Multimodal Smart Glove for Sign Language Recognition Using Deep Learning

Anh Thu Nguyen Ngoc; Manh Duong Phung; Tam Phong Truong; Thai Anh Nguyen Duong; Vu Linh Nguyen

REVIEW 4 major objections 6 minor 17 references

Reviewed by Pith at T0; open to challenge.

T0 means a machine referee read the full paper against a public rubric. The mark states how deep the mechanical check went, never who wrote it. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · glm-5.2

Smart glove plus camera hits 95% sign recognition

2026-07-09 21:56 UTC pith:IT2AWIB5

load-bearing objection The 95% accuracy claim rests on 10 gesture sequences with a confusion matrix computed on training data — the central empirical result is unsupported. the 4 major comments →

arxiv 2607.06996 v1 pith:IT2AWIB5 submitted 2026-07-08 cs.HC

Multimodal Smart Glove for Sign Language Recognition Using Deep Learning

Anh Thu Nguyen Ngoc , Tam Phong Truong , Thai Anh Nguyen Duong , Vu Linh Nguyen , Manh Duong Phung This is my paper

classification cs.HC

keywords languagerecognitionsignglovemodeldeeplearningsmart

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper claims that a wearable smart glove combining flex sensors, an inertial measurement unit, and a camera-based facial-expression module can recognize Vietnamese sign language gestures in real time with roughly 95% accuracy. The system streams finger-bending and hand-motion data from an ESP32-C6 microcontroller to a host computer, fuses those readings with facial cues extracted via MediaPipe, and feeds the combined 14-dimensional time series into a two-layer LSTM neural network. The authors convert the trained model to TensorFlow Lite and demonstrate live inference on a laptop, reporting a 95.34% confidence score for a test gesture. The paper frames this as a proof of concept that multimodal sensing — glove hardware for manual signals plus a camera for non-manual grammar cues — can be packaged into a deployable, lightweight recognition pipeline rather than confined to offline or vision-only setups that struggle with lighting and occlusion.

Core claim

The central claim is that fusing wearable sensor data (flex sensors measuring finger bend and an IMU measuring hand orientation) with camera-derived facial-expression indicators into a single 25-frame time series, processed by a stacked LSTM network, yields approximately 95% recognition accuracy across three Vietnamese sign language gestures and remains lightweight enough for real-time TensorFlow Lite inference on commodity hardware. The mechanism carrying the argument is the multimodal fusion at the input level: ten flex channels, three IMU orientation axes, and one discrete facial-expression code are concatenated into a uniform 25-by-14 sequence that the LSTM processes end-to-end without a

What carries the argument

The load-bearing machinery is a two-layer stacked LSTM (64 hidden units each, 0.5 dropout) that ingests a 25-frame, 14-feature multivariate time series. Ten features come from flex sensors on the glove fingers, three from the IMU's orientation axes, and one is a discrete facial-expression code (0–6) derived from MediaPipe landmark distances. The ESP32-C6 microcontroller handles sensor acquisition and Wi-Fi transmission; the host computer runs the LSTM inference via TensorFlow Lite. Categorical cross-entropy loss and the Adam optimizer drive training, with early stopping at a patience of five epochs over a 20% validation split.

Load-bearing premise

The reported 95% accuracy rests on a dataset of only three gesture classes and ten total recording sequences (250 time steps), which means the number likely reflects performance on a tiny, near-memorized sample rather than statistically robust generalization across diverse signers, hand sizes, or signing speeds.

What would settle it

If the system were tested on a held-out set of gestures from signers not represented in training data — or if the vocabulary were expanded beyond three words — and the accuracy dropped sharply (say below 70%), the central feasibility claim would be undermined. The current three-class, ten-sequence evaluation cannot distinguish genuine learned gesture dynamics from memorization of a handful of recording patterns.

