iWave i.MX8M Mini Board with NXP eIQ ML Software Enables Low Cost Facial Recognition System

iWave i.MX8M Mini Board with NXP eIQ ML Software Enables Low Cost Facial Recognition System

Have you recently been sceptical of using a contact-based access system in your office or a public place? This trait is a major concern in most places for a valid reason. An access surface in a public place is used by many individuals, which makes it a potential source for contracting the deadly Covid 19 virus. Taking this into account, iWave Systems, a leading embedded solutions provider, has successfully demonstrated an alternative solution using facial recognition technology. The solution helps customers with a zero-contact access application by using individuals’ faces to authorize access to a commercial/industrial space, home/office, transportation, banking, and Government sites.

Facial Recognition:

Facial Recognition is the process of recognizing the identity of a person by using their facial features against a previously stored database.

It is a technology that uniquely identifies or verifies a person by comparing and analysing patterns based on the person’s facial details. The face capture process transforms the analogy information into a set of digital information, while the face match process verifies the information with a database of known faces to find a match.

iWave Solution :

The facial recognition demo is running on iWave’s development board based on the NXP® i.MX8M Mini applications processor. The power-efficient edge computing platform with a SODIMM form factor is coupled with a MIPI Camera module (1080p@30 fps) , MIPI Display (1920 x1080 60fps), and multiple connectivity options. Through the support of key features such as camera, display, connectivity, and the NXP eIQ machine learning software, the i.MX 8M Mini board provides an intelligent platform for the development of facial recognition systems.

Demo Environment

The captured image and stored images are fed to the application to recognize the faces. eIQ OpenCV ML software compares the novel face features with the known face images in the Django framework database. Real-time data logging can be configured to send the information with alert for authorized or unauthorized detection.

NXP eIQ OpenCV Machine Learning Software:

 iWave i.MX8M Mini board is integrated with the NXP eIQ OpenCV machine learning softwarewhich enables faster time to market while reducing the development complexity. The eIQ software includes pre-optimized libraries and tools to perform machine learning and computer vision applications. The eIQ software enables developers to accelerate the development flow of the ML applications by taking full advantage of the underlying i.MX8M Mini SoC. The software supports C++/Python/Java API’s which provides the programming flexibility to the developers.

Why iWave?

 iWave Systems Pvt. Ltd., with vast expertise in NXP platforms, provides a wide range of custom and standard NXP System on Modules –i.MX6 , i.MX8i.MX8M, i.MX8X and i.MX8M mini/nano. iWave assures customers of product longevity of 10+ years, providing custom design services and long term technical support. iWave can help customers with custom design implementation, porting trained models, hardware, and software pipeline optimization for machine learning functions on the i.MX8M.

More detailed information on the i.MX8M Mini board can be found here.

To get in touch with us for enquiries and further information, please write to mktg@iwavesystems.com or contact our Regional Partners.

Please follow and like us:
Pin Share
About mixos

Mike is the founder and editor of Electronics-Lab.com, an electronics engineering community/news and project sharing platform. He studied Electronics and Physics and enjoys everything that has moving electrons and fun. His interests lying on solar cells, microcontrollers and switchmode power supplies. Feel free to reach him for feedback, random tips or just to say hello :-)

view all posts by admin
Subscribe
Notify of
guest

0 Comments
Inline Feedbacks
View all comments
Get new posts by email:
Get new posts by email:

Join 97,426 other subscribers

Archives