OpenMV
Shields
Lens
Robotics
Book
Video
Download
Docs
Forum
OpenMV.io
GithubOn industrial electronic equipment assembly lines, product panels typically contain various components such as knobs, labels, buttons, and accessories. Manual quality inspection methods are prone to misjudgement, missed detection, and low efficiency.
Therefore, industrial electronic assembly manufacturers utilise SingTown's OpenMV intelligent camera to construct a smart visual inspection system, achieving automatic recognition and judgement of font printing content and angle, knob position, and component installation status. The system's inspection range is 350mm in length by 150mm in width, with a camera installation distance within 200mm, enabling simultaneous multi-item inspection within a confined space.
This solution can be widely applied in scenarios such as electronic control panels, switchgear, and assembly lines for precision instrument housings, assisting enterprises in achieving efficient and automated quality inspection.

Industrial electronics assembly manufacturers have developed a machine vision inspection system based on the OpenMV smart camera, integrating computer vision, AI image recognition, template matching, and OCR character detection algorithms to achieve real-time inspection of complex panel assembly.
This embedded vision system captures partial product images via high-definition cameras, performs OCR text recognition and tilt angle analysis on label areas to determine whether text is misapplied, misaligned, or exhibits colour anomalies; simultaneously, it utilises geometric feature matching algorithms to detect whether knob angles and positions comply with standards. For accessories of different colours (such as small yellow and grey components), the system can automatically determine whether installation is correct through colour segmentation and morphological analysis.
Furthermore, template comparison can also detect abnormalities such as foreign objects, dropped items, and missing components. Within the detection cycle (within 5 seconds), it completes the judgement and outputs a signal to the PLC or host computer, enabling the automatic rejection of defective products.
This solution offers advantages such as high detection accuracy (error <0.1mm), rapid response, strong environmental adaptability, and edge deployment, making it widely applicable in electronic assembly and consistency control scenarios.

AI Sentinel Based on OpenMV: Automatic Alert for Unsecured Key Locations
Automatically detects whether the door of a key location has remained open for an extended period and issues a timely alert.

Personnel crossing the boundary triggers an alarm; OpenMV interprets the “sense of security boundary”
Detects personnel or equipment crossing virtual perimeter lines.

“AI Urban Management Officer” is here: an automated unauthorised street vending detection system built on OpenMV
Automatically identifies illegal street vending activities to support daily urban governance.

Improper storage of gas cylinders? Use OpenMV to automatically trigger hazard alerts
Automatically identifies non-compliant placement positions of gas cylinders to detect potential gas safety hazards in advance.

Did you perform live-line work without wearing insulating gloves? OpenMV issues an immediate alert!
Automatically identifies whether personnel are wearing insulating gloves to assist in safe operations.

Utilise the OpenMV smart camera to identify surface defects on aluminium plates in real time
Online identification of surface defects on aluminium plates, such as scratches and dents, to support quality control.