Optical Character Recognition & Verification Systems (OCR / OCV Systems)

System features

Features of OCR inspection

Inspection background

In our daily life, products related to printed words can be seen everywhere. For example: characters on the keyboard, labels on clothes, characters on electrical appliances, etc. However, the appearance of these products will cause complaints from customers to the manufacturer due to some defects in text printing, such as pictures, shifts, excessive ink, leakage, and missing printing.

In order to overcome this problem, manufacturers will conduct strict tests before the products leave the factory. The traditional detection method is manual visual inspection. Although the visual method is flexible, it can make different judgments on various errors. However, due to the large number and variety of products and the high labor consumption, long-term inspection will cause eye fatigue or be misjudged by subjective emotions, which will also lead to the outflow of defective products and cause customer complaints.

OCR inspection principle

Using machine vision inspection technology, according to different product materials, defects and customer requirements, using different light sources, different lighting angles and cameras with different pixels, the defect image can be distinguished from the background image. Then use the color, grayscale, shape, and size of the defect image to identify the defect, use different algorithms to write software according to the image effect, and develop software according to customer requirements. Real-time detection, analysis and calculation of products with high precision, high efficiency and high stability can effectively improve the detection speed and accuracy of the production line, greatly improve output and quality, reduce labor costs, and prevent misjudgments caused by eye fatigue.

Inspection details

1. Install an OCR character detection system on the production line.
2. After the product is coded, the visual sensor is used to trigger the machine to take pictures, and the obtained label pictures are sent to the system. The system extracts, analyzes and compares the pictures to determine whether the product has missed a code, and checks whether there are errors or omissions in the production batch number and other information.
3. When a product with unqualified characters is detected, the system will send out an audible and visual alarm and send out a rejection signal.

Advantages of OCR/OCV system

• AI algorithm: high stability, adapting to the environment and background disturbance; different defect samples can be automatically identified after training
• Dataization: Independent database, save multiple samples, analyze non-good products, and retain history
• Multi-orientation: 360 ° comprehensive inside and outside the samples
• High precision: detection accuracy can be high
• Modularization, can flexibly increase or decrease the detection function according to customer actual needs
• Easy to operate: It is easy to operate and easy to maintain
• Safety: Medical grade material manufacturing, fully compliant with medical supplies production environment