Hand Segmentation Research Articles

Interpreting the Projected Frontal Area in Front Crawl: Determining the Projected Frontal Area of Each Body Segment.

This study aimed to provide evidence for the interpretation of the projected frontal area (PFA) during front crawl. To achieve this goal, we developed a method for calculating the PFA of each body segment using digital human technology and compared the pressure drag under two calculation conditions: a combination of the PFA with and without accounting for the horizontal velocity of each body segment. Twelve competitive male swimmers performed a 15-meter front crawl at 1.20 m·s-1. The three-dimensional positions of the reflective markers attached to the swimmer's body were recorded using an underwater motion-capture system. Based on the body shape of each swimmer obtained from the photogenic body scanner, individual digital human body models were created with the color of the model's vertices divided into eight body segments. The time series of the volumetric swimming motion was reconstructed using inverse kinematics. The PFA of each body segment was then calculated by the automatic processing of a series of parallel frontal images. The pressure drag index, defined as the value excluding the drag coefficient while simultaneously considering the PFA and the horizontal velocity, was calculated under two conditions: the static condition (accounting for only the PFA of each body segment) and the dynamic condition (accounting for the PFA and horizontal velocity of each body segment). Notably, the pressure drag index was higher under the static condition than under the dynamic condition for the humerus, ulna, and hand segments (p < 0.001). The results obtained using our methodology indicate that the PFA of the upper limb segments overestimates their contribution to pressure drag during front crawl under the static condition.

Research on Mixed Reality Hand Interaction Technology in Flight Simulation Teaching

Abstract The integration of mixed reality simulation training in institutional education and teaching processes can yield significant quality benefits. Non-wearable interactive methods represent a more natural form of hand interaction within flight cockpits, covering various emerging fields such as mixed reality, computer vision, and human-computer interaction. This paper is guided by a “human-centered” approach to natural human-computer interaction and proposes a virtual hand mixed reality interaction scheme based on hand natural feature points. This study introduces a hand detection, segmentation, and recognition algorithm based on skin colour and key hand feature points. Initially, the algorithm uses the Otsu adaptive threshold algorithm in the YCbCr space for skin colour detection to accommodate varying image brightness levels. Subsequently, it employs a hand Keypoint model for rapid hand detection within skin-like areas while excluding interference from other regions. During the process of hand tracking, optimization prediction is performed using the particle filter algorithm combined with the artificial fish swarm algorithm to achieve tracking accuracy within six pixels in both horizontal and vertical directions. Gesture recognition involves extracting Fourier descriptive contour features of the hand bone structure through identification of feature points. Furthermore, this study combines the optimization capabilities of the artificial fish swarm algorithm to enhance support vector machine model parameter optimization for improved recognition rates. Testing involved 800 processed images as part of a test set for gesture recognition; only five commonly used gestures within flight cockpits were recognized and classified with an accuracy rate reaching up to 98%. Finally, this research presents virtual representations of common operational gestures including natural hand states, control stick manipulation, and throttle handling positions, button activations, and rotational movements via head-mounted displays or screens. The proposed mixed reality-based hand gesture interaction system addresses challenges related to complex background interference during hand detection in cockpit environments as well as issues arising from lighting disturbances. Additionally it resolves problems associated with insufficient particles leading to tracking failures while significantly enhancing registration effects during tracking processes. Moreover it mitigates issues related to Fourier descriptive features being influenced by background variations or changes in pose along with limitations pertaining to expressing singular forms of gestures thereby improving overall classification accuracy.

Temporal localization of upper extremity bilateral synergistic coordination using wearable accelerometers.

