Скачать с ютуб The AI Opportunity - Building trust in automated visual inspection в хорошем качестве

The AI Opportunity - Building trust in automated visual inspection

Find out more at https://www.cambridgeconsultants.com/ai In part one of the video series #AIOpportunity, Tim Ensor, Director of Artificial Intelligence, shares his insights into using AI in high-trust applications. In particular, automated visual inspection implemented by a global manufacturer of medical devices. Transcript Using artificial intelligence in high-trust applications is something many of our clients are grappling with. One particular area prompting plenty of thought is automated visual inspection. Our team recently helped a global manufacturer of medical devices with exactly this issue. Their products make a real difference to the lives of thousands of patients each year, and quality is extremely important to them. I’m Tim Ensor, and I lead the AI Capability at Cambridge Consultants. This is the first of a series of short videos on ‘The AI opportunity’. I'll be sharing our most recent AI developments; the challenges they address for industry and the opportunities they are creating for the ambitious businesses that have deployed them. The head of engineering at our client had been exploring the use of AI to automate the end-of-line quality inspection process. Currently, the inspection process is manually very intensive to ensure they only ever ship good products for doctors to use. The challenge they’d always encountered was that standard neural network image classifiers are just not accurate enough to allow him to trust the AI and remove the manual inspection step from his workflow. In addition to this, he wanted an AI to be able to identify types of defect that it hadn’t seen before. Working closely with their manufacturing team, we developed a visual anomaly detection system that understands exactly what a good product looks like. It can identify one so confidently that good products don’t require manual inspection. Beyond this, the system can continually learn when it does encounter new defects and to feed insights back to the manufacturing team to continually improve their processes. By taking this approach, we’re using AI to deliver unique capability and deliver direct business benefits for our clients. If you’d like to talk more about using AI for visual inspection or any other business challenge needing a unique AI solution, please get in touch. You can find more about our work at cambridgeconsultants.com/ai