Watch this falsifier — get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Desk Editor's Note

The 95% accuracy claim rests on 10 gesture sequences with a confusion matrix computed on training data — the central empirical result is unsupported.

read the letter

The headline: the 95% accuracy claim is not supported by the experimental design. The dataset has 3 gesture classes and 10 total sequences. With a 20% validation split, that's roughly 2 validation samples. The confusion matrix in Fig. 6b is explicitly labeled 'on trained data.' So the headline number is computed on training data, and the validation accuracy they mention (93-95%) is based on ~2 samples — a single misclassification swings it by 50 percentage points. This is the load-bearing problem, and the reader and stress-test are both right to flag it hard. There's also a real dimensionality inconsistency: Section 3.2 specifies d=14 (10 flex + 3 IMU + 1 facial) while Section 4.1 describes a 9-dimensional vector (5 flex + 3 IMU + 1 face). The described architecture and the actual experiments don't match, which suggests the paper was assembled from two different versions of the system. What's actually new: the specific hardware integration (ESP32-C6, ADS1115 ADC, BNO055 IMU, SF15 flex sensors) applied to Vietnamese Sign Language is a genuine engineering contribution. The TFLite deployment for real-time inference on a laptop is a practical step. The system pipeline — sensor fusion, preprocessing, LSTM, sentence builder — is clearly described and reproducible in principle. The hardware design is documented with schematics. But the core methodology (flex + IMU + LSTM for sign language) is well-established in the literature they cite [4, 15, 17]. MediaPipe facial cues are a minor addition, and the facial expression encoding (7 discrete values) is underspecified. The vocabulary is 3 gestures — far below practical translation needs. No cross-validation, no error bars, no independent test set, no inter-subject evaluation. The real-time demo on 5 participants is mentioned but not quantified. This is a workshop-level hardware demo paper dressed up with a performance claim it can't support. The engineering is competent; the evaluation is not. It doesn't deserve a serious referee at a full venue. If the authors collected a proper dataset (50+ gestures, multiple signers, cross-validation) and fixed the dimensionality inconsistency, it could become a solid systems paper. As-is, the central claim doesn't hold.

Referee Report

4 major / 6 minor

Summary. The paper presents a multimodal smart glove system for Vietnamese Sign Language (VSL) recognition, combining flex sensors, an IMU, and camera-based facial cues processed by an LSTM network. The hardware design (ESP32-C6, ADS1115, BNO055) is clearly described, and the system is deployed via TensorFlow Lite for real-time inference. The central empirical claim is approximately 95% recognition accuracy across three VSL gestures.

Significance. The integration of wearable sensing with facial-cue analysis for VSL is a reasonable design choice, and the end-to-end pipeline from hardware through TensorFlow Lite deployment is a practical contribution. However, the significance is substantially limited by the experimental evaluation: only three gesture classes and ten total sequences are used, and the headline accuracy appears to be computed on training data. These issues undermine the empirical claims and prevent the work from constituting a rigorous evaluation at this stage.

major comments (4)

Section 4.1 and Fig. 6b: The dataset comprises only 3 gesture classes and 10 total sequences (250 time steps). With a 20% validation split (Section 3.3), this yields approximately 2 validation sequences, making the reported 93-95% validation accuracy statistically uninformative. More critically, Fig. 6b is explicitly labeled 'Confusion matrix on trained data,' indicating the headline accuracy is computed on training data, not a held-out test set. The central performance claim of ~95% accuracy is therefore unsupported. The authors must collect a substantially larger dataset, use proper train/test splits or cross-validation, report results on a held-out test set, and include confidence intervals or error bars.
Section 3.2 vs. Section 4.1: There is a dimensionality inconsistency. Section 3.2 specifies d=14 features (10 flex + 3 IMU + 1 facial), while Section 4.1 specifies a 9-dimensional feature vector (5 flex + 3 IMU + 1 face). This discrepancy suggests the described architecture may not match the actual experimental setup and must be reconciled.
Section 4.3: The real-time deployment evaluation reports a single successful inference with a 95.34% confidence score for one gesture ('Tôi'). While demonstrating feasibility, a single trial does not constitute a rigorous real-time evaluation. The authors should report quantitative results across multiple gestures, participants, and trials, including latency and failure modes.
Section 3.1: The facial expression pipeline encodes expressions into discrete values 0-6 representing seven grammatical components, but the mapping is not specified, and it is unclear how these discrete values are used by the LSTM or validated. Given that facial cues are a claimed modality, this component requires proper description and justification.

