

In orthognathic surgery, precise analysis and diagnosis are essential for successful results. In facial asymmetric patient, traditional 2D image analysis has been used by lateral and P-A Cephalometric view, Skull PA, Panorama, Submentovertex view etc. But clinicians sometimes misdiagnose because they cannot find exact landmark due to superimposition, moreover image can be magnified and distorted by projection technique or patient's skull position, when using these analysis and method. For overcome these defects, analysis by using of 3D CT has been introduced. In this way we can analysis precisely by getting the exact image free of artifact and finding exact landmark with no interruption of superimposition. So we want to review of relationship between various skeletal landmarks of mandible or cranial base and facial asymmetry by predictable analysis using 3D CT. We select the cases of the patients who visited our department for correction of facial asymmetry during 2003-2007 and who were taken image of 3D CT for diagnosis. 3D CT images were reconstructed to 3D image by using V-Work program (Cybermed Inc., Seoul, Korea). And we analysis the relationship between facial asymmetry and various affecting factor of skeletal pattern. The mandibular ramus hight difference between right and left was most affecting factor that express facial asymmetry. And in this research, there was no relationship between cranial base and facial asymmetry. The angulation between facial midline and mandibular ramus divergency has significant relationship with facial asymmetry

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.213-220
• /
• 2018

Face morphing, one of the most powerful image processing techniques that are often used in image processing and computer graphic fields, as it is a technique to change the image progressively and naturally from the original image to the target image. In this paper, we propose a method to generate Delaunay triangles using the facial landmark vertices generated by the Dlib face landmark detector and to implement morphing through warping and cross dissolving of Delaunay triangles between the original image and the target image. In this paper, we generate vertex points for face not manually but automatically, which is the major feature of the face such as eye, eyebrow, nose, and mouth, and is used to generate Delaunay triangles automatically which is the main characteristic of our face morphing method. Simulations show that we can add vertices manually and get more natural morphing results.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.666-673
• /
• 2014

This paper proposes a scalable face recognition method for unconstrained face databases, and shows a simple experimental result. Existing face recognition research usually has focused on improving the recognition rate in a constrained environment where illumination, face alignment, facial expression, and background is controlled. Therefore, it cannot be applied in unconstrained face databases. The proposed system is face feature extraction algorithm for unconstrained face recognition. First of all, we extract the area that represent the important features(landmarks) in the face, like the eyes, nose, and mouth. Each landmark is represented by a high-dimensional LBP(Local Binary Pattern) histogram feature vector. The multi-scale LBP histogram vector corresponding to a single landmark, becomes a low-dimensional face feature vector through the feature reduction process, PCA(Principal Component Analysis) and LDA(Linear Discriminant Analysis). We use the Rank acquisition method and Precision at k(p@k) performance verification method for verifying the face recognition performance of the low-dimensional face feature by the proposed algorithm. To generate the experimental results of face recognition we used the FERET, LFW and PubFig83 database. The face recognition system using the proposed algorithm showed a better classification performance over the existing methods.

• Archives of Craniofacial Surgery
• /
• v.19 no.1
• /
• pp.75-78
• /
• 2018

Depression of facial contour after parotidectomy is still challenging to many of surgeons. A 68-year-old man presented with a 4-month history of a painless swelling in both parotid area. The mass was multiple and fixed at the parotid region. We conducted a parotid duct preserving bilateral superficial parotidectomy by one-stage operation to remove the multiple tumors. A lazy S incision was made in both preauricular area and the peripheral branches of the facial nerve were identified using surgical landmark. After dissecting the branches of the facial nerve and parotid duct, main parotid duct was preserved but only small fine ductules from the superficial lobe were ligated. Parotid gland was excised from its anterior aspect with about 1 cm of normal parotid tissue margin. The patient was followed up for 6 years to evaluate postoperative parotid gland function and the computed tomography (CT) was taken. Patient was satisfied with no significant complication such as sunken changes in facial contour, facial nerve function. As far as we know, it is the first study to compare long-term soft tissue contours of soft tissue of duct preserving superficial parotidectomy with duct sacrificing superficial parotidectomy by means of CT findings.