The human upper extremity is characterized by inherent motor abundance, allowing a diverse array of tasks with agility and adaptability. Upper extremity functional limitations are a common sequela to Stroke, resulting in pronounced motor and sensory impairments in the contralesional arm. While many therapeutic interventions focus on rehabilitating the weaker arm, it is increasingly evident that it is necessary to consider bimanual coordination and motor control. Participants were recruited to two groups differing in age (Group 1 (n=10): 23.4 ±2.9 years, Group 2 (n=10): 55.9 ±10.6 years) for an exploratory study on the use of accelerometry to quantify bilateral coordination. Three tasks featuring coordinated reaching were selected to investigate the acceleration of the upper arm, forearm, and hand during activities of daily living (ADLs). Subjects were equipped with acceleration and inclination sensors on each upper arm, each forearm, and each hand. Data was segmented in MATLAB to assess inter-limb and intra-limb coordination. Inter-limb coordination was indicated through dissimilarity indices and temporal locations of congruous movement between upper arm, forearm, or hand segments of the right and left limbs. Intra-limb coordination was likewise assessed between upper arm-forearm, upper arm-hand, and forearm-hand segment pairs of the dominant limb. Acceleration data revealed task-specific movement features during the three distinct tasks. Groups demonstrated diminished similarity as task complexity increased. Groups differed significantly in the hand segments during the buttoning task, with Group 1 showing no coordination in the hand segments during buttoning, and strong coordination in reaching each button with the upper arm and forearm guiding extension. Group 2's dissimilarity scores and percentages of similarity indicated longer periods of inter-limb coordination, particularly towards movement completion. Group 1's dissimilarity scores and percentages of similarity indicated longer periods of intra-limb coordination, particularly in the coordination of the upper arm and forearm segments. The Expanding Procrustes methodology can be applied to compute objective coordination scores using accessible and highly accurate wearable acceleration sensors. The findings of task duration, angular velocity, and peak roll angle are supported by previous studies finding older individuals to present with slower movements, reduced movement stability, and a reduction of laterality between the limbs. The theory of a shift towards ambidexterity with age is supported by the finding of greater inter-limb coordination in the group of subjects above the age of thirty-five. The group below the age of thirty was found to demonstrate longer periods of intra-limb coordination, with upper arm and forearm coordination emerging as a possible explanation for the demonstrated greater stability.

Hand Gestures Recognition Model Using Adaptive Feature Extraction with Attention-Based Hybrid Deep Learning via Optimization Strategy

Research on continuous hand gesture recognition is motivated by applications of deaf people to provide effective communication between one another. Numerous techniques are adapted for effectively identifying the hand gesture. Moreover, the collection of data becomes a challenging task in the existing models. In some instances, hand gesture in low-resolution images becomes a complicated task. In this research work, a deep learning-based hand gesture detection model is designed using hand data points to uncover patterns that are used to convey information. Initially, hand gesture images are obtained from public sources. The collected inputs are preprocessed through Contrast-Limited Adaptive Histogram Equalization and filtering to eliminate the unnecessary blurs in the images. The preprocessed images undergo hand segmentation using four methods color space transformation, skin color detection, active contour, and morphological operation. The segmented image is subjected to data point feature extraction, where the Adaptive Weighted Scale-Invariant Feature Transform is utilized for further enhancement. The hand data point-extracted features are given to the recognition of hand gestures with the support of an attention-based hybrid network, where the Attention-based Hybrid 1D Convolutional Neural Network with Recurrent Neural Network recognizes the hand gestures from the hand data points. In the hybridization network, the values are optimized with the help of the investigated Adaptive Dandelion White Shark Optimizer to enhance recognition effectiveness. The test results are validated with the existing hand gesture recognition models using diverse evaluation metrics. The findings of the recommended method show 97% and 99% in terms of accuracy and NPV. Thus, the developed model is validated to outperform significant performance rather than the existing models.