minor comments (6)

Section 2.2: The number of flex sensors is inconsistent — the text mentions 'multiple SF15 flex sensors' and Section 3.2 lists 10, but Section 4.1 uses only 5. Clarify the actual count.
Section 4.1, Table 1: The gesture label for the example data is not specified; indicate which gesture class the example belongs to.
Section 3.3: The batch size of 128 exceeds the total dataset size (10 sequences), so it is unclear how training with this batch size was actually conducted.
Figure 1 and Figure 4: The two system overview figures are nearly identical; consider consolidating or differentiating them more clearly.
Section 1: The phrase 'Integration flex and IMU sensors' is missing a preposition; should read 'Integration of flex and IMU sensors.'
The abstract states 'approximately 95%' accuracy; this should be qualified given that the evaluation is conducted on training data with a minimal dataset.

Circularity Check

0 steps flagged

No circularity found; the derivation chain is self-contained despite methodological flaws

full rationale

The paper's central claim (~95% recognition accuracy) is an empirical result from training an LSTM on sensor data, not a derivation that reduces to its inputs by construction. The input layer (flex sensors, IMU, facial features) feeds into preprocessing, then into an LSTM network, then into a softmax classifier — this is a standard supervised learning pipeline with no definitional circularity. The paper does not define any quantity in terms of the result it claims to predict. Self-citations [8,9,16] involve overlapping authors (Phung, M.D.) but concern robot navigation and crack detection — they are tangential background citations, not load-bearing for the sign language recognition claim. The serious problems in this paper (evaluation on training data per Fig. 6b's label, a dataset of only 10 sequences, dimensionality mismatch between Section 3.2's d=14 and Section 4.1's 9-dimensional vector) are correctness and experimental validity concerns, not circularity. The derivation chain does not exhibit any step where an output is equivalent to an input by definition, fit, or self-citation.

Axiom & Free-Parameter Ledger

5 free parameters · 3 axioms · 0 invented entities

The paper does not invent new theoretical entities. It relies on standard deep learning components and off-the-shelf hardware. The free parameters are standard hyperparameters chosen empirically.

free parameters (5)

LSTM hidden units = 64
Chosen architecture hyperparameter for both LSTM layers (Section 3.3).
Dropout rate = 0.5
Chosen regularization hyperparameter (Section 3.3).
Batch size = 128
Chosen training hyperparameter (Section 3.3).
Temporal frames (T) = 25
Fixed sequence length chosen for data segmentation (Section 3.1).
Resampling interval = 80 ms
Chosen temporal resolution for signal processing (Section 3.1).

axioms (3)

standard math LSTM networks are well suited for sequential data to learn temporal patterns.
Standard machine learning assumption invoked in Section 3.3 to justify the choice of model.
domain assumption Facial expressions encoded as discrete values 0-6 correspond to seven distinct grammatical components.
Invoked in Section 3.1 to justify the facial cue feature representation; no validation is provided for this encoding scheme.
ad hoc to paper 25 temporal frames at 80ms intervals sufficiently capture the temporal dynamics of a sign language gesture.
Invoked in Section 3.1 to define the input shape; the choice of 2 seconds is not justified against gesture duration distributions.

pith-pipeline@v1.1.0-glm · 10105 in / 2066 out tokens · 230852 ms · 2026-07-09T21:56:21.773514+00:00 · methodology

0 comments

read the original abstract

Sign language recognition technologies can improve communication between deaf individuals and the broader community, but many existing systems face challenges in real-world deployment. This paper presents a deployable smart glove system for sign language recognition that integrates wearable sensing and deep learning. The glove incorporates flex sensors and an inertial measurement unit (IMU) to capture finger articulation and hand motion, while facial cues are obtained through a camera. Sensor data are transmitted via an ESP32-C6 microcontroller and processed using a long short-term memory (LSTM) network to model temporal gesture dynamics. Experimental results show that the proposed model achieves an overall recognition accuracy of approximately 95%. The trained model is further converted to TensorFlow Lite for real-time inference. This demonstrates the feasibility of the system for practical sign language translation applications.

