Large vision models give Quality Control a Big Brotherly spin
Ever wondered how your evening snack-time cookies turn out perfectly uniform in shape and texture? Chances are they were inspected by the cameras and AI systems built by this Chennai-based startup.
Jidoka Technologies' software tools and computer vision models help detect product defects in real-time across assembly lines. From biscuits to car gears to coconut oil bottles, its systems use multiple cameras and powerful vision models to flag anomalies and eject defective items in a flash as the products run through conveyors.
'Modern computer vision can transform product inspection as manufacturers aim for higher quality,' says Sekar Udayamurthy, co-founder and CEO.
Typically factories engage workers for manual quality checks. But, they are subjective as individual workers cannot perform uniformly causing either higher wastage or higher defects. Also the process could be slow. The startup makes it consistent, faster and helps companies scale inspections.
It can inspect 10,000 parts per minute with more than 99% accuracy, according to Udayamurthy.
It monitors manufacturing processes involving human workers in real time to prevent rework.
Its tools can be used for various tasks including counting, sorting, label text verification, assessing inventory and suggesting improvements in the manufacturing process with analytical dashboards. Jidoka provides hardware tools along with its software and models.
Giving us a lowdown on this entrepreneurial journey, Udayamurthy informs us that he was working in a senior role in the US at Cognizant, building products for Fortune 500 clients while his co-founders, Dr Krishna Iyengar, Vinodh Venkatesan were both employed in an auto manufacturing facility in Chennai.
They identified quality control as a key pain point in the manufacturing sector, which led to higher wastage and costly recalls.
So they began building industry-specific AI models.
Starting with automobiles, Jidoka Technologies performs three million inspections a day across FMCG, pharmaceutical, electronics and logistics verticals for major companies like Britannia and Maruti Suzuki. 'We are the only ones who give both product and process inspection on a single platform.
Secondly, we are the only ones that can do it at these speeds. These are our primary differentiators,' he said.
The trio has built domain-specific vision models for each industry and holds two patents in anomaly detection and decision engine. The startup was incubated by NSRCEL of IIM Bangalore and has so far raised
19.5 crore. It raised 11 crore in Pre-Series A round from Arali Ventures. Jidoka aims to hit the $25 million revenue mark in five years time and bets on expanding its services to different verticals such as solar and semiconductors as well as geographic expansion in Australia, Europe and North America. They plan to build a platform for proactive monitoring for quality and throughput and building large vision models (LVM) to handle tasks in multiple domains.
'The end-game is to create generic models that can work across customer bases,' explains Udayamurthy.
Stay informed with the latest
business
news, updates on
bank holidays
and
public holidays
.
AI Masterclass for Students. Upskill Young Ones Today!– Join Now
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Time of India
20 minutes ago
- Time of India
Stable Money raises $20 million in flat Series B round led by Fundamentum
BENGALURU: Wealth-tech startup Stable Money has raised $20 million (Rs 173 crore) in a Series B round led by Fundamentum Partnership, the early-stage fund co-founded by Nandan Nilekani. Aditya Birla Ventures also participated, along with existing investors Z47, RTP Global and Lightspeed. The round comes less than a year after the company's previous fundraise. Stable Money plans to use the capital to expand its product offerings, strengthen its network of banking and non-banking financial company (NBFC) partners, and extend its reach into smaller cities and towns. Founded in 2022, the Bengaluru-based startup operates a digital platform that facilitates fixed-return investments. It allows users to book fixed deposits without opening a savings account and offers features such as instant withdrawal, a 7-day trial fixed deposit (FD), and FD-backed credit cards. The company recently launched Stable Bonds as part of its product expansion. Stable Money said it currently has over 20 lakh users and manages more than Rs 3,000 crore in assets across FDs and bonds. India's fixed deposit market includes more than 230 million account holders and continues to grow at an annual rate of around 12%. The company had previously raised $20 million across earlier funding rounds from investors including Z47, Lightspeed, RTP Global, and Marshot, along with angel backers such as Swiggy's Sriharsha Majety and Snapdeal founders Kunal Bahl and Rohit Bansal. Stay informed with the latest business news, updates on bank holidays and public holidays . AI Masterclass for Students. Upskill Young Ones Today!– Join Now
India Today
22 minutes ago
- India Today
Retail gets personal: How brands are fast learning what you want
