Face Rotation Research Articles

Labral Repair of the Acetabulum Using a Toggle Suture Technique

Acetabular labral repair requires positioning the labrum on the edge of the acetabulum with appropriate tension and rotation to recreate the suction seal with the femoral head. Considering that the labrum is a triangular shape in cross-section, rotation of the articular face of the labrum relative to the femoral head also affects the suction seal. The purpose of the toggle suture technique described herein is to control the rotation of the labrum to allow the articular face to directly contact the femoral head and optimize the suction seal. The technique is performed by passing the midaspect of a suture around the labrum at the chondrolabral junction. The loop is retrieved and delivered outside the same portal. One of the 2 free suture tails is then passed through the loop, which is then manually tensioned. This creates a single loop around the labrum with a suture tail on either side that allows for rolling, or “toggling,” of the labrum to place the articular face in line with the femoral head.

Inner-Canthus Localization of Thermal Images in Face-View Invariant

Inner-canthus localization has played an essential role in measuring human body temperature. This is due to the theory that human core body temperature can be measured in the inner-canthus. Such measurement is useful for mass screening since it is non-contact, non-invasive and fast. This paper presents an algorithm that has been developed to locate the inner-canthus. The algorithm proposed a robust method in various face-view, i.e., frontal, sided and tilted. The algorithm consisted of: face segmentation, determining face-orientation, rotating face into straight view, eye localization, and inner-canthus localization. The face segmentation used human temperature threshold of 34°C — the face orientation used trend line of a middle point between each most-bottom and most-top coordinates. The face rotation was based on the gradient of the trend line. Once the face is rotated, the eye location was determined using facial proportion. The inner-canthus location was determined as the highest intensities in the eye-frame. The test on 15 thermal images of faces with various view showed localization accuracy of 80% for eye-frame determination and 100% for inner-canthus localization.

Inner-Canthus Localization of Thermal Images in Face-View Invariant

Inner-canthus localization has played an essential role in measuring human body temperature. This is due to the theory that human core body temperature can be measured in the inner-canthus. Such measurement is useful for mass screening since it is non-contact, non-invasive and fast. This paper presents an algorithm that has been developed to locate the inner-canthus. The algorithm proposed a robust method in various face-view, i.e., frontal, sided and tilted. The algorithm consisted of: face segmentation, determining face-orientation, rotating face into straight view, eye localization, and inner-canthus localization. The face segmentation used human temperature threshold of 34°C — the face orientation used trend line of a middle point between each most-bottom and most-top coordinates. The face rotation was based on the gradient of the trend line. Once the face is rotated, the eye location was determined using facial proportion. The inner-canthus location was determined as the highest intensities in the eye-frame. The test on 15 thermal images of faces with various view showed localization accuracy of 80% for eye-frame determination and 100% for inner-canthus localization.

Effects of the upper respiratory tract cross-section on the vertical and sagittal dimension and the facial axis according to Ricketts

This study assesses the effects of the upper respiratory tract width at the level of the adenoid in patients with a normal and abnormal breathing route on basic parameters of the morphology of the facial skeleton. <b>Aim.</b> Comparison of skeletal parameters determining vertical (SNL/ML, NL/ML, NL/ML), sagittal (SNA, SNB) dimensions and type of facial rotation (the angle of the facial axis according to Ricketts) in the study and control groups and determination of the threshold value (a cut-off point) of width according to Holmberg, at which there is a deviation from the average values of basic parameters of morphology of the facial skeleton. <b>Material and methods.</b> The study included 221 patients treated at an orthodontic clinic in Kielce. Based on the medical history taken, clinical examination and subjective evaluation of the upper respiratory tract width according to Holmberg 112 patients were enrolled into the study group and 109 patients into the control group. The width of the upper respiratory tract was measured using the modified Holmberg method and parameters assessing the vertical (SNL/ML, NL/ML) and sagittal (SNA, SNB) dimensions, as well as the anterior angle of the Ricketts’ axis were measured using the analysis of lateral teleroentgenograms of the head. <b>Results.</b> All compared skeletal parameters indicated significant statistical differences between the study and control group. These differences were: Ricketts’ angle 6.5°, SNL/ML 8.5°, NL/ML 9.7°, SNA 2.4°, SNB 1.4°. <b>Conclusions.</b> The width of the upper respiratory tract at the level of the adenoid significantly affects values of skeletal parameters evaluating the vertical (SNL/ML, NL/ML) and sagittal (SNA, SNB) dimensions and the type of rotation of the facial axis. There is a correlation between a gradual decrease in the airway dimension according to Holmberg and an increase in the vertical dimension (SNL/ML, NL/ML) and anterior angle of the Ricketts’ facial axis (posterior rotation of the mandible) and a decrease in the sagittal dimension (SNA, SNB).

Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation

The detection of human emotions has applicability in various domains such as assisted living, health monitoring, domestic appliance control, crowd behavior tracking real time, and emotional security. The paper proposes a new system for emotion classification based on a generative adversarial network (GAN) classifier. The generative adversarial networks have been widely used for generating realistic images, but the classification capabilities have been vaguely exploited. One of the main advantages is that by using the generator, we can extend our testing dataset and add more variety to each of the seven emotion classes we try to identify. Thus, the novelty of our study consists in increasing the number of classes from N to 2N (in the learning phase) by considering real and fake emotions. Facial key points are obtained from real and generated facial images, and vectors connecting them with the facial center of gravity are used by the discriminator to classify the image as one of the 14 classes of interest (real and fake for seven emotions). As another contribution, real images from different emotional classes are used in the generation process unlike the classical GAN approach which generates images from simple noise arrays. By using the proposed method, our system can classify emotions in facial images regardless of gender, race, ethnicity, age and face rotation. An accuracy of 75.2% was obtained on 7000 real images (14,000, also considering the generated images) from multiple combined facial datasets.

Linear Predictors of Facial Rotation Pattern in Croatian Subjects with Skeletal Class III Malocclusion.

ObjectivesThe objective of this study was to determine whether the linear measures of the maxilla, mandible and cranial base were predictors of facial growth rotation in a Croatian population with Class III malocclusion by cephalometric radiographic methods.Material and methodsThe examined sample consisted of pretreatment lateral cephalometric records of 201 (111 females and 90 males) untreated Class III patients of Caucasian Croatian ancestry from the Department of Orthodontics at Zagreb University. The measurements were divided into five categories for analysis: cranial base, skeletal maxillary and skeletal mandibular relationships, sagittal intermaxillary and vertical relationships. Five multiple linear regression models were used to identify predictors of facial rotation pattern.ResultsThe effective length of the mandible was the most important predictor of facial rotation pattern, with the increased length largerly predisposing the tendency to the vertical growth pattern. No significant dichotomy was found regarding gender apart from the fourth model in which the posterior rotation of maxilla is related to female gender.ConclusionThese predictors could help orthodontists determine timing and therapy for Croatian patients with Class III malocclusions.

A Face Tracking Method in Videos Based on Convolutional Neural Networks

Face tracking in surveillance videos is one of the important issues in the field of computer vision and has realistic significance. In this paper, a new face tracking framework in videos based on convolutional neural networks (CNNs) and Kalman filter algorithm is proposed. The framework uses a rough-to-fine CNN to detect faces in each frame of the video. The rough-to-fine CNN method has a higher accuracy in complex scenes such as face rotation, light change and occlusion. When face tracking fails due to severe occlusion or significant rotation, the framework uses Kalman filter to predict face position. The experimental results show that the proposed method has high precision and fast processing speed.

Retrospective epidemiological study of mandibular rotational types in patients with orthodontical malocclusion.

The primary aim of this study was to illustrate the prevalence of facial skeletal discrepancy in an Italian sample. Another aim was to evaluate the effectiveness of the sagittal skeletal discrepancy classification in order to establish a morphologic pattern of growth useful for diagnosis and prediction of therapeutic results. The authors considered a sample of 732 patients (426 females and 306 males) aged between 6 and 17 years old. Cephalometric parameters were evaluated in order to establish a relationship between sagittal skeletal discrepancy and the classification of facial rotations (Lavergne and Petrovic). Facial types with neutral mandibular growth direction were the most prevalent, and were most observed in classes I and II; the latter was more represented than others in our sample. Facial types with posterior mandibular growth direction were the most prevalent in class III. Sagittal skeletal discrepancy classification is not able to establish a specific facial type or predict an individual responsiveness to treatment.