Figures

Figures reproduced from arXiv: 2607.06996 by Anh Thu Nguyen Ngoc, Manh Duong Phung, Tam Phong Truong, Thai Anh Nguyen Duong, Vu Linh Nguyen.

**Figure 1.** Figure 1: System overview The overall architecture of the proposed sign language recognition system is illustrated in [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗

**Figure 2.** Figure 2: Hardware design of the hand glove ADS1115 and BNO055 via the I2C interface. The collected data are then transmitted wirelessly to the host computer for further processing [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗

**Figure 3.** Figure 3: Schematic circuit of the hand glove [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗

**Figure 4.** Figure 4: System pipeline for gesture recognition, including input acquisition, preprocess [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗

**Figure 5.** Figure 5: Neural network inference pipeline for sign language recognition. [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

**Figure 6.** Figure 6: Recognition result of the proposed model. [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗

**Figure 7.** Figure 7: Real-time recognition using the proposed sign language glove. [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗

discussion (0)

Reference graph

Works this paper leans on

17 extracted references · 17 canonical work pages

[1]

IEEE transactions on multimedia 24, 1750–1762 (2021)

Adaloglou, N., Chatzis, T., Papastratis, I., Stergioulas, A., Papadopoulos, G.T., Zacharopoulou, V ., Xydopoulos, G.J., Atzakas, K., Papazachariou, D., Daras, P .: A comprehensive study on deep learning-based methods for sign language recognition. IEEE transactions on multimedia 24, 1750–1762 (2021)

work page 2021
[2]

Multimedia Tools and Applications 79(31), 22177–22209 (2020)

Aloysius, N., Geetha, M.: Understanding vision-based continuous sign language recognition. Multimedia Tools and Applications 79(31), 22177–22209 (2020)

work page 2020
[3]

In: Visual analysis of humans: Looking at People, pp

Cooper, H., Holt, B., Bowden, R.: Sign language recognition. In: Visual analysis of humans: Looking at People, pp. 539–562. Springer (2011)

work page 2011
[4]

IEEE Sensors Journal 23(24), 31389–31398 (2023)

Feng, D., Zhou, C., Huang, J., Luo, G., Wu, X.: Design and implementation of gesture recog- nition system based on flex sensors. IEEE Sensors Journal 23(24), 31389–31398 (2023)

work page 2023
[5]

IEEE Access 10, 40979–40998 (2022)

Joksimoski, B., Zdravevski, E., Lameski, P ., Pires, I.M., Melero, F.J., Martinez, T.P ., Garcia, N.M., Mihajlov, M., Chorbev, I., Trajkovik, V .: Technological solutions for sign language recognition: a scoping review of research trends, challenges, and opportunities. IEEE Access 10, 40979–40998 (2022)

work page 2022
[6]

Liu, Z., Qian, S., Xia, C., Wang, C.: Are transformer-based models more robust than cnn- based models? Neural Networks 172, 106091 (2024)

work page 2024
[7]

In: Third workshop on computer vision for AR/VR at IEEE computer vision and pattern recognition (CVPR)

Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.L., Y ong, M., Lee, J., et al.: Mediapipe: A framework for perceiving and processing reality. In: Third workshop on computer vision for AR/VR at IEEE computer vision and pattern recognition (CVPR). vol. 2019, p. 2. Long Beach, CA (2019)

work page 2019
[8]

In: 2024 International Conference on Control, Robotics and Informatics (ICCRI)

Nguyen, D.P ., Nguyen, T.L., Tu, M.D., Quach, C.H., Truong, X.T., Phung, M.D.: Socially aware motion planning for service robots using lidar and rgb-d camera. In: 2024 International Conference on Control, Robotics and Informatics (ICCRI). pp. 109–114. IEEE (2024)

work page 2024
[9]

Intelligent Service Robotics 18(6), 1369–1380 (2025)

Nguyen, T.L., Nguyen, D.P ., Nu, T.T.T., Le, Q., Tran, T.H., Phung, M.D.: Real-time recog- nition of human interactions from a single rgb-d camera for socially-aware robot navigation. Intelligent Service Robotics 18(6), 1369–1380 (2025)

work page 2025
[10]

In: 2015 15th International Conference on Control, Automation and Systems (ICCAS)

