Anomalies Detection on Bottle

csdetb-icono

Customer

A company in Japan that manufactures glass bottles for medicines.

Project Details

  • Duration: 3 Months+

Technologies:

  • Deep Learning
  • MongoDB
  • RabbitMq
  • Python
problem-img

Problem

The company produces more than 100k+ bottles every day.

  • They have to QC each bottle manually.
  • Manual QC takes too much time and prone to errors
  • Lot of people needs to be allocated due to high volume.
solution-img

Solution

Deployed a Computer Vision based system with Industrial cameras fitted in a way that captures the bottom view.

  • The Camera captures the photo on the trigger of the sensor. The photo is sent to the processor.
  • The system performs OCR and provides results.
  • The System also cross-verifies the correct sequence by comparing the OCR result with the serial number received from the printer.

100%

Accuracy in false print detection

<1 Sec

time between OCR & real-time alerts

Insights on innovation

Stay updated with the trending and most impactful tech insights. Check out the expert analyses, real-world applications, and forward-thinking ideas that shape the future of AI Computer Vision and innovation.