A Dataset for Kinship Estimation from Image of Hand Using Machine Learning

Kinship (Familial relationships) detection is crucial in many fields and has applications in biometric security, adoption, forensic investigations, and more. It is also essential during wars and natural disasters like earthquakes since it may aid in reunion, missing person searches, establishing emergency contacts, and providing psychological support. The most common method of determining kinship is DNA analysis which is highly accurate. Another approach, which is noninvasive, uses facial photos with computer vision and machine learning algorithms for kinship estimation. Each part of the Human -body has its own embedded information that can be extracted and adopted for identification, verification, or classification of that person. Kinship recognition is based on finding traits that are shared by every family. We investigate the use of hand geometry for kinship detection, which is a new approach. Because of the available hand image Datasets do not contain kinship ground truth; therefore, we created our own dataset. This paper describes the tools, methodology, and details of the collected MKH, which stands for the Mosul Kinship Hand, images dataset. The images of MKH dataset were collected using a mobile phone camera with a suitable setup and consisted of 648 images for 81 individuals from 14 families (8 hand situations per person). This paper also presents the use of this dataset in kinship prediction using machine learning. Google MdiaPipe was used for hand detection, segmentation, and geometrical key points finding. Handcraft feature extraction was used to extract 43 distinctive geometrical features from each image. A neural network classifier was designed and trained to predict kinship, yielding about 93% prediction accuracy. The results of this novel approach demonstrated that the hand possesses biometric characteristics that may be used to establish kinship, and that the suggested method is a promising way as a kinship indicator.

Hand Segmentation With Dense Dilated U-Net and Structurally Incoherent Nonnegative Matrix Factorization-Based Gesture Recognition

Hand Segmentation With Dense Dilated U-Net and Structurally Incoherent Nonnegative Matrix Factorization-Based Gesture Recognition

A Review on Sign Language Recognition and Learning System

This paper presents innovative approaches to various aspects of sign language recognition and learning, catering to the diverse needs within this field. It introduces a system utilizing 2D image sampling and concatenation, trained with convolutional neural networks, achieving accurate and robust sign recognition even with low-cost cameras. Another system, SignQuiz, offers a cost-effective web-based solution for learning finger-spelled signs in Indian Sign Language (ISL), outperforming traditional printed mediums. Additionally, a dynamic hand gesture recognition system employing deep learning architectures demonstrates superior performance over existing methods, addressing challenges such as hand segmentation and sequence modeling. Furthermore, an efficient deep convolutional neural network approach for hand gesture recognition, including transfer learning, achieves high recognition rates across various datasets. Finally, a robust model for static sign recognition in ISL, utilizing CNNs and evaluating on a diverse dataset, attains exceptional accuracy and outperforms previous works. These contributions collectively advance the field of sign language recognition and learning, offering solutions that are accurate, cost-effective, and efficient, thereby facilitating better communication and interaction for the hearing-impaired community. Key Words: CNN, Sign language recognition, Hand gesture recognition, Machine learning, Transfer Learning, SVM.

Sign Language Recognition by Image Processing

A prototype sign language interpreter that can converse in American Sign Language (ASL) is presented in this study. The visual stimulation of sign language aids in the development of speech and language. It promotes social contact, fosters the development of cognitive structures, and lessens harmful social behaviors. Early exposure to sign language supports language development in academic, social, and emotional domains. Building a user-hand gesture-only human-computer interface (HCI) is the foundation of the dependable paradigm. Using Python and OpenCV, hand gesture recognition is built using the theories of hand segmentation and the hand detection system. The training photos are labeled with different names based on what is in the database. A binary feature vector is created from each image. Convolutional neural networks (CNNs) and cameras are used to capture images from hand sign videos in real time, which are then used to carry out the feature extraction process. The algorithm generates output based on the projected maximum similarity between these features and the features of database photographs. With the aid of an application, this model provides adequate accuracy even in the absence of a constant or monochromatic background. The person's hand movements are captured on video with the camera; the video is subsequently processed and translated into text. The user hears the speech that has been transformed from the output. The suggested system recognizes letters, numbers, and certain common words in sign language. Raw photos and videos are transformed into corresponding text that can be read and comprehended by using image processing algorithms and neural networks to map the gesture to the right text in the training data. When paired with a sizable source database, this protocol will surely be highly beneficial for closing the communication gap between people who can talk and hear and those who cannot.

A comparison of minimum segment models for the estimation of centre of mass position and velocity for slip recovery during a bathtub transfer task

BackgroundExploring the use of minimum marker sets is important for balancing the technical quality of motion capture with challenging data collection environments and protocols. While minimum marker sets have been demonstrated to be appropriate for evaluation of some motion patterns, there is limited evidence to support model choices for abrupt, asymmetrical, non-cyclic motion such as balance disturbance during a bathtub exit task. Research questionHow effective are six models of reduced complexity for the estimation of centre of mass (COM) displacement and velocity, relative to a full-body model. MethodsEight participants completed a bathtub exit task. Participants received a balance perturbation as they crossed the bathtub rim, stepping from a soapy wet bathtub to a dry floor. Six reduced models were developed from the full, 72-marker, 12 segment 3D kinematic data set. Peak displacement and velocity of the body COM, and RMSE (relative to the full-body model) for displacement and velocity of the body COM were determined for each model. ResultsMain effects were observed for peak right, left, anterior, posterior, upwards and downwards motion, and peak left, anterior, posterior, upwards and downwards velocity. Time-varying (RMSE) was smaller for models including the thighs than models not containing the thighs. In contrast, inclusion of upper arm, forearm, and hand segments did not improve model performance. The model containing the sacrum marker only consistently performed the worst across peak and RMSE metrics. SignificanceFindings suggest a simplified centre of mass model may adequately capture abrupt, asymmetrical, non-cyclic tasks, such as balance disturbance recovery during obstacle crossing. A reduced kinematic model should include the thighs, trunk and pelvis segments, although models that are more complex are recommended, depending on the metrics of interest.

Analysis of glove local microclimate properties for various glove types and fits using 3D scanning method

Due to their geometry and thermal physiology, hands are most vulnerable to cold weather injuries and loss of dexterity. Gloves are the most common for hand protection during exposure to extreme thermal and hazardous environments. Although glove microclimate properties such as area factor, air gap thickness, and contact area play a significant role in thermal protection, identifying local (at individual hand segments) glove microclimate properties is still a research gap. For the first time, the glove-microclimate properties for 16 hand segments at high spatial resolution were analyzed by employing state-of-the-art hand-held 3D scanner and post-processing techniques for different glove types. Our results clearly indicate that the glove area factor for distal phalanges is significantly higher (by 49.8 %) than that for other hand segments, which increases the heat transfer from distal phalanges. In contrast, average air gap thickness was relatively uniform across all hand segments. The glove type had a pronounced effect on glove microclimate properties, e.g., bulky and heavy cold weather protective gloves had a larger average air gap thickness and glove area factor. Regression models are also developed to estimate the glove microclimate properties from simple measurement (i.e., ease allowance). Overall, this study provides essential information for the design and development of protective gloves that can help improve safety, comfort, and dexterity. Methods and mathematical models developed in this study also contribute to facilitating extremity (e.g., hand) focused thermoregulation modeling, hazard simulation, injury prediction, ergonomic design, optimum performance (dexterity and tactility) along with thermal protection.

Hand bone extraction and segmentation based on a convolutional neural network

Automatic segmentation of hand bone X-ray images is an important process in skeletal bone age assessment (BAA). The segmentation process is extremely difficult and complicated due to the complex structure and tiny size of hand bone features, which may lead to inaccurate feature localization and incomplete segmentation. A two-stage segmentation method is proposed in this paper. In the first stage, the OSA-YOLOv5 network is used to extract hand bones, and in the second stage, GRU-UNet is used to separate extracted hand bones. The hand bone X-ray dataset consists of a mixed dataset of 1000 left-hand bone X-ray images of adolescents from licenced local hospitals and 1000 left-hand bone X-ray images from the RSNA public dataset. The training efficiency of the OSA-YOLOv5 network is 28 % higher than that of the traditional network, and the proposed network exhibits with a higher extraction accuracy. The segmentation accuracy of the GRU-Unet segmentation model 14.70 % higher than that if Unet. The spatial sequence features with spatial rules are found to have a positive correlation in GRU-Unet. Experimental results show that the proposed segmentation method has good generalization and robustness, which provides a good foundation for subsequent BAA.

Fine semantic segmentation of hands for human functional pattern recognition in IADLs using deep learning

AbstractBackgroundAlzheimer’s Disease (AD) is an irreversible degenerative brain disease and the most common cause of dementia, in the elderly population (age 65 and above) although people younger may develop the disease (Clemmensen, 2020). AD is characterized by impairment in behavior and cognition which eventually obstruct the Instrumental Activities of Daily Living (IADL) (Kumar, 2022). Researchers have predicted functional capacity by assessing IADL as they are strongly associated with cognitive impairment. With the availability of big data and public repositories of multimedia data such as images and videos, artificial intelligence algorithms have been used in classifying and making informed decisions that could help in disease prediction and monitoring. In the context of early diagnosis of Alzheimer, researchers have worked with machine learning techniques applied to neuroimaging for AD classification (Lama, 2021). Researchers and practitioners often use Activity of Daily Living to monitor independent‐living senior citizens’ self‐care ability, wellness status, and disease progression (Zhu, 2021). Automating the assessments of IADL will ease the evaluation of functional and cognitive function and strengthen the prediction of AD.MethodOur work approaches the timely detection and diagnosis of AD by exploring the deficiency in hand dexterity and visuospatial skills while performing IADL using egocentric videos. Therefore, in this work, we propose a fine semantic segmentation of hands, optimizing the predictions at the level of the relationship between pixels in a deep learning method. We trained the optimized RefineNet‐Pix convolutional neural network, obtaining a higher accuracy in the segmentation of semantic maps of hands.ResultsWith the optimization of RefineNet‐Pix we obtained an accuracy higher than 87.9% (Urooj, 2018) in the semantic segmentation of hands. By integrating the RefineNet‐Pix results to the base model for human functional pattern recognition, we obtain an accuracy higher than 74% with respect to the base model (Yemisi, 2022).ConclusionThe optimized RefineNet‐Pix model segments pixel‐wise the hand regions in egocentric videos, providing hand motion information that can be used to classify impairment based on human functional patterns. Optimization of these models is a way forward in building a technological device for the support of Alzheimer’s diagnosis.

Fine semantic segmentation of hands for human functional pattern recognition in IADLs using deep learning

AbstractBackgroundAlzheimer’s Disease (AD) is an irreversible degenerative brain disease and the most common cause of dementia, in the elderly population (age 65 and above) although people younger may develop the disease (Clemmensen, 2020). AD is characterized by impairment in behavior and cognition which eventually obstruct the Instrumental Activities of Daily Living (IADL) (Kumar, 2022). Researchers have predicted functional capacity by assessing IADL as they are strongly associated with cognitive impairment. With the availability of big data and public repositories of multimedia data such as images and videos, artificial intelligence algorithms have been used in classifying and making informed decisions that could help in disease prediction and monitoring. In the context of early diagnosis of Alzheimer, researchers have worked with machine learning techniques applied to neuroimaging for AD classification (Lama, 2021). Researchers and practitioners often use Activity of Daily Living to monitor independent‐living senior citizens’ self‐care ability, wellness status, and disease progression (Zhu, 2021). Automating the assessments of IADL will ease the evaluation of functional and cognitive function and strengthen the prediction of AD.MethodOur work approaches the timely detection and diagnosis of AD by exploring the deficiency in hand dexterity and visuospatial skills while performing IADL using egocentric videos. Therefore, in this work, we propose a fine semantic segmentation of hands, optimizing the predictions at the level of the relationship between pixels in a deep learning method. We trained the optimized RefineNet‐Pix convolutional neural network, obtaining a higher accuracy in the segmentation of semantic maps of hands.ResultWith the optimization of RefineNet‐Pix we obtained an accuracy higher than 87.9% (Urooj, 2018) in the semantic segmentation of hands. By integrating the RefineNet‐Pix results to the base model for human functional pattern recognition, we obtain an accuracy higher than 74% with respect to the base model (Yemisi, 2022).ConclusionThe optimized RefineNet‐Pix model segments pixel‐wise the hand regions in egocentric videos, providing hand motion information that can be used to classify impairment based on human functional patterns. Optimization of these models is a way forward in building a technological device for the support of Alzheimer’s diagnosis.

Efficient hand segmentation for rehabilitation tasks using a convolution neural network with attention

Efficient hand segmentation for rehabilitation tasks using a convolution neural network with attention

Use of adult anthropometric tables to estimate children body segment inertial parameters

ABSTRACT There is a lack of knowledge in the literature concerning Body Segment Inertial Parameters (BSIP) for children aged 4 to 15 years. Nevertheless, these data are fundamental for studying the dynamics of the healthy and pathological musculoskeletal system. One common method for obtaining BSIP is to use regression equations derived from anthropometric tables. However, the majority of these equations are based on adult data. In this study, we compared certain BSIP (segment mass, center of mass position, and transverse moment of inertia) derived from adult anthropometric tables with the corresponding BSIP extracted from a pediatric anthropometric table. The goal of this study was to determine the accuracy of using adult anthropometric tables to calculate pediatric BSIP. For this comparison, we assessed the proximity of several adult anthropometric tables to a pediatric anthropometric table by Jensen (1986) for each BSIP. Our results revealed differences between the BSIP obtained using adult tables and the BSIP obtained with the pediatric table used as a reference. When considering all the tables, the mean relative difference was 12% for segment mass, 12% for center of mass position, and 25% for transverse moment of inertia. Notably, the greatest relative differences were observed for the head, hand, and foot segments. Additionally, the relative difference in female data was higher compared to males. This result could be attributed to the predominant use of male subjects in the adult tables considered in this study. Finally, the adult anthropometric tables by Dumas and Wojtsuch (2018) and De Leva (1996) provided results that were closer in comparison to Jensen (1986).

Hand gesture recognition via deep data optimization and 3D reconstruction

Hand gesture recognition (HGR) are the most significant tasks for communicating with the real-world environment. Recently, gesture recognition has been extensively utilized in diverse domains, including but not limited to virtual reality, augmented reality, health diagnosis, and robot interaction. On the other hand, accurate techniques typically utilize various modalities generated from RGB input sequences, such as optical flow which acquires the motion data in the images and videos. However, this approach impacts real-time performance due to its demand of substantial computational resources. This study aims to introduce a robust and effective approach to hand gesture recognition. We utilize two publicly available benchmark datasets. Initially, we performed preprocessing steps, including denoising, foreground extraction, and hand detection via associated component techniques. Next, hand segmentation is done to detect landmarks. Further, we utilized three multi-fused features, including geometric features, 3D point modeling and reconstruction, and angular point features. Finally, grey wolf optimization served useful features of artificial neural networks for hand gesture recognition. The experimental results have shown that the proposed HGR achieved significant recognition of 89.92% and 89.76% over IPN hand and Jester datasets, respectively.

Comparison of machine learning models for MRI image-based brain tumor classification and segmentation

