Computer Vision for Quality Inspection

Orange Business Services offers an asset-based Computer Vision service made for visual inspection. It includes a trained Machine Learning model (using customer’s data), the deployment of the model in the customer’s infrastructure as well as a frontend interface. Using photos taken on a production line, the solution can in near real-time detect defaults and validate the quality of each product. It replaces manual inspection which is time consuming and an expensive process. Orange Business Services’ Computer Vision solution can detect smallest defects reliably, not relying on defect-labelled training data and is able to adapt automatically to new defects that have not occurred before.

Request private offer

Overview

The AWS portfolio offers a great number of tools and components to develop a ready-to-deploy Computer Vision solution. To unlock the power of these cloud native components a skilled team of experts is required. Orange Business Services is providing the expertise as well as the asset of a ready-to-deploy Computer Vision solution for quality inspection. Orange Business Services’ AWS certified experts will implement and customize the solution to bring its customers successfully to the end of their Machine Learning journey.

Orange Business Services is using its expertise in numerous fields as IoT, cloud, connectivity, or big data to unlock may use-cases in the manufacturing industry (and many other verticals). One of the results is its offering: Computer Vision for quality inspection. The most common use-cases raised up when scaling Machine Learning in industry are :

Automating and computerizing manual processes as quality inspection
Improving workers’ safety on the factory lines
Inventory management, storage units’ management

The Computer Vision solution Orange Business Services offers is easily deployable for quality inspection but can answer more use-cases, as the ones mentioned before. To facilitate the deployment of such a Machine Learning model, and to prove the business value it can generate: the solution has been splitted into two main deployment steps which are called offers.

Basic offer (fixed price upon requirements) – from 35k€

Pre-packaged solution
State-of-the-art Computer Vision for quality inspection
Training of models using custom dataset
Frontend interface for model validation & testing
Setup of AWS accounts and VPN Gateway

Full offer - on quotation

Setting up IoT devices or cameras for data collection, data cleaning and pre-processing
Frontend interface and monitoring tools
MLOps pipeline for retraining and deployment of the Computer Vision model
VPN access, peering / routing / connection
Tailor-made features

Are you interested in such a solution? Once we are in contact, our experts will assess your data and give you the best advice to set up as soon as possible the Computer Vision Machine Learning model we have developed. We implement at first the basic offer which can be extended and upgraded following your needs.

Highlights

Low data requirement to train: using the zero-shot learning technology, the model only needs a few pictures of “good products” to be trained and then be deployed
Automatically detect new defects: the solution can adapt automatically to new defects that have not occurred before on the production line
Close to real-time analysis: the solution can analyse up to 10 frames per second which is score reliable for production line. Meaning analysing 10 products per second

Details

Sold by

Orange Business

Unlock automation with AI agent solutions

Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.

Explore AI agent solutions

Pricing

Custom pricing options

Request private offer

Pricing is based on your specific requirements and eligibility. To get a custom quote for your needs, request a private offer.

How can we make this page better?

We'd like to hear your feedback and ideas on how to improve this page.

Legal

Content disclaimer

Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.