Zekun Blog

Across the Great Wall, we can reach every corner in the world.

Slides Thief: Turn Photographed Presentation Slides into Clean PDFs

Just take photos of the slides, they are yours now.

We have all done it: sitting at an angle in a classroom, academic talk, tech sharing session, or trade show, quickly taking photos of presentation slides before they disappear. The problem comes l...

MemoryCustodian Skill - Project Memory for Coding Agents

Durable memory. Minimal context.

When working with coding agents such as Codex, Claude Code, Gemini CLI, or similar tools, one problem appears again and again: Every new session starts as if the agent has never seen the project b...

Social inequality and cultural factors impact the awareness and reaction during the cryptic transmission period of pandemic

PNAS Nexus

The World Health Organization (WHO) declared the COVID-19 outbreak a Public Health Emergency of International Concern on 2020 January 31. However, rumors of a “mysterious virus” had already been ci...

Characterizing browser-based medical imaging AI with serverless edge computing: towards addressing clinical data security constraints

SPIE Medical Imaging, 2023

The deployment of deep learning algorithms in clinical practice faces challenges in data privacy and local hardware constraints. This work presents the tools and design choices of a browser-based e...

WearMask: Fast in-browser face mask detection with serverless edge computing for COVID-19

Electronic Imaging

The COVID-19 epidemic has been a significant healthcare challenge in the United States. COVID-19 is transmitted predominately by respiratory droplets generated when people breathe, talk, cough, or ...

K-Means-Based Anomalous Email Detection in PySpark

Anomaly detection for emails based on MinHash and K-Means, implemented with PySpark and Colab

K-Means is known as a common unsupervised learning clustering method. But in fact, the K-Means algorithm can be applied to more scenarios. In this post, I will use a K-Means-based approach to compl...

WearMask - Face Mask Detection Project Details

Low-cost solution for small businesses and public places

The paper has been published on arXiv. Background Last November, the COVID-19 epidemic in the United States reached a new peak. During Thanksgiving week alone, there were 1,147,489 new cases and ...

Super-Fast In-Browser Face Mask Detection

Open the web page, and you have it!

facemask-detection.com 👈👈 This is an AI tool that detects masks super fast: No installation or registration. No need to buy expensive devices. You don’t even need a continuous internet conn...

Tutorial for Compiling NCNN with WASM

The second step to deploying a deep learning model in the browser

The content of this tutorial is an extension of the Tutorial for compiling NCNN library. After we successfully compile the NCNN library normally, we can use its tools to convert our models into NC...

Tutorial for Compiling the NCNN Library

The first step to deploying a deep learning model

This is a tutorial for compiling the NCNN library. The content comes from my attempts to complete the Mask-Detection project, so the process is based on the Yolo-Fastest model. I hope it will help ...