Tofu Counting

csdetb-icono

Customer

One of Japan’s leading Fried tofu manufacturer.

Project Details

  • Duration: 1 Month +

Technologies:

  • Deep Learning
  • OpenCV
  • Python
  • PyQt
  • MongoDb
  • Edge computing device
problem-img

Problem

  • The tofu manufacturer faces challenges in accurately counting the fried tofus going into a single packaging.
  • Manual counting is prone to errors due to fast-moving lines.
  • It also fails to provide real-time insights and statistics on the efficiency of each line. This limits the benefits of real-time production monitoring.

 

solution-img

Solution

We developed a desktop application that detects and counts fried tofu using a segmentation model.

  • The count is updated in real time and displayed on-screen for each package pass.
  • Daily reports can be easily exported and analyzed by improving the workflow of food production automation.
  • The solution is designed for quick integration into existing food packaging automation lines.
  • Built to support food processing automation. It increases speed, accuracy, and operational clarity.
  • Helps with packaging line optimization by identifying trends in discounts or drops in output.

99.56%

Accuracy

< 1s

Detection & Counting Speed

Implementation-Challenges

Implementation Challenges

  • Achieving accurate segmentation and counting on fast-moving tofu pieces.
  • Ensuring consistent results under different lighting and frying conditions.
  • Integrating with existing automated food packaging systems without halting operations.
  • Providing exportable data that aligns with production reports.
  • Designing the UI for non-technical plant operators.
Key-Features

Key Features

  • Real-time tofu detection and counting display.
  • Compatible with high-speed production lines. 
  • Easy daily report export for batch tracking.
  • Seamless integration into food packaging automation environments.
  • Supports operational scalability across multiple lines.
  • Improves overall efficiency in food processing automation.

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.

November 4, 2025 - 8 minutes to read

At the Edge of Vision – The Story of WebOccult + Deeper-I at Japan IT Week 2025

Collaboration creates a story. Some are born from timing, others from shared ambition. But the partnership between WebOccult and Deeper-I began from something subtler, a mutual belief that intelligence should live closer to the world it serves. For years, Vision AI has been mastering the art of seeing, while Edge AI has been perfecting the […]

Read More

Ruchir Kakkad

CEO & Co-founder

October 31, 2025 - 8 minutes to read

The Intelligence of Reading – How Vision AI Learns to Understand Surfaces

Any object that leaves a factory belt carries an identity. It may appear as a string of numbers etched into metal, a barcode printed on paper, or a label attached to packaging or glass material. Together, these small symbols form the nervous system of modern industry. They track movement, record responsibility, and ensure that everything […]

Read More

Ruchir Kakkad

CEO & Co-founder

October 29, 2025 - 10 minutes to read

The Technical Anatomy of a Parking Twin

Every city breathes in patterns. Cars move, pause, and disperse in a rhythm that repeats itself through hours and seasons. Beneath this rhythm lies a kind of language, the pulse of motion that defines how urban life organizes itself. Yet, for all the technology that has reshaped cities, one of the simplest and most visible […]

Read More

Ruchir Kakkad

CEO & Co-founder

Whatsapp Img