Phi, L.T., Nguyen, H.D., Bui, T.Q., Vu, T.T.: A glove-based gesture recognition system for vietnamese sign language. In: 2015 15th International Conference on Control, Automation and Systems (ICCAS). pp. 1555–1559. IEEE (2015)

work page 2015
[11]

IEEE Access 10, 123358–123377 (2022)

Saeed, Z.R., Zainol, Z.B., Zaidan, B., Alamoodi, A.H.: A systematic review on systems-based sensory gloves for sign language pattern recognition: An update from 2017 to 2022. IEEE Access 10, 123358–123377 (2022)

work page 2017
[12]

In: 2020 international conference on inventive computation technologies (ICICT)

Sharma, S., Singh, S.: Vision-based sign language recognition system: A comprehensive re- view. In: 2020 international conference on inventive computation technologies (ICICT). pp. 140–144. IEEE (2020)

work page 2020
[13]

IEEE Transactions on Human-Machine Systems45(4), 526–533 (2015)

T ubaiz, N., Shanableh, T., Assaleh, K.: Glove-based continuous arabic sign language recogni- tion in user-dependent mode. IEEE Transactions on Human-Machine Systems45(4), 526–533 (2015)

work page 2015
[14]

Neural computing and applications 32(12), 7957–7968 (2020)

Wadhawan, A., Kumar, P .: Deep learning-based sign language recognition system for static signs. Neural computing and applications 32(12), 7957–7968 (2020)

work page 2020
[15]

IEEE Internet of Things Journal 11(24), 40787–40799 (2024)

Wang, D., Wang, M., Zhang, Z., Liu, T., Meng, C., Guo, S.: Wearable electronic glove and multilayer para-lstm-cnn-based method for sign language recognition. IEEE Internet of Things Journal 11(24), 40787–40799 (2024)

work page 2024
[16]

IEEE Access 9, 60201– 60214 (2021)

Zhu, Q., Dinh, T.H., Phung, M.D., Ha, Q.P .: Hierarchical convolutional neural network with feature preservation and autotuned thresholding for crack detection. IEEE Access 9, 60201– 60214 (2021)

work page 2021
[17]

IEEE Robotics and Automation Letters9(2), 1540–1547 (2023)

Zhu, R., Fan, D., Lin, J., Feng, H., Wang, H., Dai, J.S.: Machine-learning-assisted soft fiber optic glove system for sign language recognition. IEEE Robotics and Automation Letters9(2), 1540–1547 (2023)

work page 2023

[1] [1]

IEEE transactions on multimedia 24, 1750–1762 (2021)

Adaloglou, N., Chatzis, T., Papastratis, I., Stergioulas, A., Papadopoulos, G.T., Zacharopoulou, V ., Xydopoulos, G.J., Atzakas, K., Papazachariou, D., Daras, P .: A comprehensive study on deep learning-based methods for sign language recognition. IEEE transactions on multimedia 24, 1750–1762 (2021)

work page 2021

[2] [2]

Multimedia Tools and Applications 79(31), 22177–22209 (2020)

Aloysius, N., Geetha, M.: Understanding vision-based continuous sign language recognition. Multimedia Tools and Applications 79(31), 22177–22209 (2020)

work page 2020

[3] [3]

In: Visual analysis of humans: Looking at People, pp

Cooper, H., Holt, B., Bowden, R.: Sign language recognition. In: Visual analysis of humans: Looking at People, pp. 539–562. Springer (2011)

work page 2011

[4] [4]

IEEE Sensors Journal 23(24), 31389–31398 (2023)

Feng, D., Zhou, C., Huang, J., Luo, G., Wu, X.: Design and implementation of gesture recog- nition system based on flex sensors. IEEE Sensors Journal 23(24), 31389–31398 (2023)

work page 2023

[5] [5]

IEEE Access 10, 40979–40998 (2022)

Joksimoski, B., Zdravevski, E., Lameski, P ., Pires, I.M., Melero, F.J., Martinez, T.P ., Garcia, N.M., Mihajlov, M., Chorbev, I., Trajkovik, V .: Technological solutions for sign language recognition: a scoping review of research trends, challenges, and opportunities. IEEE Access 10, 40979–40998 (2022)

work page 2022

[6] [6]

Liu, Z., Qian, S., Xia, C., Wang, C.: Are transformer-based models more robust than cnn- based models? Neural Networks 172, 106091 (2024)

work page 2024

[7] [7]

In: Third workshop on computer vision for AR/VR at IEEE computer vision and pattern recognition (CVPR)

Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.L., Y ong, M., Lee, J., et al.: Mediapipe: A framework for perceiving and processing reality. In: Third workshop on computer vision for AR/VR at IEEE computer vision and pattern recognition (CVPR). vol. 2019, p. 2. Long Beach, CA (2019)

work page 2019

[8] [8]

In: 2024 International Conference on Control, Robotics and Informatics (ICCRI)

Nguyen, D.P ., Nguyen, T.L., Tu, M.D., Quach, C.H., Truong, X.T., Phung, M.D.: Socially aware motion planning for service robots using lidar and rgb-d camera. In: 2024 International Conference on Control, Robotics and Informatics (ICCRI). pp. 109–114. IEEE (2024)

work page 2024

[9] [9]

Intelligent Service Robotics 18(6), 1369–1380 (2025)

Nguyen, T.L., Nguyen, D.P ., Nu, T.T.T., Le, Q., Tran, T.H., Phung, M.D.: Real-time recog- nition of human interactions from a single rgb-d camera for socially-aware robot navigation. Intelligent Service Robotics 18(6), 1369–1380 (2025)

work page 2025

[10] [10]

In: 2015 15th International Conference on Control, Automation and Systems (ICCAS)

Phi, L.T., Nguyen, H.D., Bui, T.Q., Vu, T.T.: A glove-based gesture recognition system for vietnamese sign language. In: 2015 15th International Conference on Control, Automation and Systems (ICCAS). pp. 1555–1559. IEEE (2015)

work page 2015

[11] [11]

IEEE Access 10, 123358–123377 (2022)

Saeed, Z.R., Zainol, Z.B., Zaidan, B., Alamoodi, A.H.: A systematic review on systems-based sensory gloves for sign language pattern recognition: An update from 2017 to 2022. IEEE Access 10, 123358–123377 (2022)

work page 2017

[12] [12]

In: 2020 international conference on inventive computation technologies (ICICT)

Sharma, S., Singh, S.: Vision-based sign language recognition system: A comprehensive re- view. In: 2020 international conference on inventive computation technologies (ICICT). pp. 140–144. IEEE (2020)

work page 2020

[13] [13]

IEEE Transactions on Human-Machine Systems45(4), 526–533 (2015)

T ubaiz, N., Shanableh, T., Assaleh, K.: Glove-based continuous arabic sign language recogni- tion in user-dependent mode. IEEE Transactions on Human-Machine Systems45(4), 526–533 (2015)

work page 2015

[14] [14]

Neural computing and applications 32(12), 7957–7968 (2020)

Wadhawan, A., Kumar, P .: Deep learning-based sign language recognition system for static signs. Neural computing and applications 32(12), 7957–7968 (2020)

work page 2020

[15] [15]

IEEE Internet of Things Journal 11(24), 40787–40799 (2024)

Wang, D., Wang, M., Zhang, Z., Liu, T., Meng, C., Guo, S.: Wearable electronic glove and multilayer para-lstm-cnn-based method for sign language recognition. IEEE Internet of Things Journal 11(24), 40787–40799 (2024)

work page 2024

[16] [16]

IEEE Access 9, 60201– 60214 (2021)

Zhu, Q., Dinh, T.H., Phung, M.D., Ha, Q.P .: Hierarchical convolutional neural network with feature preservation and autotuned thresholding for crack detection. IEEE Access 9, 60201– 60214 (2021)

work page 2021

[17] [17]

IEEE Robotics and Automation Letters9(2), 1540–1547 (2023)

Zhu, R., Fan, D., Lin, J., Feng, H., Wang, H., Dai, J.S.: Machine-learning-assisted soft fiber optic glove system for sign language recognition. IEEE Robotics and Automation Letters9(2), 1540–1547 (2023)

work page 2023