Development of a SMA-Fishing-Line-McKibben Bending Actuator

High power-to-weight ratio soft artificial muscles are of overarching importance to enable inherently safer solutions to human–robot interaction. Traditional air-driven soft McKibben artificial muscles are linear actuators, and it is impossible for them to realize bending motions through use of a single muscle. More than two McKibben muscles are normally used to achieve bending or rotational motions, leading to heavier and larger systems. In addition, air-driven McKibben muscles are highly nonlinear in nature, making them difficult to be controlled precisely. An shape memory alloy (SMA)-fishing-line-McKibben (SFLM) bending actuator has been developed. This novel artificial actuator, made of an SMA-fishing-line muscle and a McKibben muscle, was able to produce the maximum output force of 3.0 N and the maximum bending angle (the rotation of the end face) of 61°. This may promote the application of individual McKibben muscles or SMA-fishing-line muscles alone. An output force control method for the SFLM is proposed, and based on MATLAB/Simulink software, an experiment platform is set up and the effectiveness of control system is verified through output force experiments. A three-fingered SFLM gripper driven by three SFLMs has been designed for a case study and for which the maximum carrying capacity is 650.4 ± 0.2 g.

3D Face Feature Location Method Based on Stripes and Shape Index

A 3D face feature location method based on stripes and shape index is proposed in order to locate the feature points in face exactly and quickly. The grating projection technique is used to obtain 3D face image. Based on the difference between the background fringe image and the deformed fringe image, the basic information of the human face in the image is determined. The basic information includes left and right edge lines, upper and lower edge coordinates and the width of the human face in the image. And then, the approximate position of the ear is quickly determined according to the left or right edge line. The found areas of the tip of the nose and the inner canthus are reduced according to the position of the ear. The position of the tip of the nose and the inner canthus are determined according to the height and shape index information. The experiment was conducted in a dark environment, with an average total time of 4.05 seconds and an average time of positioning of 1.07 seconds. When the allowable error is 15 pixels, the positioning accuracy is 85.34% for different poses, and the positioning accuracy is 96.88% when the face rotation angle is less than 20 degrees.

A finite element analysis of stability of subtrochanteric oblique osteotomy in total hip arthroplasty for type IV developmental dysplasia of the hip

Objective Finite element analysis was used to evaluate the effects of different angles of subtrochanteric osteotomy on the bone and prosthesis stress and the stability of the osteotomy surface. Methods CT scan of A 50 year old female patient with Crowe type developmental dysplasia of the hip (DDH) was subjected to the CT scan, the femur data were extracted, the digital model was established, components were digitalized, and the operation was simulated. The osteotomy was done under the rotor downward inclination of 30°, 45°, 60°, 90°. The affected lateral single leg standing was developed by mechanical loading. The stress distribution, relative displacement and measurement of each model were detected. Results The stress distribution of the femoral and hip replacement was different from that of the whole femur. After the subtrochanteric osteotomy, the stress concentration appeared in both the prosthesis and the femur, and the stress concentration area of the femur was mainly located at the distal end of the osteotomy. From the angle of the displacement of the osteotomy plane, the relative displacements after 30°, 45°, 60° and 90° osteotomy were 101, 29, 48, and 133 μm respectively. The rotation and axial displacement of the osteotomy face were balanced when the inclination was 45°, and the overall displacement was minimum. Conclusion The finite element analysis shows that the subtrochanteric osteotomy can cause the stress concentration of the distal femur of the osteotomy. Because of the small overall displacement, the tilt of the rotor under 45° osteotomy is expected to obtain the best stability of the osteotomy surface. Key words: Developmental dysplasia of the hip; Total hip arthroplasty; Subtrochanteric oblique osteotomy; Finite element analysis

Holistic face representation is highly orientation-specific.

