Sold by: MphasisÂ
Deployed on AWS
Computer Vision & ML based Printed Circuit Board defect detector for missing hole, mouse bite, spur, open/short circuit and spurious copper
Overview
PCB Anomaly Detection is a computer vision-based machine learning solution to identify defects in Through-Hole PCBs. The algorithm identifies 6 different kinds of defects: Missing Hole, Mouse Bite, Spur, Open Circuit, Short Circuit, Spurious copper. The algorithm takes reference PCB templates for analysis and identification of defects in erroneous PCB images.
Highlights
- The solution identifies defects, places a bounding box around it and classifies the type of defect. It can find multiple defects in a single PCB and works well for all types of Through-Hole PCBs
- The solution is rotational invariant for testing data (provided the training data is straight and still). This solution can also ignore the background noise to an extent.
- Mphasis DeepInsights is a cloud-based cognitive computing platform that offers data extraction & predictive analytics capabilities. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $16.00 |
ml.m5.large Inference (Real-Time) Recommended | Model inference on the ml.m5.large instance type, real-time mode | $8.00 |
ml.m5.large Training Recommended | Algorithm training on the ml.m5.large instance type | $10.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $16.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $16.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $16.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $16.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $16.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $16.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $16.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
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.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Bug Fixes and Performance Improvement
Additional details
Inputs
- Summary
- Supported Content-Type : 'image/jpeg'
Input Schema: (For Training)
- Top view of non-erroneous, complete images of templates taken in portrait mode (no partial images)
Input Schema: (For Testing)
- Top view of complete image of PCBs taken in portrait mode (no partial image)
- Limitations for input type
- * Vertical and Horizontal resolution of 72 dpi or more * No shadow and background noise in images (for better performance) * The template images must be straight and still images without any defect
- Input MIME type
- image/jpeg
https://github.com/Mphasis-ML-Marketplace/PCB-Defect-Detector/tree/main/input/training
https://github.com/Mphasis-ML-Marketplace/PCB-Defect-Detector/tree/main/input/training
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Valor Process Preparation is the only complete process engineering solution available for PCB manufacturing. As lot sizes are reduced and the number of unique designs increases, the ability to enable an Industry 4.0 lot-size-one capability is only possible with a single point of truth for all aspects of the process engineering space. It is not possible to achieve best-in-class manufacturing with traditional, separate point solutions in front of each machine. Not only are separate point solutions ineffective, in most cases the data source is different for each machine, creating expensive inconsistencies across your manufacturing line. Contact us for more information on how Valor Process Preparation can solve your PCB assembly challenges.
Instrumental's cloud platform serves as the AI-enabled backbone for companies optimizing their manufacturing processes, to accelerate time-to-market, improve yields, eliminate rework and save engineering time. This data infrastructure enables companies to dramatically reduce waste and increase product margins as they bring products to market.
The electronic manufacturing services (EMS) market is poised to hit USD 1 trillion by 2032 driven by the surging penetration of smart devices and smartphones, production shift to APAC countries along with notable opportunities in medical device manufacturing in Europe and North America.
Customer reviews
0 ratings
0 AWS reviews
|
3 external reviews
Star ratings include only reviews from verified AWS customers. External reviews can also include a star rating, but star ratings from external reviews are not averaged in with the AWS customer star ratings.
Mazibar R.
Automatically identifying defects using image processing
Reviewed on Oct 08, 2024
Review provided by G2
What do you like best about the product?
On our part, the PCB Defect Detector has proven to be an important tool for effectively handling our PCB inspection. It can easily identify simple issues such as missing holes and shorts and so we are able to identify problematic boards for further review.
What do you dislike about the product?
The PCB Defect Detector is rather insensitive in its ability to distinguish between some of the defects or when the defects have faint features. It can also have issues with the differentiation between small and large solder bridges.
What problems is the product solving and how is that benefiting you?
Since PCB Defect Detector works independently the time my team consumes on PCB inspection has greatly reduced though the system cannot determine the root cause of the defects and implement corrective actions on its own.
Patric G.
Efficient and Reliable PCB Defect Detector
Reviewed on Oct 02, 2024
Review provided by G2
What do you like best about the product?
I personally like the software user interface (UI), which I find extremally intuitive and suitable for operators with minimal technical knowledge. In terms of performance, the software processes PCB images fairly quickly, depending on the resolution and the number of layers involved. For single-layer PCBs, detection times are quick and efficient. Multi-layer boards, however, can slow down the detection slightly.
Overall extremely happy with the software functionality.
Overall extremely happy with the software functionality.
What do you dislike about the product?
One of the main issues that I found with the PCB detector is the occasional risk of false positives/negatives on complex boards and I encounter some slower performance with multi-layer boards or when using extremely high-resolutions images.
What problems is the product solving and how is that benefiting you?
It helps me to prevent and forecast any commonly PCB defect. It gives more security to my clients and operators to use our designed PCB program.
Yousaf M.
Best tol to finalize the design
Reviewed on Oct 28, 2022
Review provided by G2
What do you like best about the product?
The best thing is to analyze the design and finalize it more conveniently than other tools. I have completed almost 30 structures with the help of this fantastic tool
What do you dislike about the product?
There is not much to dislike, but according to my use, I would suggest improving the GUI and interface a little more so its more user-friendly and a newcomer can work
What problems is the product solving and how is that benefiting you?
Once a design is completed, it's harder for the designer to review and find any faults or defects, and asking someone increases time. I have completed work before deadlines with its help