Retail is transforming fast with 'phygital' and 'omnichannel' as buzzwords, allowing customers to order online, pick offline and vice versa. The trend was discussed in the panel discussion 'Brick & Mortar in a Digital World: Retail's Road Ahead' at the recent Indo-UAE Conclave 2025 in Dubai, organised by the India Today Group, where speakers analysed the strengths of physical stores and how digital is being used to augment those benefits while bringing in cost and inventory optimisation for Teckchandani, CEO of the UAE-based fashion and retail conglomerate Apparel Group, said each of the retailers today is in the world of omnichannel or what is now called connected Group today has close to 2,400 stores across 14 countries, of which roughly 1,900-plus are within the Gulf Cooperation Council (GCC), besides a large e-commerce business, 'It's no longer digital versus physical, but about how you catch the consumer,' Teckchandani the consumer journey starts with digital. Around 75 per cent of the time, the customer has already done all the research or looked at the product online. And then, the transaction may end up at the retail store—or not. This allows the flexibility to buy online but refund or exchange at the store, or vice versa, he says. Apparel Group has also ventured into quick commerce, wherein they are offering 60-minute delivery and using their network of 1,900 retail stores as fulfilment centres for online Markose, CEO, international business, Titan Company Limited, shared how digital commerce is rising in India but offline had its own critical mass. Sharing an example, he said when they acquired CaratLane in 2016, it was an online company with about Rs 600 crore in revenue, of which 99.5 per cent came from online crossed Rs 4,000 crore last year. And from 99.5 per cent, revenue online has dropped to just 8 per cent, with in-store revenue now contributing 92 per cent. 'Today, the sweet spot is in the middle. You can't just be digital, and you can't just be a traditional physical company—you've got to be in both spaces,' said key thing is that in every category, there's a price point below which people are very comfortable buying online. So in India, for watches, it's about $40—anything below that, people are happy to buy online; anything above that, they prefer to see it in stores. In jewellery, that threshold is around $200. This varies from category to category, he leveraging technologies like AVRs or artificial intelligence, Teckchandani said brands are building 'stores of the future', which offer full experience and digital transformation for customers at the store level. For instance, they have installed smart mirrors at their Tommy Hilfiger store and have a phygital store established in Dubai Hills Mall—the first in the region. This includes mobile point of sale and frictionless checkout. Even the loyalty programme is offered through a mobile app instead of a plastic said Teckchandani, are also being used to improve backend operations. These include a lot of digital tools which are used for store transfer optimisation, markdown optimisation, price optimisation and allocation optimisation. 'All of these ensure the product is where it should be and where the consumer is—creating a positive customer journey by ensuring that you carry the best SKUs (stock keeping units) in the same store.'advertisementMarkose said the India and UAE markets have been closely linked for a long time. Commerce and trade between the Middle East and India began 2,000 to 4,000 years ago with the spice trade between the Arabs and a result, the Middle East was their first preferred destination to take the Tanishq brand outside India, due to the large Indian diaspora. But they had to adapt it to suit the retail market in the Middle East. For instance, the store formats there are much smaller than in India, some of their stores are 30,000 sq ft—that size and scale doesn't work in the UAE. Another aspect was that jewellery sales in the UAE is very transactional. The levels of customer service that Tanishq provides in India were not really the norm here. Even something as simple as seating in the stores was uncommon as consumers usually walk in, do the deal, and walk of the things Markose pointed out was that retail has moved from a time when there were limited choices to now, where there is an overwhelming abundance. 'Consumers sometimes struggle with what to pick. So, the game is shifting toward personalisation,' he said, adding that the question now is: how do I know you as an individual? How do I know what you're interested in, what you've purchased? How do I build a relationship where I can predict what you're likely to be interested in? For instance, in Tanishq, which offers around 60,000 different SKUs, how do we figure out and present the few products that you will actually like?Subscribe to India Today Magazine
Time of India
22 minutes ago
- Time of India
OpenAI announces $150,000 in grants to 11 Indian nonprofits for social innovation
Artificial intelligence (AI) model developer OpenAI has announced grants worth $150,000 for non-profit organisations in India tackling challenges in healthcare, education, agriculture, gender equity, and disability inclusion. The San Francisco, US-based company is expanding its ' AI for Impact Accelerator ' in India, under which 11 nonprofits will receive grants in the form of API credits and technical resources, it said in a statement on Tuesday. As part of the OpenAI Academy, the programme is delivered in collaboration with philanthropic partners The Agency Fund, Tech4Dev, and 'India has shown how AI can drive inclusive innovation at scale. These organisations are solving some of the country's most complex challenges with ingenuity and empathy,' said Pragya Misra, policy & partnerships lead, OpenAI India. 'This work reflects the spirit of the India AI Mission and reaffirms OpenAI's commitment to meaningful impact.' Among the 11 nonprofits selected under the program are Rocket Learning, which uses WhatsApp and generative AI (GenAI) to deliver personalised early childhood education to four million children across 11 Indian states, reaching 20% of India's public daycare system. Noora Health uses AI to assist 400,000 caregivers by reducing nurse workload by 80%, and Educate Girls uses AI to identify and re-enrol over two million out-of-school girls, improving learning for 2.4 million children in 30,000 villages, OpenAI said. Discover the stories of your interest Blockchain 5 Stories Cyber-safety 7 Stories Fintech 9 Stories E-comm 9 Stories ML 8 Stories Edtech 6 Stories Other names include Udhyam, Digital Green, Precision Development, i-Stem, Pinky Promise, Myna Mahila Foundation, Youth Impact and IDinsight.