It has long been argued that face processing requires disproportionate reliance on holistic processing (HP), relative to that required for nonface object recognition. Nevertheless, whether the holistic nature of face perception is achieved via a unique internal representation or by the employment of an automated attention mechanism is still debated. Previous studies had used the face inversion effect (FIE), a unique face-processing marker, or the face composite task, a gold standard paradigm measuring holistic processing, to examine the validity of these two different hypotheses, with some studies combining the two paradigms. However, the results of such studies remain inconclusive, particularly pertaining to the issue of the two proposed HP mechanisms-an internal representation as opposed to an automated attention mechanism. Here, using the complete composite paradigm design, we aimed to examine whether face rotation yields a nonlinear or a linear drop in HP, thus supporting an account that face processing is based either on an orientation-dependent internal representation or on automated attention. Our results reveal that even a relatively small perturbation in face orientation (30 deg away from upright) already causes a sharp decline in HP. These findings support the face internal representation hypothesis and the notion that the holistic processing of faces is highly orientation-specific.

Face Recognition Employing DMWT Followed by FastICA

Face recognition becomes a challenging topic in several fields since images of faces are varied by changing illuminations, facial rotations, facial expressions, etc. In this paper, two dimensional discrete multiwavelet transform (2D DMWT) and fast independent component analysis (FastICA) are proposed for face recognition. Preprocessing, feature extraction, and classification are the main steps in the proposed system. In the preprocessing step, each pose in the database is divided into six parts to reduce the effect of unnecessary facial features and highlight the local features in each part. For feature extraction, the 2D DMWT is applied to each part for dimensionality reduction and features extraction. This results in two facial representations. Then FastICA followed by $$\ell _2$$ -norm is applied to each representation, which produces six and three different techniques for the first and second representation, respectively. This results in features that are more discriminating, less dependent, and more compressed. In the recognition step, the resulted compressed features from the two representations are fed to a neural network-based classifier for training and testing. The proposed techniques are extensively evaluated using five databases, namely ORL, YALE, FERET, FEI, and LFW, which have different facial variations, such as illuminations, rotations, facial expressions, etc. The results are analyzed using K-fold cross-validation. Sample results and comparison with a large number of recently proposed approaches are provided. The proposed approach is shown to yield significant improvement compared with the other approaches.

Viewpoint-Consistent 3D Face Alignment.

Most approaches to face alignment treat the face as a 2D object, which fails to represent depth variation and is vulnerable to loss of shape consistency when the face rotates along a 3D axis. Because faces commonly rotate three dimensionally, 2D approaches are vulnerable to significant error. 3D morphable models, employed as a second step in 2D+3D approaches are robust to face rotation but are computationally too expensive for many applications, yet their ability to maintain viewpoint consistency is unknown. We present an alternative approach that estimates 3D face landmarks in a single face image. The method uses a regression forest-based algorithm that adds a third dimension to the common cascade pipeline. 3D face landmarks are estimated directly, which avoids fitting a 3D morphable model. The proposed method achieves viewpoint consistency in a computationally efficient manner that is robust to 3D face rotation. To train and test our approach, we introduce the Multi-PIE Viewpoint Consistent database. In empirical tests, the proposed method achieved simple yet effective head pose estimation and viewpoint consistency on multiple measures relative to alternative approaches.

Iridium Halide Complexes [1,1‐X2‐8‐SMe2‐1,2,8‐IrC2B9H10]2 (X = Cl, Br, I): Synthesis, Reactivity and Catalytic Activity

The reactions of thallium salt Tl[7‐SMe2‐7,8‐C2B9H10] with [(cod)RhCl]2 and [Cp*RuCl]4 are accompanied by room‐temperature polyhedral rearrangement, giving rhoda‐ and ruthenacarboranes 1‐cod‐8‐SMe2‐1,2,8‐RhC2B9H10 (2) and 1‐Cp*‐8‐SMe2‐1,2,8‐RuC2B9H10 (3), respectively. According to DFT calculations, the rearrangement could be attributed to the triangular face rotation mechanism. The reaction of iridium derivative 1‐cod‐8‐SMe2‐1,2,8‐IrC2B9H10 (1) with anhydrous hydrohalic acids HX (X = Cl, Br, I) results in the dimeric halide iridacarboranes [1,1‐X2‐8‐SMe2‐1,2,8‐IrC2B9H10]2 [4a–c; X = Cl (a), Br (b), I (c)]. Bromide 4b reacts with Tl[Tl(η‐7,8‐C2B9H11)] and TlCp giving iridacarboranes 8′‐SMe2‐1,1′‐Ir(2,3‐C2B9H11)(2′,8′‐C2B9H10) (5) and 1‐Cp‐8‐SMe‐1,2,8‐IrC2B9H10 (6). The formation of the latter compound is accompanied by demethylation of the SMe2 substituent. The structures of 2, 3, 5 and 6 were determined by single‐crystal X‐ray diffraction. Iridacarboranes 4b and [1,1‐Br2‐4‐SMe2‐1,2,3‐IrC2B9H10]2 (7) catalyze the dimerization of diphenylacetylene, giving 1,2,3‐triphenylnaphthalene in 20–24 % yields. Compounds 4b and 7 also effectively catalyze the reductive amination reaction between aldehydes (or ketones) and primary (or secondary) amines in the presence of carbon monoxide, giving the corresponding secondary and tertiary amines in high yields (60–85 %).

