Case Study: Hitachi achieves 100% defect detection in visual inspection with Looker

Hitachi Using visual inspection AI for quality control and achieving 100% accuracy

Hitachi, a Japanese electronics manufacturer, needed to improve quality control at Omika Works, where manual visual inspection of crimp terminals was time-consuming, error-prone, and difficult to scale across factories. Hitachi turned to Looker as part of a Google Cloud-based visual inspection initiative, using Visual Inspection AI and its Hitachi industrial edge computer CE50-10 to make defect detection easier for on-site staff.

Looker helped Hitachi build and test a visual inspection system that created a machine learning model from about 100 sample images in roughly one day. The solution achieved a 100% defect identification rate with no false negatives, and the PoC showed the system was usable for manufacturing-site deployment, while also helping Hitachi evaluate workflow timing and integration needs for future rollout.

Hitachi

Masayuki Takagaki

Management Department, Production Management Division