YAFE aimed to automate the quality inspection process in tire manufacturing by developing a vision-based application system. The goal was to identify defective tire printing on the manufacturing line and redirect faulty tires for reprinting. The solution involved training a machine learning algorithm to read tire markings, compare them with the assembly line database, and flag defects. The algorithm then signaled the decision-making system to redirect the tire for reprinting.


Industrial cameras face data variability due to lighting, uneven tire surfaces, and printing quality. Extracting complex features is challenging due to complex markings and occlusions. OCR reliability is unreliable, and real-time dashboard performance is required.

Tech Stack


YAFE, Vision-Based Tire Quality Inspection solutions include advanced image processing, a deep learning model, OCR enhancements, optimized dashboard design, and automated monitoring and feedback mechanisms. These solutions reduce data variability, ensure consistent data quality, and address complex markings and occlusions, ensuring accurate data extraction and optimal system performance.


Industrial AI Camera Integration: Implemented an advanced tire analysis system using industrial AI cameras to capture live feeds. Image Processing Techniques: Utilized cutting-edge image processing techniques to pre-process the captured images. Deep Learning Model: Developed a sophisticated deep learning model specialized in identifying and extracting key features, particularly focusing on the DOT number. OCR System: Integrated an Optical Character Recognition (OCR) system to extract data from the identified features. Real-time Web Dashboard: Implemented a real-time web dashboard to display insights into daily tire manufacturing activities, seamlessly integrating extracted data. Accuracy Enhancement: Achieved a remarkable 99% accuracy, significantly reducing manual errors and boosting production efficiency by up to 10 times.


YAFE's vision-based quality inspection system revolutionized the tire manufacturing process by

Enhancing Accuracy

  • Achieved 99% accuracy in identifying defective tire printing, minimizing false positives and negatives.

Boosting Productivity

  • Increased production efficiency by up to 10 times by automating the quality inspection process.

Improving Decision-Making

  • Provided comprehensive insights into daily manufacturing activities through real-time data analysis, enabling strategic decision-making.


Katomaran, a pioneering app development company based in India, has set a new standard in the tire industry with its innovative approach to quality inspection using vision-based technology. YAFE is a solution that utilizes advanced machine learning and image processing techniques to enhance the accuracy, productivity, and efficiency of tire manufacturing operations.