Face Reconstruction Based on Multiscale Feature Fusion and 3D Animation Design

The development of the Internet of Things and 3D technology promotes the wide application of face models in 3D animation. However, because the expression is inconsistent with the facial muscle movement, the reconstruction results may be far from the real appearance in the process of reconstructing the face appearance. Therefore, this paper proposes a character expression simulation model under the framework of 3DS Max. According to the relationship between head bones and muscles, a facial muscle motion model was established. Then, the expression simulation design of the original three-dimensional animation character “yaya” was carried out under the framework of 3DS Max technology. The experimental results of “yaya” facial expression test showed that the face simulation model using this method not only has vivid and natural expression but also conforms to the law of facial muscle movement, which provides an important reference for the construction and application of 3D face model.

A Futuristic Approach for Stroke Rehabilitation Using Smart Gloves

Stroke is a serious, common, and assured as a global health issue across the globe. Stroke is one of most common cause of death and is a leading cause of impairment in adults. Despite all impressive progression and development in the treatment of stroke, without effective modes of care most stroke patients care will continue to rely on physiotherapy involvement. The purpose of this paper is to explain about a new and better device which helps patients affected by stroke who are not able to move their hands. To rehabilitate stroke survivors, the proposed prototype is designed such that it is a portable smart glove which helps users to regain their muscle memory by continuously contracting and releasing their muscles without the involvement of physiotherapist. This device/glove also consists of sensors that collect and send data to UI using ESP32. This UI is available for the doctors to see the statistics of glove usage and monitors the patient’s conditions. The Glove uses a soft robotics approach to replicate the human hand. The Glove initially aims to contract and release all the muscles in the hand in regular intervals of time. This muscle movement aims to build lost muscle memory.

Micro-expression recognition based on facial action learning with muscle movement constraints

As a spontaneous facial expression, micro-expression reveals the psychological responses of human beings. However, micro-expression recognition (MER) is highly susceptible to noise interference due to the short existing time and low-intensity of facial actions. Research on facial action coding systems explores the correlation between emotional states and facial actions, which provides more discriminative features. Therefore, based on the exploration of correlation information, the goal of our work is to propose a spatiotemporal network that is robust to low-intensity muscle movements for the MER task. Firstly, a multi-scale weighted module is proposed to encode the spatial global context, which is obtained by merging features of different resolutions preserved from the backbone network. Secondly, we propose a multi-task-based facial action learning module using the constraints of the correlation between muscle movement and micro-expressions to encode local action features. Besides, a clustering constraint term is introduced to restrict the feature distribution of similar actions to improve categories separability in feature space. Finally, the global context and local action features are stacked as high-quality spatial descriptions to predict micro-expressions by passing through the Convolutional Long Short-Term Memory (ConvLSTM) network. The proposed method is proved to outperform other mainstream methods through comparative experiments on the SMIC, CASME-I, and CASME-II datasets.

Nonfrontal Expression Recognition in the Wild Based on PRNet Frontalization and Muscle Feature Strengthening

Nonfrontal facial expression recognition in the wild is the key for artificial intelligence and human-computer interaction. However, it is easy to be disturbed when changing head pose. Therefore, this paper presents a face rebuilding method to solve this problem based on PRNet, which can build 3D frontal face for 2D head photo with any pose. However, expression is still difficult to be recognized, because facial features weakened after frontalization, which had been widely reported by previous studies. It can be proved that all muscle parameters in frontalization face are more weakened than those of real face, except muscle moving direction on each small area. Thus, this paper also designed muscle movement rebuilding and intensifying method, and through 3D face contours and Fréchet distance, muscular moving directions on each muscle area are extracted and muscle movement is strengthened following these moving directions to intensify the whole face expression. Through this way, nonfrontal facial expression can be recognized effectively.