ОБ ОДНОМ КЛАССЕ СИЛЬНО СИММЕТРИЧНЫХ МНОГОГРАННИКОВ

We prove the completeness of the list of closed convex polyhedra in E 3 , that are strongly symmetric with respect to the rotation of the faces . Polyhedron is called symmetric if it has at least one non-trivial rotation axis. All axes intersect at a single point called the center of the polyhedron. All considered polyhedra are polyhedra with the center. A convex polyhedron is called a strongly symmetrical with respect to the rotation of the faces, if each of its faces F has an rotation axis L , intersects the relative interior of F , and L is the rotation axis of the polyhedron. It is obvious that the order of rotation axis of L does not necessarily coincide with the order of this axis, if the face of F regarded as a figure separated from the polyhedron. It has previously been shown, that the requirement of global symmetry of the polyhedron faces the rotation axis can be replaced by the weaker condition of symmetry of the star of each face of the polyhedron: to polyhedron was symmetrical with respect to the rotation of the faces, it is necessary and sufficient that some nontrivial rotation axis of each face, regarded as a figure separated from the polyhedron, is the rotation axis of the star of face. Under the star of face F is understood face itself and all faces have at least one common vertex with F . Given this condition, the definition of the polyhedron strongly symmetric with respect to the rotation of the faces is equivalent to the following: the polyhedron is called a strongly symmetrical with respect to the rotation of the faces , if some non-trivial rotation axis of each face, regarded as a figure separated from the polyhedron, is the rotation axis of the star of face. In the proof of the main theorem on the completeness of the list of this class of polyhedra using the result of the complete listing of the so- called polyhedra of 1st and 2nd class [1]. In this paper we show that in addition to the polyhedra of the 1st and 2nd class, listed in [1], only 8 types of polyhedra belongs to the class of polyhedra stronghly symmetric with respect to the rotation of faces. Seven of this eighteen types are not combinatorially equivalent regular or semi-regular (Archimedean). One type of eight is combinatorially equivalent Archimedean polyhedra, but does not belong to polyhedra of 1st or 2nd class. Turning to the polyhedra, dual strongly symmetrical about the rotation of faces, that is, to the polyhedra, stronghly symmetric about the rotation of polyhedral angles, we get their complete listing. It follows that there are 7 types of polyhedra, highly symmetric with respect to the rotation of polyhedral angles which are not combinatorially equivalent to Gessel bodies. Class of polyhedra stronghly symmetric with respect to the rotation of faces, as well as polyhedra 1st and 2nd class mentioned above can be viewed as a generalization of the class of regular (Platonic) polyhedra. Other generalizations of regular polyhedra can be found in [3],[4], [12]-[15].

Assembled molecular face-rotating polyhedra to transfer chirality from two to three dimensions.

In nature, protein subunits on the capsids of many icosahedral viruses form rotational patterns, and mathematicians also incorporate asymmetric patterns into faces of polyhedra. Chemists have constructed molecular polyhedra with vacant or highly symmetric faces, but very little is known about constructing polyhedra with asymmetric faces. Here we report a strategy to embellish a C3h truxene unit with rotational patterns into the faces of an octahedron, forming chiral octahedra that exhibit the largest molar ellipticity ever reported, to the best of our knowledge. The directionalities of the facial rotations can be controlled by vertices to achieve identical rotational directionality on each face, resembling the homo-directionality of virus capsids. Investigations of the kinetics and mechanism reveal that non-covalent interaction among the faces is essential to the facial homo-directionality.

