Machine vision technology and applications continue to hold a spot in my heart even though it became less interesting to me over the years. My $25K system from 1993 went to $10K by 1996 to $5K and under by 2000, all the while becoming more powerful and easier to use. However, I’ve lately talked with a company working on Artificial Intelligence for machine vision. It seems to be getting some traction. Here are two recent releases.
Landing AI and the Association for Advancing Automation (A3) have released a report from a survey covering a range of topics, including the level of adoption, benefits, and challenges of implementing AI-based visual inspection.
“As evidenced by the survey, AI-based machine vision is already creating value for the manufacturing industry, with proven benefits including improved accuracy, flexibility, and reduced cost,” said Dongyan Wang, Vice President of AI Transformation at Landing AI. “The availability of easy-to-use AI tools specifically designed for visual inspection will drive further industry adoption and bring the benefits of AI to more organizations.”
The report from Landing AI and A3 found that companies have a high degree of confidence in the effectiveness of AI, with 55% of respondents saying their overall opinion is either high or very high. The survey showed that 26% of respondents have adopted AI-based machine vision while 41% say they plan to in the future. Of those who are using AI, improved accuracy is the top benefit (62%).
While implementing AI, the primary challenge is scarcity of data on which to train AI models, noted 62% of manufacturers. Companies were also concerned about scalability as solutions moved out of pilot programs, with 27% saying they struggled when moving from proof-of-concept to initial deployment.
Additional findings from the Landing AI and A3 report include:
- In a heavily automated sector, manual inspection is still playing an important role, with 40% saying their inspection is either completely or mostly manual.
- The confidence level of businesses regarding AI effectiveness is high with 26% saying they are already using AI for visual inspection.
- When it comes to using AI, scarcity of data, complexity of integrating AI within existing infrastructure, and the inability to achieve lab results in production are the top three challenges.
- Most businesses prefer to have ownership of their AI projects either by developing in-house or by working with a vendor.
AI Visual Inspection Platform to Improve Quality and Reduce Costs
Meanwhile, Landing AI unveiled LandingLens, an end-to-end visual inspection platform specifically designed to help manufacturers build, deploy, and scale AI-powered visual inspection solutions.
“AI-powered visual inspection solutions have demonstrated clear advantages over conventional methods, yet the overall adoption is slow as many companies get stuck after some small-scale proof-of-concept projects,” said Andrew Ng, founder and CEO of Landing AI. “LandingLens, developed with the know-how and expertise from building and shipping many visual inspection projects, is best positioned to bridge the gap and enable teams to succeed. With an intuitive interface, Landing AI’s visual inspection platform allows even non-AI experts to train and deploy a model with a few clicks, putting the ownership of the solution in the hands of users so they can build and update the solutions without being beholden to a third-party AI team.”
- Defect and Data Management: A robust data preparation module helps customers improve efficiency and produce more accurately labeled data, resulting in better performing models in less time.
- Model Iteration: Training and evaluation tools enable users to rapidly develop a deployment-ready model.
- Continuous Learning: Inference and monitoring modules allow users to scale their AI solutions by enabling them to deploy production-ready models to the edge with ease, while continuously monitoring those deployments from a central location.
- Reduced Project Lifecycle: Reduces the AI project development life cycle time by up to 67%.
- Cost reduction: Reduce the overall AI development and deployment costs by up to 60%
- Improved Accuracy: Improves accuracy of Machine Learning models through more accurately labeled data
- Scaling: Enable users to effectively scale to multiple production lines across many factories