Google Cloud on Tuesday launched Visual Inspection AI, a new tool to help manufacturers identify defects in products before they're shipped. It's the latest move from Google to win more customers in the manufacturing space, one of the key verticals the cloud company is targeting.
Visual Inspection AI is designed for various industries and uses cases, such as automotive, semiconductor production, and electronics manufacturing. Manufacturers have for years used AutoML Google's general-purpose AI product for quality control, but Visual Inspection AI is more accurate and efficient.
Based on pilots run by several Google Cloud customers, Visual Inspection AI can build accurate models with up to 300 times fewer human-labelled images than general-purpose ML platforms. It also improved accuracy in production trials by up to 10X compared with general-purpose ML approaches.
Using Visual Inspection AI doesn't require any special expertise. Inspection models can be downloaded to machines on the factory floor and run autonomously at the edge. At the same time, Visual Inspection AI has fully integrated with Google Cloud's portfolio of analytics and ML/AI solutions, giving manufacturers the ability to combine its insights with other data sources.
The tool integrates with existing products from Google Cloud partners, including SOTEC, Siemens, GFT, QuantiPhi, Kyocer and Accenture.
Manufacturing was one of six verticals Google Cloud identified as key to its growth in 2019, along with the public sector, financial services, healthcare, retail and communications/media. Since then, Google Cloud has been hiring executives to bolster its industry expertise and landing customers in manufacturing like Siemens, Ford, and Renault. Google recently commissioned a survey that showed manufacturers already, on average, allocate 36% of their overall IT spend to AI.