Industrial Imaging & Machine Vision
Wide-ranged and Precise Solutions for Any Industry
Kritikal’s Deep-learning based technology platform provides fast and accurate solutions for AI-based Defect Inspections like Barcode Reading, 360° Inspection, 3D Imaging, Robotic Guidance, and Surface Inspection. Our best-in-class AI-enabled Machine Vision technology with accurate defect classification capabilities requires significantly less training time as compared to rule-based Machine Vision systems and support decision-making on the fly. Our expertise in computer vision technology in industrial settings enables our clients to improve yields and reduce defect rates leading to drastic business transformations.
Service Offerings
AI-enabled Barcode Readers and OCR Systems
By implementing Kritikal’s sophisticated Barcode reading and Optical character recognition (OCR) technology, manufacturers can significantly extend the functionality of their Machine Vision systems. Text-based information like product labels, data printed on a product box/body can be captured, interpreted, and processed by the robotic system as per the requirement.
Product Development Services
At KritiKal, we take pride in designing superior quality vision systems for high-end industrial imaging product development. From stand-alone camera-based products to multi-camera products, our team has years of experience in designing vision-based products for a multitude of business sectors including Automotive, Printing, Packaging, Food, Beverage, and Pharmaceutical.
Object Detection and Classification
With years of experience in designing & developing Object detection, recognition/classification, and tracking algorithms. KritiKal’s deep-learning engine is a go-to solution for categorizing objects based on their Size, Shape, Appearance, or any other measurable physical entity.
Robotic Guidance
We offer vision support for Robotic Guidance systems. Whether you are into production or managing a project, our Robotic Guidance technology enables precision robot guidance for Robots, Cobots, and AGVs.
3D Imaging
Our 3D imaging technology uses the same approach as the human visual system. At Kritikal, we use industry-grade optical equipment to capture Dense and Accurate 3D images as per the client’s requirement to create a realistic replica of the object for quality control purposes.
Surface & 360° Defect Inspection
Quality control is a critical aspect of production. Fast production lines and round the clock working of machines makes manual inspection and defect detection a tough job to do.
At Kritikal, with our expertise in AI, Vision Systems, and Complex Algorithm development, we can help you develop a deep-learning-based non-contact inspection System. Kritikal’s deep-learning technology helps you to perform 360° Defect inspection by measuring Shape, Size, Colour, and Pattern of regular/complex shapes such as bottles and aluminum castings.
Our algorithm can easily classify any deviation in Texture, Print, Colour, and Pattern of various surfaces and assemblies like Glass, Plastic, Metal, Foil, Films, Laminates, and Textiles to inspect defects in the form of Blister, Cracks, Bubbles, Black particles and Printing & Assembly mismatch.
KritiKal's Defect Inspection System
Kritikal’s Deep-learning based defect inspection system contains four modules that allow for Objection detection, localization of key issues in the object, and classification of defects into categories. It also provides an AI-enabled OCR engine that analyses the text in the image and provides a digital output.
Finder
The finder helps in segregating the object from the background and localizing single or multiple features of the image.
Inspector
At this stage, the inspector cross-checks the image for any defect in the product by comparing it with correct images.
Classifier
The classifier analysis the defective items and classifies the defects into categories as per the client’s requirement.
Text-miner
The text-miner is used to extract text data from complex environments like metal surfaces and challenging backgrounds.
Our Methodology
This figure shows how our system works in a real-life scenario. Starting with the problem statement that includes an understanding of defect profile, speed, and accuracy requirements followed by getting images for error classification, testing, and learning purpose to resolve any error before deploying the system online.
Implementation Approach
POC, Proposal Development
& Go-Ahead
& Go-Ahead
Sample data is collected from the client and tested on our deep-learning system to get accuracy and defect detection rates as per the client requirements.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
Data Gathering &
Ground Truth Preparation
Ground Truth Preparation
Sample data is collected from the client and tested on our deep-learning system to get accuracy and defect detection rates as per the client requirements.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
Acceptance on
Good – Bad Parts
Good – Bad Parts
Sample data is collected from the client and tested on our deep-learning system to get accuracy and defect detection rates as per the client requirements.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
Defect
Classification
Classification
Sample data is collected from the client and tested on our deep-learning system to get accuracy and defect detection rates as per the client requirements.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
This step helps us in proposal development and deciding the implementation approach, Cost, and Project timeline.
Teams Involved
When to Use AI Enabled System
In places where the defect possibility is high Al-based Machine Vision is recommended rather than rule-based MV.
To detect defects that cannot be easily characterized based on quantification, shape, or size.
If defect classification is important for process control and improvement.
e.g. Contamination of grease, dust and chips varying in size, shape, and location.
To detect cracks or cosmetics defects that can come anywhere in the product or inspection of shiny or low contrast items.
To identify defects in components with different background/pattern or challenging feature extraction.