AI Demo: Scotch Tape Detection

See how our AI detects scotch tape on banknotes — and where it looks

Below are real banknote images captured by an early prototype of our new CIS sensor. The AI model (ResNet50 running on our Analog NPU) classifies each image as Tape Detected or No Tape — and the Grad-CAM heatmap shows exactly which regions the AI focused on to make its decision.

1

Original Image

IR scan of a banknote from prototype CIS

2

AI Heatmap (Grad-CAM)

Red/Yellow = high attention, Blue = low attention

3

Hover / Tap to Compare

Move your cursor to reveal the heatmap

Tape Detected

These banknotes have scotch tape applied. Notice how the AI highlights the taped regions in warm colors (red/yellow).

Banknote with tape - Sample 1 Grad-CAM heatmap - Sample 1
Grad-CAM
Tape Detected 100%
Banknote with tape - Sample 2 Grad-CAM heatmap - Sample 2
Grad-CAM
Tape Detected 99.8%
Banknote with tape - Sample 3 Grad-CAM heatmap - Sample 3
Grad-CAM
Tape Detected 100%
Banknote with tape - Sample 4 Grad-CAM heatmap - Sample 4
Grad-CAM
Tape Detected 100%
Banknote with tape - Sample 5 Grad-CAM heatmap - Sample 5
Grad-CAM
Tape Detected 100%
Banknote with tape - Sample 6 Grad-CAM heatmap - Sample 6
Grad-CAM
Tape Detected 100%

No Tape (Clean)

These banknotes are clean — no tape. The AI's attention is spread more evenly across the surface, confirming no localized anomaly.

Clean banknote - Sample 7 Grad-CAM heatmap - Sample 7
Grad-CAM
No Tape 99.3%
Clean banknote - Sample 8 Grad-CAM heatmap - Sample 8
Grad-CAM
No Tape 100%
Clean banknote - Sample 9 Grad-CAM heatmap - Sample 9
Grad-CAM
No Tape 100%
Clean banknote - Sample 10 Grad-CAM heatmap - Sample 10
Grad-CAM
No Tape 99.9%
Clean banknote - Sample 11 Grad-CAM heatmap - Sample 11
Grad-CAM
No Tape 100%
Clean banknote - Sample 12 Grad-CAM heatmap - Sample 12
Grad-CAM
No Tape 100%

Deep Dive: How the AI Focuses

A deep neural network processes images through multiple layers. Early layers detect basic features (edges, textures), while deeper layers recognize high-level patterns. Watch how the AI's attention progressively narrows from broad scanning to pinpointing the exact tape location.

Tape Detected Confidence: 100%

Original (IR Scan)

Original banknote
1 Layer 1
Layer 1 Grad-CAM

Edges & textures

2 Layer 2
Layer 2 Grad-CAM

Patterns & shapes

3 Layer 3
Layer 3 Grad-CAM

Object parts

4 Layer 4
Layer 4 Grad-CAM

Final decision

Notice how the attention concentrates from the entire surface to the exact tape location as layers deepen.

No Tape Confidence: 99.3%

Original (IR Scan)

Original banknote
1 Layer 1
Layer 1 Grad-CAM

Edges & textures

2 Layer 2
Layer 2 Grad-CAM

Patterns & shapes

3 Layer 3
Layer 3 Grad-CAM

Object parts

4 Layer 4
Layer 4 Grad-CAM

Final decision

With no tape present, the attention remains broadly distributed — the AI found nothing suspicious to focus on.

How It Works

Model: ResNet50, fine-tuned for binary classification (tape / no tape). Trained on real banknote images captured by an early prototype of our Advanced CIS sensor under infrared illumination.

Visualization: Grad-CAM (Gradient-weighted Class Activation Mapping) shows which image regions most influenced the AI's decision. Red/yellow = high influence, blue = low influence.

Why it matters: Traditional rule-based tape detection uses a mechanical sensor that physically touches every banknote. It's noisy, wears out, and achieves only ~65% detection rate at best. Our AI-based approach analyzes the full image at 1,000+ notes per minute with near-100% accuracy — and the mechanical sensor is completely eliminated.

12/12
Correct in this demo
100%
Validation accuracy
~1ms
Inference time per note
No Code
Retrain with new data only

Question? Let us know.