Author: Shao, Li
Title: The design of soft computational interfaces and chip-integrated textiles for gesture recognition in interactive application
Advisors: Tan, Jeanne (SFT)
Degree: Ph.D.
Year: 2023
Subject: Textile fabrics -- Technological innovations
Textile fibers -- Technological innovations
Smart materials
Wearable technology
Hong Kong Polytechnic University -- Dissertations
Department: School of Fashion and Textiles
Pages: 1 volume (unpaged) : color illustrations
Language: English
Abstract: The design project investigates interactive electronic textiles (e-textiles) that seamlessly integrate gesture recognition (G-R) and illumination functionalities. G-R textiles covertly incorporate technology into flexible fabrics for natural, ubiquitous, and non-invasive human-computer interaction (HCI). The conventional look and feel of G-R fabrics might boost their technological adaptability and universality. Wireless communication and internet of thing (IoT) can be utilised to develop G-R textiles as remote interfaces enabling screenless interaction with smart devices.
The intelligent interactivity of G-R textiles enables novel textile structures to sense, compute, adapt to, and respond to external stimuli and user gestures. Advanced semiconductor chips and machine learning technologies are integrated in the creation of innovative G-R textiles. Reviewing historical and worldwide literature and products reveals manipulative and communicative gestures (further categorized as 1-D, 2-D, 2.5-D, and 3-D). The recognition mechanism, fabrication techniques, materials, application scenario and mode, and design process model are then investigated to identify specific research gaps and problems. A practice-led research methodology employing the 'analysis-synthesis-evaluation' research process is utilised to address the initial problem identified in practice. A novel empathy-material-computation-iteration (EMCI) design model is proposed and organically implemented into the ASE research process in order to create novel G-R textiles for solving research problems.
Based on the EMCI design model, three experiments are conducted on the design of G-R textiles. In the first experiment, 'multidimensional G-R embellishment', a series of launderable multidimensional G-R textile swatches with rich texture are created and manufactured by beading, hand embroidery, and tasselling using the capacitive sensing mechanism. POF substrate fabrics and illuminative sequins based on chip-LEDs are used to visualise recognition results. The portability, expandability, and adaptability of its interactive system are iteratively enhancing. Secondly, 'chip-integrated communicative G-R textiles', a computer vision-based prototype able to recognize 22 number gestures and gestures of expressive symbol is produced. A micro-sized, detachable photoelectric device is inserted into the channels of a double-layered woven POF fabric. An open-source machine-learning algorithm processes and recognizes gestures photos acquired in real-time. The communicative G-R textile swatch is evaluated with users to enhance usability and experience. Thirdly, 'universal sensing matrixes for computational G-R textiles', woven G-R fabrics with universal sensing matrixes are created and fabricated as soft interfaces for the recognition of new manipulative gestures. The universal sensing matrixes are double-layered structures woven of conductive yarns and POFs to detect the capacitance signals of the gestures, which are recognised using machine learning techniques. By incorporating user gesture data, the computational G-R textile interface is more universal and applicable.
The G-R textile swatches are applied in the design of smart wearables and interiors for HCI and rehabilitation. A novel EMCI design model comprehensively concerning user-needs, non-conventional materials, computational design, and iteration for G-R textiles in wearables and interiors is developed. Integrating POFs into fabric constructions or embedding new illuminative sequins real-timely visualize recognition results for better experience and user-friendliness. Various fabrication techniques are utilised to enrich texture, appearance, gesture, and interactive manner of manipulative and communicative G-R textiles to address research gaps in this field.
Rights: All rights reserved
Access: open access

Files in This Item:
File Description SizeFormat 
6817.pdfFor All Users15.23 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/12369