A Case of Thyroid Eye Disease Revealed During Secondary Adrenal Insufficiency

Introduction: Thyroid eye disease (TED) or Graves’ orbitopathy (GO) is an autoimmune disease of the retro-orbital tissues. GO is mostly associated with hyperthyroidism in 90% of patients; however, it may coexist with hypothyroid conditions in 5% of cases. Clinical Case: A 56-year-old male with a past medical history of autoimmune diseases including hypothyroidism and Ulcerative Colitis on chronic steroid therapy presented to the emergency department with nausea, fatigue, weight loss, and muscle weakness. The patient stated that his glucocorticoids were abruptly discontinued a month prior to his current presentation. On examination, vitals were stable. The patient was somnolent with a depressed mood. He had bilateral periorbital edema and bilateral eyeball protrusion, left more pronounced than right. Extraocular muscle movement revealed a delay in the lateral movement of the left eye causing double vision on exam. He had no starring look or lid lag. The thyroid gland was normal in size and contour. Initial Laboratories revealed a white blood cell count of 6.7 K/mcL (4-10 K/mcL) with 18% eosinophil count (0-5%). Cortisol at 8 AM was 2.9 mcg/dL (4.3 -22.4 mcg/dl). The patient was managed for secondary adrenal insufficiency and restarted immediately on Prednisone. A review of a recent CT scan of the head revealed bilateral proptosis with no signs of compressing lesions. Further thyroid studies revealed TSH of 2.9 mcIU/mL (0.3-3.7 mcIU/mL), free T4 of 0.8 ng/dL (0.75-2.0 ng/dL), free T3 of 1.6 ng/dL (2.4-4.2 ng/dL), TPO antibodies <0.3 IU/mL (0.0-9.0 IU/mL) and TSH receptor antibodies 0.90 IU/L (reference range <1.75 IU/L). The patient was then diagnosed with Hypothyroid Grave’s ophthalmopathy with negative antibodies given the evidence of proptosis on CT and exam revealing extraocular muscle movement restriction causing diplopia. The patient had a unique presentation of TED with hypothyroidism and asymmetric ophthalmic signs that were only manifested after the patient discontinued the prednisone and therefore unmasking the underlying disorder. Fortunately, in June of 2020, the US Food and Drug Administration (FDA) approved Teprotumumab (an insulin-like growth factor 1 [IGF-1] receptor inhibitor) for the treatment of Graves’ orbitopathy based on the findings from two 24-week trials comparing teprotumumab with placebo in 171 patients with active, moderate-to-severe orbitopathy. (1) Our patient was started on Levothyroxine along with Prednisone and referred for ophthalmology evaluation for possible qualification for Teprotumumab treatment. Conclusion: Clinician awareness of the unusual presentations of TED would allow for early recognition and prevention of progression, especially with the recently approved treatment modality. References: (1) Teprotumumab for Thyroid-Associated Ophthalmopathy. Smith TJ Et al. N Engl J Med. 2017;376(18):1748.

Noninvasive Measurement of Tongue Pressure and Its Correlation with Swallowing and Respiration

Tongue pressure plays a critical role in the oral and pharyngeal stages of swallowing, contributing considerably to bolus formation and manipulation as well as to safe transporting of food from the mouth to the stomach. Smooth swallowing relies not only on effective coordination of respiration and pharynx motions but also on sufficient tongue pressure. Conventional methods of measuring tongue pressure involve attaching a pressure sheet to the hard palate to monitor the force exerted by the tongue tip against the hard palate. In this study, an air bulb was inserted in the anterior oral cavity to monitor the pressure exerted by the extrinsic and intrinsic muscles of the tongue. The air bulb was integrated into a noninvasive, multisensor approach to evaluate the correlation of the tongue pressure with other swallowing responses, such as respiratory nasal flow, submental muscle movement, and thyroid cartilage excursion. An autodetection program was implemented for the automatic identification of swallowing patterns and parameters from each sensor. The experimental results indicated that the proposed method is sensitive in measuring the tongue pressure, and the tongue pressure was found to have a strong positive correlation with the submental muscle movement during swallowing.

Mechanosensory input shapes Drosophila motor behavior through Patterned Spontaneous Network Activity

Neural activity sculpts circuit wiring in many animals. In vertebrates, patterned spontaneous network activity (PaSNA) generates sensory maps and establishes local circuits. However, it remains unclear how PaSNA might shape neuronal circuits and behavior in invertebrates. Previous work in the developing Drosophila embryo discovered spontaneous muscle activity that did not require synaptic transmission, and hence was myogenic, preceding PaSNA. These studies, however, monitored muscle movement, not neural activity, and were therefore unable to observe how myogenic activity might relate to subsequent neural network engagement. Here we use calcium imaging to directly record neural activity and characterize the emergence of PaSNA. We demonstrate that the spatiotemporal properties of PaSNA are highly stereotyped across embryos, arguing for genetic programming. Consistent with previous observations, we observe neural activity well before it becomes patterned, initially emerging during the myogenic stage. Remarkably, inhibition of mechanosensory input results in excessive PaSNA, demonstrating that muscle movement serves as a brake. Finally, using an optogenetic strategy to selectively disrupt mechanosensory inputs during PaSNA, followed by quantitative modeling of larval behavior, we demonstrate that mechanosensory modulation during development is required for proper larval foraging. This work thus provides a foundation for using the Drosophila embryo to study the role of PaSNA in circuit formation, provides mechanistic insight into how PaSNA is entrained by motor activity, and demonstrates that spontaneous network activity is essential for locomotor behavior. These studies argue that sensory feedback during the earliest stages of circuit formation can sculpt locomotor behaviors through innate motor learning.