Texture recognition based on magnetostrictive tactile sensor array and convolutional neural network
Source abstract
Abstract
Tactile sensors are key devices in surface information perception for robots that can recognize the surface texture of fabrics with different materials and winding patterns in unstructured environments, thus helping the robot process fabrics more effectively. In this study, a magnetostrictive tactile sensor array was designed and loaded onto the robotic fingertips, and the output voltage waveform was obtained by manipulating the sensor array to slide in contact with fabrics. The output voltage waveform diagram was normalized to build the FTS-15 tactile texture dataset. The convolutional neural network ResNet-18 model was built to pre-process the dataset, and the accuracy of recognizing 15 fabrics reached 97.95%. The results show that this texture recognition method can be effectively applied to the field of fabric texture recognition.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Sensor and Energy Harvesting Materials · Industrial Vision Systems and Defect Detection · Tactile and Sensory Interactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology 1 , Tianjin 300130, China
Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology 2 , Tianjin 300130, China
Funding
Colleges and Universities in Hebei Province Science and Technology Research Project · Hebei Provincial Central Guidance Local Science and Technology Development Project · National Natural Science Foundation of China · Natural Science Foundation of Hebei Province
References (25)
Show source-provided references
1. Automatic recognition method for the three-elementary woven structures and defects of carbon fabric prepregs10.1016/j.compstruct.2022.115527 ↗
2. A framework of human action recognition using length control features fusion and weighted entropy-variances based feature selection10.1016/j.imavis.2020.104090 ↗
3. From BoW to CNN: Two decades of texture representation for texture classification10.1007/s11263-018-1125-z ↗
4. Bilinear convolutional neural networks for fine-grained visual recognition10.1109/tpami.2017.2723400 ↗
5. Deep filter banks for texture recognition, description, and segmentation10.1007/s11263-015-0872-3 ↗
6. Material recognition using tactile sensing10.1016/j.eswa.2017.10.045 ↗
7. There’s more to ‘sparkle’ than meets the eye: Knowledge of vision and light verbs among congenitally blind and sighted individuals10.1016/j.cognition.2019.03.017 ↗
8. Fabric classification using a finger-shaped tactile sensor via robotic sliding10.3389/fnbot.2022.808222 ↗
9. Surface texture recognition by deep learning-enhanced tactile sensing10.1002/aisy.202100076 ↗
10. Non-equilibrium-Growing aesthetic ionic skin for fingertip-like strain-undisturbed tactile sensation and texture recognition10.1002/adma.202300593 ↗
11. Effects of sensing tactile arrays, shear force, and proprioception of robot on texture recognition10.3390/s23063201 ↗
12. Tactile-based fabric defect detection using convolutional neural network with attention mechanism10.1109/tim.2022.3165254 ↗
13. Fingertip skin-inspired microstructured ferroelectric skins discriminate static/dynamic pressure and temperature stimuli10.1126/sciadv.1500661 ↗
14. An artificial neural tactile sensing system10.1038/s41928-021-00585-x ↗
15. A flexible triboelectric tactile sensor for simultaneous material and texture recognition10.1016/j.nanoen.2021.106798 ↗
16. Machine learning classifiers for surface crack detection in fracture experiments10.1016/j.ijmecsci.2021.106698 ↗
17. Deep residual pooling network for texture recognition10.1016/j.patcog.2021.107817 ↗
18. Deep residual learning for image recognition: A survey10.3390/app12188972 ↗
19. Design of magnetostrictive tactile sensor for depth detection10.1108/sr-01-2022-0051 ↗
20. The slip hypothesis: Tactile perception and its neuronal bases10.1016/j.tins.2016.04.008 ↗
21. A holistic model of human touch10.1007/978-1-4757-9800-5_118 ↗
22. The mechanosensory neurons of touch and their mechanisms of activation10.1038/s41583-021-00489-x ↗
23. Biomimetic tactile sensor array based on magnetostrictive materials10.1109/jsen.2021.3068160 ↗
24. Large-area, flexible SnS/paper-based piezoresistive pressure sensor for artificial electronic skin application10.1109/jsen.2020.3029017 ↗
25. Can you see what you feel? Color and folding properties affect visual-tactile material discrimination of fabrics10.1167/16.3.34 ↗