Blog

Regardless of whether companies manufacture cars, semiconductor chips, smartphones, or food and beverages, production quality and yield are two of the industry’s top performance metrics.

Poor production quality control results in significant operational and financial costs in the form of reworked parts, scrap generated, reduced yield, increased work in process inventory, post-sale recalls, warranty claims, and repairs.

In fact, the American Society for Quality estimates that for many organisations, the cost of quality is as high as 15-20 percent of annual sales revenue, which translates to billions of dollars annually for larger manufacturers.

AI-based vision quality inspection system

To help manufacturers perform production quality inspections more accurately and cost-effectively, Constems-AI uses computer vision-based AI to automate business operations processes by eliminating manual interventions and enhancing safety, security, control, and operational efficiencies. Their solutions help execute quality control for various agriculture-based products, manage traditional and modern retail operations, and reinforce sales and distribution by cutting down reaction time to market.

“We at Constems-AI are building an AI-based vision quality inspection system for consumer goods and processed foods segments to ensure end consumers receive the products without any defects or contamination,” says Amit Singh, Co-founder, CEO and Business Head, Constems-AI, speaking about how their cost-effective solution is reducing the dependency on ad-hoc human quality checks on the manufacturing lines.

“Our AI-Based visual inspection platform called CAInatics is an easily deployable system for manufacturing lines to support quality control teams with production data and real-time Overall Equipment Effectiveness (OEE) reports, providing real-time quality control, predictive analytics, and rejection integration RPAs,” he adds.

Addressing the problem with existing visual inspection approaches

Compared to traditional image processing, AI allows a more nuanced and robust performance in an uncontrolled environment; it tolerates a significant variation in ambient lighting, viewing angle, rain, dust, occlusion, and other environmental issues. AI also tolerates a high variation in shape of objects of interest, such as defects, vehicles, fruits, faces, etc. By learning from the data over time, machine learning easily locates and recognises objects not seen at training time.

Constems-AI’s proprietary technology video and sensors solution extracts relevant information from image and video data. Leveraging superlative processing capabilities and proprietary algorithms, their solutions send alerts based on predefined user KPIs and seamlessly fit into existing infrastructure .

The founding team

Amit comes with more than 15 years of experience in strategising and executing large-scale product deployments, together with Amit Srivastava, the CTO and Development Engineering Head who is passionate about building and deploying AI-based vision, having worked in tech leadership and R&D roles in AI and ML for over two decades. Both the co-founders are passionate about AI and vision-based technology.

The duo also holds US patents in the area of Augmented Reality, Multimedia, Home Connectivity and Streaming Technologies from their past engagements.

How the Intel Startup Program powered Constem’s growth journey

“The support Intel Startup Program has provided to young deep-tech startups like ours has been nothing short of amazing. Intel has been of great help to us to identify competencies, which improve our core. We also received sound advice on product development, go-to-market strategy and on how to hyper-focus on positioning and penetrating the market,” says Amit Singh, talking about how Intel played a significant role in accelerating the startup’s business and technology product improvements, which helped them define their way ahead in terms of technology and go-to-market.

“Powered by the Intel edge systems, our platform has achieved a peak predictive accuracy of 95 percent while maintaining seamless consistency in performance,” he adds.

The Intel Startup Program: enabling startups to scale their game-changing innovations

The Intel Startup Program is Intel India’s flagship program to engage with technology startups who have an IP or innovative solutions that have the potential to create impact on customers and align with Intel’s focus areas. The program is at the forefront of engaging with India’s startup ecosystem through high impact collaborations with the industry, academia and government and runs multiple initiatives that are either vertically aligned or focused on emerging technologies.

It engages with startups that have a unique global or local value proposition to solve genuine customer problems, enabling them with domain and business expertise from the industry and mentorship from Intel.

For more details visit: https://www.intel.in/startup-program