THESIS: Development of Offline Sign Language Translation Glasses

High Level Description
Advancements in wearable technologies and computer vision have led to innovative ways to make day-to-day life more accessible for everyone. One such opportunity is recognizing and translating sign language in an embedded system to facilitate communication between hearing-impaired individuals and those who can't understand sign language. This project aims to create a wearable system, namely a pair of smart glasses, that can recognize sign language signals and display them on an embedded screen attached to the glasses. Through this project, we aim to understand the capabilities of machine vision applications on resource constrained devices and enhance accessibility for all in various environments.

Project Description
This project focuses on the development of a wearable system for sign language recognition using glasses integrated with a camera and an embedded display. Key objectives include:

• Gesture recognition: Develop, train and fine-tune an edge machine vision algorithm to detect and classify sign language gestures on a resource constrained device such as a Raspberry Pi Zero.
• User Interface and Output: Implement a method for starting recognition and displaying the translated result.
• System Design and Assembly: Build a pair of smart glasses with a camera and display to capture hand gestures and output result.
• Testing and Validation: Test the glasses in real-world or simulated scenarios to assess recognition accuracy, latency, usability, and robustness in various lighting and background conditions.
• Iteration and Improvement: Refine the hardware and software system to improve recognition performance, accuracy, and user comfort.

Who are we looking for?
We are seeking a master's student with a background in Embedded Systems, Computer Science, Electrical Engineering, or related fields to join our project. While prior experience with machine learning, sensor integration, and wearable technology is beneficial, it is not required. The ideal candidate should have:

• An interest in assistive technologies, wearable devices, and real-time signal processing.
  
• Motivation to work hands-on with both hardware and software, including sensor integration and algorithm development.
  
• Eagerness to contribute to research that promotes inclusivity and accessibility through technology.
• Fluency in Swedish, both written and spoken

Purpose
The primary purpose of this thesis is to develop a working computer vision algorithm that is capable of recognizing sign language and translating it on a resource constrained device. By integrating this algorithm with a camera and display system, we aim to work towards seamless communication and empower individuals with hearing impairments. This technology could lead to more inclusive environments and set the foundation for future innovations in wearable assistive devices.

The completed thesis project can be published and used in your personal portfolio as well as in company marketing. Please include your Resumé/CV and cover letter in your application.

An Exciting Journey with Knightec Group
Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe's leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies – from idea to complete solution.

Practical Information
This is a thesis position, located at our office in Solna, Rättarvägen 3. Start date

Please submit your application as soon as possible, but no later than If you have any questions, you are welcome to contact Myko Smid. Note that due to GDPR, we only accept applications through our careers page.