Cupertino, CA, December 20, 2022 – Aizip, Inc., a technology leader in artificial intelligence (AI) for applications on the Internet of Things (IoT), also known as tiny machine learning (TinyML), announced today the volume shipping of robust vision models.
Computer vision is one of the AI fields that trains and enables computers to capture and interpret information from image and video data. By applying machine learning (ML) models to images, computers can classify objects and respond accordingly. Over the last decade, the marketplace has witnessed a wide range of AI vision applications, such as package detection in doorbells, face recognition in smart locks, symptom diagnosis in healthcare, defect detection in production lines, and object detection in self-driving cars, among many others.
Aizip started with its first TinyML model in Visual Wake Words (VWW) at its inception in 2020. Since then, the company has developed multiple vision models for a wide range of applications. Aizip’s face detection and recognition models were successfully developed and deployed on ARM Cortex M4 devices, and a very compact object detection model has been designed and extended to support tracking and counting applications. The License-Plate-Reading (LPR) model, which handles automobile license plate reading, has also been enhanced to work with street signs.
“We are very excited with the release and volume shipping of our robust vision models,” said John Rea, