Search Results (67)

This paper presents a dual-band antenna designed for integration into eyewear. The antenna is intended for a system supporting visually impaired individuals, where a wearable camera integrated into glasses transmits data to a remote receiver. To enhance system reliability within indoor environments, the proposed design supports both fifth-generation (5G) wireless communication and Wi-Fi networks. The compact antenna is specifically dimensioned for integration within eyeglass temples and operates in the 3.5 GHz and 5.8 GHz frequency bands. Prototype measurements, conducted using a human head phantom, validate the antenna’s performance. The results demonstrate good impedance matching across the desired frequency bands and a maximum gain of at least 4 dBi in both bands. Full article

This research addresses the optimization and deployment of convolutional neural networks for eyeglasses detection on low-power edge devices. Multiple convolutional neural network architectures were trained and evaluated using the FFHQ dataset, which contains annotated eyeglasses in the context of faces with diverse facial features and eyewear styles. Several post-training quantization techniques, including Float16, dynamic range, and full integer quantization, were applied to reduce model size and computational demand while preserving detection accuracy. The impact of model architecture and quantization methods on detection accuracy and inference latency was systematically evaluated. The optimized models were deployed and benchmarked on Raspberry Pi 5 and NVIDIA Jetson Orin Nano platforms. Experimental results show that full integer quantization reduces model size by up to 75% while maintaining competitive detection accuracy. Among the evaluated models, MobileNet architectures achieved the most favorable balance between inference speed and accuracy, demonstrating their suitability for real-time eyeglasses detection in resource-constrained environments. These findings enable efficient on-device eyeglasses detection, supporting applications such as virtual try-ons and IoT-based facial analysis systems. Full article

The eyeglass lens manufacturing industry has become increasingly vulnerable to supply chain risks due to overlapping global disruptions, including the COVID-19 pandemic, the Suez Canal blockage, the Russia–Ukraine conflict, Red Sea shipping insecurity, and recent U.S. import tariffs. These events have challenged inventory planning, supplier coordination, and cost control across the industry. This study aims to evaluate how five operational constructs—stock system, inventory optimization, standardized methodology, production capability, and logistics performance—influence inventory resilience during global crises. Using an empirical case study, data were collected from 215 supply chain professionals at a multinational lens manufacturer in Southeast Asia and analyzed via Structural Equation Modeling (SEM). The results show that inventory optimization (β = 0.93) is the most influential factor in mitigating supply–demand imbalances, followed by logistics performance and production capability. This study offers practical recommendations, including real-time demand tracking, modular production systems, and scalable logistics strategies, to enhance inventory resilience. These findings contribute to both theory and practice by providing a validated framework tailored to high-precision manufacturing under persistent global risk. Full article

Saliva is an important fluid related to the maintenance of oral and systemic health, and a decrease in saliva volume causes various adverse effects. Saliva volume should be increased to avoid the adverse effects caused by decreased saliva volume. One method to increase saliva volume is to use a wearable device daily. Wearable devices that increase saliva volume in daily life should have the following features: easy to put on and take off, automatic movement, and no need to put the device in the mouth. To the authors’ knowledge, no such device exists. Therefore, this study aims to design a wearable device that can increase saliva volume in daily life using stimulus. Several previous studies have shown that lemon odor, massage of the lower part of the jaw, and warming of the lower jaw can increase saliva volume. However, it is not known whether these three stimuli can increase saliva volume quickly and under any situation. Therefore, in this paper, we investigate suitable stimuli for increasing saliva volume under situations that may change the effect of the stimuli for the construction of a wearable device. First, we implemented a mask-type experimental wearable device that can provide odor, pressure, and thermal stimulus. Next, a questionnaire survey was administered to confirm the situations under which saliva volume decreases. The results of the questionnaire showed that saliva volume decreased after conversations, after exercise, and upon waking up. Therefore, we investigated which of the three stimuli increased saliva volume quickly under these three situations and the usual situation. The results show that an odor stimulus significantly increased saliva volume in all situations compared to other stimuli. Based on the experimental results, we propose an eyeglass-shaped device that can provide an odor stimulus. The odor stimulus of the proposed device also significantly increased saliva volume. Full article

Marfan syndrome (MFS) is a genetic disorder that affects the connective tissue in several systems, with ocular, cardiovascular, and skeletal system manifestations. Its ocular manifestations include ectopia lentis (EL), myopia, astigmatism, and corneal abnormalities. This review examines refractive alterations related to MFS such as EL, microspherophakia, lens coloboma, altered corneal biomechanics (flattening, thinning, and astigmatism), and myopia and their impact on visual acuity. The pathogenesis of these manifestations stems from mutations in the FBN1 gene (encoding fibrillin-1). Moreover, the current medical and surgical management strategies for MFS-related refractive errors, including optical correction (eyeglasses, contact lenses, etc.), and surgical interventions like lensectomy, intraocular lens (IOL) implantation (anterior chamber, posterior chamber, scleral-fixated, iris-fixated), and the use of capsular tension rings/segments are further discussed. Considering the likelihood of underdiagnosing and underestimating ocular involvement in MFS, this updated review highlights the critical need to identify and address these refractive issues to enhance the visual outcomes for those affected. Full article

This paper proposes a method for 3D reconstruction from Freehand Design Sketching (FDS) in architecture and industrial design. The implementation begins by extracting features from the FDS using the self-supervised learning model DINO, followed by the continuous Signed Distance Function (SDF) regression as an implicit representation through a Multi-Layer Perceptron network. Taking eyeglass frames as an example, the 2D contour and freehand sketch optimize the alignment by their geometrical similarity while exploiting symmetry to improve reconstruction accuracy. Experiments demonstrate that this method can effectively reconstruct high-quality 3D models of eyeglass frames from 2D freehand sketches, outperforming existing deep learning-based 3D reconstruction methods. This research offers practical information for understanding 3D modeling methodology for FDS, triggering multiple modes of design creativity and efficient scheme adjustments in industrial or architectural conceptual design. In conclusion, this novel approach integrates self-supervised learning and geometric optimization to achieve unprecedented fidelity in 3D reconstruction from FDS, setting a new benchmark for AI-driven design processes in industrial and architectural applications. Full article

This research presents a retrospective analysis of zero-shot object detectors in automating image labeling for eyeglasses detection. The increasing demand for high-quality annotations in object detection is being met by AI foundation models with open-vocabulary capabilities, reducing the need for labor-intensive manual labeling. There is a notable gap in systematic analyses of foundation models for specialized detection tasks, particularly within the domain of facial accessories. Six state-of-the-art models—Grounding DINO, Detic, OWLViT, OWLv2, YOLO World, and Florence-2—were evaluated across three datasets (FFHQ with custom annotations, CelebAMask-HQ, and Face Synthetics) to assess their effectiveness in zero-shot detection and labeling. Performance metrics, including Average Precision (AP), Average Recall (AR), and Intersection over Union (IoU), were used to benchmark foundation models. The results show that Detic achieved the highest performance scores (AP of 0.97 and AR of 0.98 on FFHQ, with IoU values reaching 0.97), making it highly suitable for automated annotation workflows. Grounding DINO and OWLv2 also showed potential, especially in high-recall scenarios. The results emphasize the importance of prompt engineering. Practical recommendations for using foundation models in specialized dataset annotation are provided. Full article

Facial analysis is an important area of research in computer vision and machine learning, with applications spanning security, healthcare, and user interaction systems. The data-centric AI approach emphasizes the importance of high-quality, diverse, and well-annotated datasets in driving advancements in this field. However, current facial datasets, such as Flickr-Faces-HQ (FFHQ), lack detailed annotations for detecting facial accessories, particularly eyeglasses. This work addresses this limitation by extending the FFHQ dataset with precise bounding box annotations for eyeglasses detection, enhancing its utility for data-centric AI applications. The extended dataset comprises 70,000 images, including over 16,000 images containing eyewear, and it exceeds the CelebAMask-HQ dataset in size and diversity. A semi-automated protocol was employed to efficiently generate accurate bounding box annotations, minimizing the demand for extensive manual labeling. This enriched dataset serves as a valuable resource for training and benchmarking eyewear detection models. Additionally, the baseline benchmark results for eyeglasses detection were presented using deep learning methods, including YOLOv8 and MobileNetV3. The evaluation, conducted through cross-dataset validation, demonstrated the robustness of models trained on the extended FFHQ dataset with their superior performances over existing alternative CelebAMask-HQ. The extended dataset, which has been made publicly available, is expected to support future research and development in eyewear detection, contributing to advancements in facial analysis and related fields. Full article

This paper presents a new approach to measuring eyelid movement using millimeter wave (mmW) radar technology. A two-step method is proposed, involving the observation of a small resolution cell corresponding to the monitored eye and the evaluation of the phase evolution over the measurement period. Simulations are conducted to support radar system optimization and data interpretation with a focus on detecting eyelid movement patterns and compensating for interference from other parts of the body. The feasibility of using this method with eyeglasses is also explored. The proposed technique’s advantages and limitations are discussed in comparison with existing measurement alternatives. The characteristics of eyelid dynamics, including blink frequency, regularity, duration, and velocity can be used to assess neurological conditions and driver drowsiness. Full article

Objectives. This study aimed to compare the audiological benefits of a non-implantable wearable option for a bone conduction (BC) implant mounted on an arch (SoundArc) to those of traditional BC hearing aids (HAs) mounted on eyeglasses (BCHAs) in patients with moderate to severe conductive or mixed hearing loss. Methods: A preliminary cross-sectional observational prospective cohort study was conducted in the Tertiary Audiological Department, University Hospital. Fourteen adults with conductive or mixed hearing loss (PTA at 0.5-1-2-4 KHz = 67 ± 15 dB HL) who had been wearing conventional BCHAs mounted on eyeglasses for at least 3 years and had declined surgical implantation of a bone conduction hearing implant (BCHI) were included in the study. Unaided and aided pure-tone air conduction (AC) and bone conduction (BC) thresholds, as well as speech tests in quiet and noise, were recorded at baseline and in two different settings: with a BCHI mounted on SoundArc^® and with their own BCHAs mounted on eyeglasses using two couplers. Participants completed questionnaires in both conditions, including the International Inventory for Hearing Aids (IOI-HA), the Hearing Handicap Inventory for Adults/Elderly (HHIA/E), the Speech, Spatial, and Qualities of Hearing Scale (SSQ), a 10-point visual analog scale (VAS), and the Fatigue Impact Scale (FIS). Results: A significant functional gain was observed in both settings (p = 0.0001). Better speech perception in quiet and noise was observed with SoundArc compared to conventional BCHAs on eyeglasses (improvements in word repetition scores in noise: +19.3 at SNR +10 dB, p = 0.002; +12.1 at SNR 0 dB, p = 0.006; and +11.4 at SNR −10 dB, p = 0.002). No significant differences were found in IOI-HA, FIS, and HHIA/E scores. However, significantly better SSQ scores were reported for SoundArc in all domains (p = 0.0038). Conclusions: Although patients were accustomed to using BCHAs mounted on eyeglasses, the bone conduction wearable option of the BCHI (SoundArc) proved to be a viable alternative for adult patients with conductive or mixed hearing loss who are unable or unwilling to undergo BCHI surgery. Full article

Massively carbon-supersaturated (MCSed) tool steel dies were developed to make galling-free forging products from titanium bar feedstocks in dry conditions without lubricating oils. Two types of tool steel dies were used, SKD11 and ACD56, following the Japanese Industrial Standard (JIS). The plasma-immersion carburizing process was employed to induce massive carbon supersaturation in two kinds of tool steel dies at 673 K for 14.4 ks. A pure titanium bar was upset in a single stroke up to the reduction of thickness of 70% using the MCSed SKD11 die. Very few bulging displacements of the upset bar proved that μ = 0.05 on the contact surface of the MCSed SKD11 die to pure titanium work. Two continuous forging experiments were performed to demonstrate that an in situ lubrication mechanism played a role to prevent the contact surface from galling to titanium works in both laboratory- and industry-scaled forging processes. After precise microstructure analyses of the contact surface, the free-carbon film formed in situ acted as a lubricating tribofilm to reduce friction and adhesive wear in continuous forging processes. The MCSed ACD56 dies were also used to describe the galling-free forging behavior of manufacturing eyeglass frames and to evaluate the surface quality of the finished temples. The applied load was reduced by 30% when using the MCSed ACD56 dies. The average surface roughness of the forged product was also greatly reduced, from 4.12 μm to 0.99 μm, together with a reduction in roughness deviations. High qualification of forged products was preserved together with die life prolongation even in dry manufacturing conditions of the titanium and titanium alloys. Full article

Purpose: This study aims to investigate the disposal practices of optical materials in Portuguese Optical Centers. Methods: This study, conducted in the Portuguese Optical Centers across 18 districts and 308 municipalities, divided the country into 4 regions for analysis. Utilizing Google Forms^®, a survey targeting Optical Center managers and related professionals was disseminated via email from February to May 2023, comprising 30 questions across 6 sections, including optical and contact lenses, maintenance solutions, eyeglass frames, and recycling participation. Data analysis employed IBM SPSS^® Statistics v.27, using non-parametric tests for variable distribution. Ethical standards and privacy policies were strictly observed throughout the research process. Results: Findings indicated that there were significant differences in the final treatment of organic and mineral lenses. Organic lenses were placed in the yellow recycling bin (22.2%), while mineral lenses were placed in the green recycling bin (37.9%). In the case of contact lenses, regardless of the type (RGP, scleral lenses, conventional hydrogels, and silicone hydrogel lenses), the majority (>50%) were disposed of in general trash. Regarding eyeglass frames, there were no significant differences between mass and metal frames, mostly being discard in general waste (~30.0%). Conclusion: Approximately half of the surveyed Portuguese Optical Centers were not actively involved in recycling. This represents a missed opportunity for optometrists to play a role in enhancing recycling rates through patient education. Full article

Metabolic syndrome poses a significant health challenge worldwide, prompting the need for comprehensive strategies integrating physical activity monitoring and energy expenditure. Wearable sensor devices have been used both for energy intake and energy expenditure (EE) estimation. Traditionally, sensors are attached to the hip or wrist. The primary aim of this research is to investigate the use of an eyeglass-mounted wearable energy intake sensor (Automatic Ingestion Monitor v2, AIM-2) for simultaneous recognition of physical activity (PAR) and estimation of steady-state EE as compared to a traditional hip-worn device. Study data were collected from six participants performing six structured activities, with the reference EE measured using indirect calorimetry (COSMED K5) and reported as metabolic equivalents of tasks (METs). Next, a novel deep convolutional neural network-based multitasking model (Multitasking-CNN) was developed for PAR and EE estimation. The Multitasking-CNN was trained with a two-step progressive training approach for higher accuracy, where in the first step the model for PAR was trained, and in the second step the model was fine-tuned for EE estimation. Finally, the performance of Multitasking-CNN on AIM-2 attached to eyeglasses was compared to the ActiGraph GT9X (AG) attached to the right hip. On the AIM-2 data, Multitasking-CNN achieved a maximum of 95% testing accuracy of PAR, a minimum of 0.59 METs mean square error (MSE), and 11% mean absolute percentage error (MAPE) in EE estimation. Conversely, on AG data, the Multitasking-CNN model achieved a maximum of 82% testing accuracy in PAR, a minimum of 0.73 METs MSE, and 13% MAPE in EE estimation. These results suggest the feasibility of using an eyeglass-mounted sensor for both PAR and EE estimation. Full article

We present the development study of a reliable and low-power actuator for microfluidics-based active glasses. The adaptive part of the lens implements two liquids of a specific refractive index separated by a thin membrane, the modification of their relative volumes allowing adaptive optical power corrections. The proposed actuator is connected to an adaptive lens by microchannels since it is intended to be installed in the temple of the glasses. The actuation is based on the electrostatic displacement of a thin film, which changes the relative volumes of two cavities filled with these liquids. The metalized film is placed slack with an “S-shape” between two electrodes biased with the actuation voltage. Very compact actuator prototypes have been developed and characterized. Power corrections ranging from +0D to +3D can be achieved via liquid volume displacement as low as 120 µL and with a power consumption of a few mW. The prototypes show good reliability without any significant change in their operation after more than 1 million actuations. For RD purposes, we have replaced some electrodes with transparent windows. With this setup, we show experimental results on the interplay between the performances and the film folding inside the actuator. Full article

Falls and frailty status are often associated with a decline in physical capacity and multifactorial assessment is highly recommended. Based on the functional and biomechanical parameters measured during clinical tests with an accelerometer integrated into smart eyeglasses, the purpose was to characterize a population of older adults through an unsupervised analysis into different physical performance groups. A total of 84 participants (25 men and 59 women) over the age of sixty-five (age: 74.17 ± 5.80 years; height: 165.70 ± 8.22 cm; body mass: 68.93 ± 13.55 kg) performed a 30 s Sit-to-Stand test, a six-minute walking test (6MWT), and a 3 m Timed Up and Go (TUG) test. The acceleration data measured from the eyeglasses were processed to obtain six parameters: the number of Sit-to-Stands, the maximal vertical acceleration values during Sit-to-Stand movements, step duration and length, and the duration of the TUG test. The total walking distance covered during the 6MWT was also retained. After supervised analyses comparison (i.e., ANOVAs), only one of the parameters (i.e., step length) differed between faller groups and no parameters differed between frail and pre-frail participants. In contrast, unsupervised analysis (i.e., clustering algorithm based on K-means) categorized the population into three distinct physical performance groups (i.e., low, intermediate, and high). All the measured parameters discriminated the low- and high-performance groups. Four of the measured parameters differentiated the three groups. In addition, the low-performance group had a higher proportion of frail participants. These results are promising for monitoring activities in older adults to prevent the decline of physical capacities. Full article