Case Study - Incloud OCR Checker background
Case Study - Incloud OCR Checker background
Case Study - Incloud OCR Checker logo

Keeping the vision to make development a painless experience for all clients in mind, InCloud always wants to deliver web or mobile applications, IOT SENSOR SYSTEMS, and CLOUD SERVICES CONSULTING with Japanese-level quality and Western-level technological skills at very cost-effective prices.

Case Study - Incloud OCR Checker background
Case Study - challenges icon

Challenge

Breathalyzers are a crucial tool in modern health and safety, providing vital information through displayed numeric data. However, the efficient storage and utilization of this data can prove to be quite challenging. This challenge becomes even more complex due to their various screen designs and numerical displays.

InCloud required a system capable of automatically reading and keeping track of the digital numbers from a breathalyzer in pictures taken with mobile phones.

That’s why they needed AI experts to develop an application quickly that could work well on both web and mobile while still maintaining efficiency, accuracy, and a minimal recognition time.

As a result, they reached out to Neurond AI, their trusted long-term partner, for solutions.

Case Study - Incloud OCR Checker background
Case Study - Solutions icon

Solution

Immediately, Neurond gathered a team of 2 AI Engineers led by a Senior AI Consultant. After extensive dialogue with InCloud, we consulted them about a lightweight mobile application that can recognize breathalyzer digit display from various conditions of images taken by mobile phones.

Upon successfully identifying InCloud’s exact needs, we initiated the development of the AI solution. The proposed model could accurately read numbers on any image, even on sharp, out-of-focus, and darkened images.

To ensure the model's capability for mobile phone usage, we planned to make it lightweight with high accuracy - a balance that would reduce computation and, consequently, processing time.

Technologies Used

  • Digital Digit Recognition
  • 7-segment Digital Displays
  • SSD (Single Shot Detection) model with MobileNet architecture
Case Study - Incloud OCR Checker background
Case Study - Impact icon

Impact

The result was a breakthrough for InCloud, as they now have a model that can recognize digital numbers on breathalyzer devices with over 98% accuracy. At the same time, the application operates smoothly on both mobile and computer platforms.

Thanks to the success of this OCR Checker application, as well as previous projects, Neurond and InCloud continue to maintain our partnership to carry out promising AI projects in the future.