Deep learning is a sub-field of Machine Learning and a significant branch of Artificial Intelligence. It aims to infer high-level abstractions from raw data by using a deep graph with multiple processing layers composed of multiple linear and non-linear transformations. Deep learning is loosely based on models of information processing and communication in the brain. Deep learning replaces handcrafted features with ones learned from very large amounts of annotated data. Learning occurs by iteratively estimating hundreds of thousands of parameters in the deep graph with efficient algorithms.
Several deep learning architectures such as convolutional deep neural networks (CNNs), and recurrent neural networks have been applied to computer vision, speech recognition, natural language processing, and audio recognition to produce state-of-the-art results on various tasks.
ProtoTech is one of the pioneering companies to apply deep learning principles to 3D data. ProtoTech 3D Measure Up service use deep learning to understand 3D body scans and recognize features.

No. With ProtoTech 3D Measure Up , you don’t have to build, maintain or upgrade deep learning pipelines.
To achieve accurate results on complex 3D scans such as feature detection, mesh processing, point cloud manipulations, geometry computations deep learning systems need to be tuned properly and trained with massive amounts of labeled ground truth data. Sourcing, cleaning, and labeling data accurately is a time-consuming and expensive task. Moreover, training a deep neural network is computationally expensive and often requires custom hardware built using Graphics Processing Units (GPU).
ProtoTech 3D Measure Up is fully managed and comes pre-trained for 3D body scan recognition and measurement tasks, so that you don’t have invest your time and resources on creating a deep learning pipeline. ProtoTech 3D Measure Up continues to improve the accuracy of its models by building upon the latest research and sourcing new training data. This allows you to focus on high-value application design and development.

The most common use-cases for 3D Measure Up include:

• Custom fitted apparels for comfort, fashion, sports and medical industries
• 3D scanner, LIDAR scanner companies can provide white-labelled software with their hardware
• Health, fitness and wellness companies to track their clients’ physical wellness progression
• Automotive, Aerospace, Marine, Furniture, Design engineers for ergonomic analysis
• eTailers, eCommerce companies to reduce return of fashion ware because of misfit
• Innerwear, Intimatewear, Lingerie companies improve customer satisfaction by providing best fit products
• Doctors can design custom orthotics, prosthetics, compression socks, insoles etc. for their patients
• Real life look-a-like avatars for digital media and gaming

If you are not already signed up for ProtoTech 3D Measure Up , you can click the “Try ProtoTech 3D Measure Up ” button on the ProtoTech 3D Measure Up page and complete the sign-up process. Once you are signed up, try out ProtoTech 3D Measure Up with your own 3D scans download the ProtoTech 3D Measure Up SDKs to start creating your own applications. Please refer to our step-by-step Getting Started Guide for more information.

ProtoTech 3D Measure Up offers APIs to detect landmarks and features of a 3D body scan, measure heights, measure straight distances, measure distances along the body surface, measure girths, compute volumes. For details, please refer to the ProtoTech 3D Measure Up API Reference.

ProtoTech 3D Measure Up currently supports the OBJ format.You can submit 3D scan either as an S3 object or HTTP URL such as Google Drive or Dropbox file URL. ProtoTech 3D Measure Up can analyze 3D scans stored in ProtoTech S3 buckets or Customer’s S3 buckets. The 3D scan must be in OBJ format. If you would like us to support a different format, you can contact us here.

ProtoTech 3D Measure Up supports 3D scan file sizes up to 20MB.

ProtoTech 3D Measure Up works across a wide range of 3D body scan resolutions. The accuracy of location of the landmarks and it’s measure increases with the increase in scan resolution. This is obvious because you have more points and thus more details in high resolution scans. At the same time, it is important to remember that there is a limit on the file size that can be processed. Further, the higher the resolution, more time it will take to process the scan for identification and measurement. For most of the applications, scans with file size up to 20 MB should be good enough.

There is no such condition. You are free to provide very small sized scans as long as it contains enough details to visibly identify the landmarks (by a human being) and the precision of the measurement obtained is acceptable to you.

Besides scan resolution, other factors that can impact are

• Quality of mesh: The mesh should be single and ideally be water tight with no gaps.
• Pose: The ideal pose for scan is standing with arms straight and pointing downwards (‘A’ pose).
• Clothing and other accessories: The clothes should tight fitting to get accurate measurements. Accessories straying out of body surface or altering profile is best avoided.
• Hair style and other accessories: Hair should ideally be tied and tucked neatly as close as possible to the head.
• Quality of scan: The scan should be clear and isolated. There should be no stray objects or points in the scan.

This API works best with consumer and professional scans. Ideally position is standing, looking straight, arms out-stretched and pointing downwards – what is also known as ‘A’ pose. The ideal outfit is minimal and body hugging. If the person has long hair, then it should be tied and tucked such that it doesn’t interfere with the measurement. Applications that are sensitive to false alarms are advised to discard outputs with confidence score below a selected (application-specific) confidence score. Please contact our technical support for details on accessing ‘confidence score’

ProtoTech 3D Measure Up supports 3D scan file sizes up to 20MB. For larger file sizes, please contact us.