Brain tumors have a high-risk factor and are extremely harmful to the human body. With the development of science and technology in recent years, automatic segmentation has become popular in medical diagnosis because it provides higher accuracy than traditional hand segmentation. At present, more and more people start to study and improve it. Due to the non-invasive nature of MRI, MR images are often used to segment and classify brain tumors. However, limited by the inaccuracy and inoperability of manual segmentation, it is very necessary to have a complete and comprehensive automatic brain tumor segmentation and classification algorithm technology. This article discusses the benefits, drawbacks, and areas of application of several traditional algorithms as well as more modern, improved, and more advanced algorithms. Segmentation methods and classification methods can be used to classify these techniques. Convolutional neural networks (CNN), Support vector machines, and Transformers are examples of classification methods. Random forests, decision trees, and improved U-Net algorithms are examples of segmentation methods. To discuss the capability of classification and segmentation, there are three sections in the area used for segmenting brain tumors with three types, including Tumor Core, Enhance Tumor, and Whole Tumor, which could be abbreviated as TC, ET, and WT. Through the comparative analysis of these methods, useful insights for future research are provided.

A novel laser melting sampler for discrete, sub-centimeter depth-resolved analyses of stable water isotopes in ice cores

Abstract We developed a novel laser melting sampler (LMS) for ice cores to measure the stable water isotope ratios (δ18O and δD) as temperature proxies at sub-centimeter depth resolutions. In this LMS system, a 2 mm diameter movable evacuation nozzle holds an optical fiber through which a laser beam irradiates the ice core. The movable nozzle intrudes into the ice core, the laser radiation meanwhile melts the ice cylindrically, and the meltwater is pumped away simultaneously through the same nozzle and transferred to a vial for analysis. To avoid isotopic fractionation of the ice through vaporization, the laser power is adjusted to ensure that the temperature of the meltwater is always kept well below its boiling point. A segment of a Dome Fuji shallow ice core (Antarctica), using the LMS, was then demonstrated to have been discretely sampled with a depth resolution as small as 3 mm: subsequent analysis of δ18O, δD, and deuterium excess (d) was consistent with results obtained by hand segmentation within measurement uncertainties. With system software to control sampling resolution, the LMS will enable us to identify temperature variations that may be detectable only at sub-centimeter resolutions in ice cores.

Lightweight real-time hand segmentation leveraging MediaPipe landmark detection

Real-time hand segmentation is a key process in applications that require human–computer interaction, such as gesture recognition or augmented reality systems. However, the infinite shapes and orientations that hands can adopt, their variability in skin pigmentation and the self-occlusions that continuously appear in images make hand segmentation a truly complex problem, especially with uncontrolled lighting conditions and backgrounds. The development of robust, real-time hand segmentation algorithms is essential to achieve immersive augmented reality and mixed reality experiences by correctly interpreting collisions and occlusions. In this paper, we present a simple but powerful algorithm based on the MediaPipe Hands solution, a highly optimized neural network. The algorithm processes the landmarks provided by MediaPipe using morphological and logical operators to obtain the masks that allow dynamic updating of the skin color model. Different experiments were carried out comparing the influence of the color space on skin segmentation, with the CIELab color space chosen as the best option. An average intersection over union of 0.869 was achieved on the demanding Ego2Hands dataset running at 90 frames per second on a conventional computer without any hardware acceleration. Finally, the proposed segmentation procedure was implemented in an augmented reality application to add hand occlusion for improved user immersion. An open-source implementation of the algorithm is publicly available at https://github.com/itap-robotica-medica/lightweight-hand-segmentation.

Design of a Custom Force Fixture Fitting Miniature Load Cells for Individual Finger Force Measurement

This research aims to address limitations of current hand grip measurement techniques by designing, building, and testing a more robust cylindrical dynamometer capable of measuring orthogonal force components while accounting for forces exerted by individual finger segments. The novel grip fixture consists of three static beams instrumented with strain gauges measuring orthogonal forces and eight attached miniature compensating load cells accounting for force contribution from finger segments. Following device fabrication and calibration, data was validated in a pilot study (n=6) where grip strengths were compared between the custom fixture and a Jamar dynamometer. Data suggests the custom dynamometer provides hand grip strength measurement comparable to that produced on a traditional dynamometer (p &gt; 0.05). Future research studies using a similar device can guide therapy for patients with impaired hand strength by providing clinical professionals with a more complete profile of the forces exerted by hand segments.