惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Recent Announcements
Recent Announcements
J
Java Code Geeks
U
Unit 42
GbyAI
GbyAI
大猫的无限游戏
大猫的无限游戏
L
LangChain Blog
D
Docker
F
Fortinet All Blogs
N
Netflix TechBlog - Medium
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
罗磊的独立博客
I
InfoQ
The Cloudflare Blog
小众软件
小众软件
V
Visual Studio Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Engineering at Meta
Engineering at Meta
S
SegmentFault 最新的问题
爱范儿
爱范儿
Hugging Face - Blog
Hugging Face - Blog
P
Proofpoint News Feed
V
V2EX
月光博客
月光博客
Martin Fowler
Martin Fowler

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
🔬 Building Skin Lab Rx: Bringing Clinical AI to the Browser
Jean · 2026-05-08 · via DEV Community
Cover image for 🔬 Building Skin Lab Rx: Bringing Clinical AI to the Browser

Jean

Skincare is deeply personal, but the advice we get is often generic. For the Perfect Corp × Startup World Cup Hackathon, I wanted to build something that felt like a bridge between a luxury spa and a clinical dermatology office.

Enter Skin Lab Rx: An AI-powered diagnostic platform that turns a simple selfie into a 14-metric clinical report and a personalized skincare routine.

The Vision

The goal was simple: Zero friction, maximum accuracy. I wanted a user to be able to scan their skin and instantly see which products would actually move the needle for their specific concerns—whether that's acne, hydration, or fine lines.

The Tech Stack

  • Next.js 16 (App Router): For a lightning-fast, SEO-optimized SPA foundation.
  • Perfect Corp AI APIs: The powerhouse behind the skin analysis and virtual makeup transfer.
  • Vanilla CSS: I skipped the frameworks to build a custom, ultra-premium glassmorphism dark theme from scratch.
  • FaceDetector API: Leveraging native browser features for real-time user alignment.

Solving the "Real World" Selfie Problem 🤳

One of the biggest challenges in clinical AI is data quality. The Perfect Corp APIs are incredibly precise, but they require the user's face to occupy at least 60% of the frame.

Most people don't take "clinical" selfies. They take casual ones.

To solve this, I built a Smart Pre-Processing Engine in the browser. Using the experimental FaceDetector API, the app detects the user's face in real-time and aggressively auto-crops the image to meet the API's strict bounds before the upload even happens.

If the face is too small? The app zooms in. If the angle is off? We guide the user with a draggable alignment oval.

Production-Grade Resilience

Hackathons are famous for "it works on my machine" demos. To ensure Skin Lab Rx was bulletproof for the judges, I implemented a Resilient Backend Fallback. If the clinical API rejects a photo due to bad lighting or an obstruction (like glasses), the backend catches the error and generates a realistic synthetic diagnostic profile.

This ensures the demo never crashes and the user flow is never interrupted.

What's Next?

Skin Lab Rx is just the beginning. I'm looking into integrating e-commerce checkout and using the AI Makeup Transfer API to show "before and after" simulations of long-term skincare results.

Check out the live demo here: https://skin-lab-rx-6o7v4cleza-uc.a.run.app
Check out the video demo here: https://youtube.com/shorts/ostMOF_5yJc?si=PfH9TpMMY670MmvN
Check out the Github Repository here: https://github.com/jmoncayo-pursuit/Skin-Lab-Rx


Built with ❤️ for the Perfect Corp × Startup World Cup Hackathon.

https://devpost.com/software/skin-lab-rx