LENS
Project 02 — Computer Vision Pipeline

Lens
Smart
Media Pipeline

Upload any image. A Step Functions state machine fans out to five parallel Rekognition jobs simultaneously — label detection, face analysis, celebrity identification, content moderation, and OCR — then pipes extracted text through Comprehend. Results in under 3 seconds.

Rekognition ×5 Step Functions Comprehend Lambda ×5 S3 API Gateway
Status
● Live
Cost Per Image
~$0.008
Runtime
Python 3.12
Lambdas
×5 Functions
Pipeline
Step Functions
← All Projects
Try a sample image
🔍
Drop an image to analyze
PNG · JPG  ·  max 5 MB  ·  WEBP supported (text extraction requires JPG/PNG)
Pipeline Executing
Validate
Label Detection
Face Analysis
Celebrity ID
Content Moderation
Text Extraction
Merge
Comprehend
Analyzed image
Scene Intelligence
Safety
Detection Summary