스테레오 비전을 이용한 마커리스 정합 : 특징점 추출 방법과 스테레오 비전의 위치에 따른 정합 정확도 평가

본 논문에서는 얼굴 영역 수술용 네비게이션을 위한 스테레오 비전과 CT 영상을 이용하여 환자-영상 간 정합(Image to patient registration) 알고리즘의 성능을 평가한다. 환자 영상 간 정합은 스테레오 비전 영상의 특징점 추출과 이를 통한 3차원 좌표 계산, 3차원 좌표와 3차원 CT 영상과의 정합 과정을 거친다. 스테레오 비전 영상에서 3가지 얼굴 특징점 추출 방법과 3가지 정합 방법을 사용하여 생성될 수 있는 5가지 조합 중 정합 정확도가 가장 높은 방법을 평가한다. 또한 머리의 회전에 따라 환자 영상 간 정합의 정확도를 비교한다. 실험을 통해 머리의 회전 각도가 약 20도의 범위 내에서 Active Appearance Model과 Pseudo Inverse Matching을 사용한 정합의 정확도가 가장 높았으며, 각도가 20도 이상일 경우 Speeded Up Robust Features와 Iterative Closest Point를 사용하였을 때 정합 정확도가 높았다. 이 결과를 통해 회전각도가 20도 범위 내에서는 Active Appearance Model과 Pseudo Inverse Matching 방법을 사용하고, 20도 이상의 경우 Speeded Up Robust Features와 Iterative Closest Point를 이용하는 것이 정합의 오차를 줄일 수 있다. This study evaluates the performance of image to patient registration algorithm by using stereo vision and CT image for facial region surgical navigation. For the process of image to patient registration, feature extraction and 3D coordinate calculation are conducted, and then 3D CT image to 3D coordinate registration is conducted. Of the five combinations that can be generated by using three facial feature extraction methods and three registration methods on stereo vision image, this study evaluates the one with the highest registration accuracy. In addition, image to patient registration accuracy was compared by changing the facial rotation angle. As a result of the experiment, it turned out that when the facial rotation angle is within 20 degrees, registration using Active Appearance Model and Pseudo Inverse Matching has the highest accuracy, and when the facial rotation angle is over 20 degrees, registration using Speeded Up Robust Features and Iterative Closest Point has the highest accuracy. These results indicate that, Active Appearance Model and Pseudo Inverse Matching methods should be used in order to reduce registration error when the facial rotation angle is within 20 degrees, and Speeded Up Robust Features and Iterative Closest Point methods should be used when the facial rotation angle is over 20 degrees.

Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos

This paper proposes a facial expression recognition (FER) method in videos. The proposed method automatically selects the peak expression face from a video sequence using closeness of the face to the neutral expression. The severely non-frontal faces and poorly aligned faces are discarded in advance to eliminate their negative effects on the peak expression face selection and FER. To reduce the effect of the facial identity in the feature extraction, we compute difference information between the peak expression face and its intra class variation (ICV) face. An ICV face is generated by combining the training faces of an expression class and looks similar to the peak expression face in identity. Because the difference information is defined as the distances of locally pooled texture features between the two faces, the feature extraction is robust to face rotation and mis-alignment. Results show that the proposed method is practical with videos containing spontaneous facial expressions and pose variations.

Principal Component Analysis based Feature Vector Extraction

Objectives: A simple and efficient method is employed to extract feature vector from images and to reduce the dimension of data. Once the feature vectors are extracted, it can be used in face recognition module. Methods/Analysis: Principal Components Analysis (PCA) is used for face recognition technique for feature identification in large data sets and to highlight their similarities and differences is more essential step in face recognition. PCA is used as efficient tool in data analysis to reduce dimension and to obtain maximum variance of data. Findings: Experiment is conducted using Yale database B. The face images are formed with multiple factors on different lighting conditions, background interference, and face rotation etc. The experimental results on Yale database B are given to illustrate the proposed method. Conclusion/Application: A simple and effective feature extraction method is analyzed for face images and experimental results are shown. Keywords: Eigenvalue, Eigenvector, Feature Vector Extraction, Face Recognition, Principal Component Analysis