Quản trị

I founded Lights Beyond Eyes with a clear mission: to develop AI-driven tools and applications to enhance daily life for the visually impaired community.

As the founder, I established the vision and long-term strategy for the club. I directly recruit, train, and manage members across our departments (teaching, research, and communication). My responsibilities also include overseeing fundraising, event planning, and outreach to ensure the project's sustainability and visibility.

A primary focus of our work is education and direct impact. We established a strategic partnership with the Nguyen Dinh Chieu Special School for the Visually Impaired. I personally designed the curriculum and organized workshops on AI applications (like ChatGPT, OCR, and text-to-speech) tailored for the visually impaired.

To date, we have directly instructed over 50 visually impaired students at Nguyen Dinh Chieu School, helping them master the VoiceOver feature in ChatGPT to effectively support their learning.

I also direct fundraising initiatives, event logistics, and outreach campaigns to support organizations like the Thien An Shelter for the Visually Impaired, ensuring the club's sustainability and visibility.

I am deeply committed to scaling this initiative, with the future goal of reaching a wider community to ensure that no visually impaired individuals are left behind in the Technology 4.0 era.

I founded The Sinom Club from June 2023 with a mission to connect Vietnam's Sino-Nom cultural heritage with the modern generation. As the founder, I lead a team of 15 members, directly instructing them in reading and writing Sino-Nom, while also developing creative educational materials to pass on cultural values to children and the elderly.

Our efforts don't just stop internally. I have successfully organized three workshops on Sino-Nom, attracting about 30 participants per session.

To explore technology more deeply, I authored the eBook "Artificial Intelligence for the Preservation and Utilization of Sino-Nom Heritage" focusing on the application of AI for heritage preservation.

Our biggest focus is the Kim Từ Điển Hán-Nôm project, a technological initiative in partnership with the Computational Linguistics Center (CLC) at the University of Science, VNU-HCMC. In this project, I take on multiple roles:

1. Research & Data Engineering: Conducting field research, digitizing ancient manuscripts, and designing a searchable database.
2. Web Development: Serving as the architect and main developer for the project's website, optimizing the display of complex Hán-Nôm characters.
3. Administration & QA: Deploying and administering the platform, while also validating the accuracy of the Nôm-to-Quốc-ngữ (Nôm-to-Vietnamese) transliteration tool.

Our ultimate goal is to create a robust digital platform, making Sino-Nom heritage more accessible to researchers, students, and the community.

Full content with pdf file

Full content with pdf file

Full content with pdf file

PDF file

PDF file

PDF file

📱 TalkingPicture – AI-Powered Image Description App

Helping visually impaired “see” the world through spoken words

TalkingPicture is a mobile application designed to support people with visual impairments in perceiving their surroundings. By using advanced AI technology, the app analyzes captured images and provides natural-sounding audio descriptions in either Vietnamese or English. With a fully accessible and intuitive interface, users can interact entirely through touch, sound cues, and vibration — no visual navigation required.

🔍 Key Capabilities

1. Tap anywhere on the screen to capture a photo and receive an instant spoken description
2. Dual-language support: Vietnamese & English
3. Two description modes: concise or detailed
4. Automatic saving and playback of the 10 most recent images
5. Gesture-based controls optimized for accessibility
6. Voice feedback, audio instructions & haptic cues for every action

🚀 How to Use TalkingPicture

1. Launch the App
2. Open TalkingPicture — voice guidance will walk you through all basic gestures (tap, swipe, hold). The app starts directly in Camera mode.
3. Camera Screen
4. Tap anywhere → take a photo
5. Phone vibrates + sound effect confirms the shot
6. Wait a moment → the app speaks the AI-generated image description
7. Hold the screen → replay the last description
8. Tap again → take the next photo
9. History Screen
10. Swipe up/down to browse saved images
11. Each image automatically plays its stored description
12. Tap → replay the current description
13. Settings Screen
14. Swipe left/right to switch between categories
15. Tap or swipe up/down to adjust language, speech speed, and description length
16. Every adjustment is confirmed by a voice cue

✨ Quick Tip: Remember 3 simple actions — Tap to capture • Hold to replay • Swipe to navigate

🌟 Our Mission

TalkingPicture empowers visually impaired users to experience the world with greater independence — transforming every image into a meaningful story told through sound.

(Illustration Video: https://youtube.com/shorts/lNiblK_f6sk?feature=share)