[AI Image Inspection Case] Counting Plastic Parts
Count plastic parts with AI!
Counting parts is a common inquiry, and this time it involves a plastic parts manufacturer. We feel that the demand for inspection automation due to labor shortages is increasing year by year. We conducted inspections using a software called DeepSky, which utilizes AI (Deep Learning). By training the software on the areas we want to detect, it adjusts its own settings and learns to recognize them. Upon verifying the samples we received, we found that counting was possible. However, for samples without specified trays, when they were in close contact or overlapping, we were able to validate the inspection items by making adjustments. Regarding inspection cycle time, the EasyInspector we submitted previously has a shorter cycle. However, since counting items not placed in trays is difficult to determine, we decided to validate this time using DeepSky. The inspection cycle time with DeepSky depends on PC specifications, but it is approximately 0.3 seconds per image (1 inspection). With DeepSky, you can utilize higher-level software that supports counting on conveyors. It is designed to accommodate various types of counting.
basic information
【Software and Equipment Used】 Software Used: Deepsky Field of View: 400 x 300mm Minimum Size of Inspection Target: 2mm Number of Inspection Points: 24 Camera Resolution: 1.3 Megapixels Lens Focal Length: 6mm Distance Between Lens and Product: 300mm Lighting: Indoor Fluorescent Light
Price range
Delivery Time
Applications/Examples of results
For more details, please refer to the related links or feel free to contact us.
