RuVector CNN - Neural Image Understanding

📤

Image Upload

Drop images to extract embeddings

🖼️

Drop images or click to upload

JPG, PNG, WebP • Multiple files supported

Quick samples:

📊

Similarity Matrix

Compare image embeddings

Images

0ms

Avg Time

512

Dimensions

Extract features from 2+ images to see similarity scores

📈

Embedding Visualization

512-dimensional feature vector

Click an image to visualize its neural embedding

> Ready for images...

📷

Real-time Neural Vision

Live CNN processing at 60+ FPS

🎯

How It Works

Real-time neural processing

1. Capture — Each video frame is grabbed at native resolution

2. Preprocess — Center-cropped to 224×224, converted to RGB

3. Inference — MobileNet-V3 extracts 512-dim embedding in ~5ms

4. Compare — Cosine similarity vs reference image (0 to 1)

💡 Tip: Set a reference image, then move objects in front of the camera to see real-time similarity changes.

🏃

Real-time Pose Estimation

17 keypoints • Skeleton visualization • MoveNet

🎯

Pose Keypoints

17 body landmarks detected

Start pose detection to see keypoints

● Nose

● Left Eye

● Right Eye

● Left Ear

● Right Ear

● Left Shoulder

● Right Shoulder

● Left Elbow

● Right Elbow

● Left Wrist

● Right Wrist

● Left Hip

● Right Hip

● Left Knee

● Right Knee

● Left Ankle

● Right Ankle

Use Cases

Fitness tracking & exercise form
Dance/movement analysis
Sign language recognition
Sports biomechanics
VR/AR body tracking
Gesture-based UI control

📊

Pose Embeddings

34-dim pose vector (x,y for 17 keypoints)

Live pose embedding visualization

> Pose detection ready...

🧠

Live Classifier

Train a classifier in real-time

1. Add labeled examples 2. Test on new images 3. Correct mistakes to improve

Test Classification:

🎯 Drop image to classify

🎯

Few-Shot Learning

Learn from 1-5 examples per class

Class A

Drop images

0 examples

Class B

Drop images

0 examples

Class C

Drop images

0 examples

🔮 Drop to classify

📈

Incremental Learning

Watch accuracy improve over time

Add examples one by one and watch the prototype centroids evolve.

📥 Drop to add example

Positive examples

Negative examples

⚖️ Drop to test

🔄

Feedback Learning

Correct mistakes to improve

The model learns from corrections. Wrong prediction? Tell it the right answer!

Train the Live Classifier above, then test images here to provide feedback

Total

Correct

—

Accuracy

💾

Memory Bank

Persistent embedding storage

View all stored embeddings and their class assignments.

No memories yet. Add examples to the classifiers above.

0 classes • 0 embeddings • 0 KB

📹

Camera Training

Train using your webcam

Ready

Interactive Demos

Try these working demos right in your browser

🔎

Similarity Search

Find similar images instantly

Click a query image, then see similarity scores for all others.

🎬

Motion Detection

Detect scene changes via embeddings

No Motion

Scene Change: 0%

⚖️

A/B Comparison

Compare two images side-by-side

Drop image

—

Similarity Score

📦

Batch Processor

Process multiple images at once

📁

Drop multiple images

Process up to 20 images

🔬

Embedding Explorer

Visualize feature dimensions

Upload an image to explore its 512-dim neural embedding

🖼️ Drop image to explore

Dim 0 Hover for details Dim 511

🚨

Anomaly Detection

Find outlier images in a set

Upload images — outliers will be highlighted in red

📊 Drop 4+ images

Code Examples

Copy-paste code snippets for common use cases

🔍

Visual Product Search

Upload a photo to find similar products in a catalog.

👤

Face Verification

Compare two face images to verify identity.

🔄

Duplicate Detection

Find near-duplicate images in a collection.

🎨

Art Style Matching

Compare artistic styles between images.

✅

Quality Control

Detect defects by embedding distance.

🗂️

Scene Clustering

Group photos by scene type automatically.

🏃

Pose Tracking

Track body pose over time for fitness.

🖐️

Gesture Control

Detect gestures to control applications.

🗃️

Image Retrieval

Build a searchable image database.

🛡️

Content Moderation

Flag similar inappropriate content.

💡

Visual Recommendations

Recommend visually similar items.

🎥

Video Keyframes

Extract unique frames from video.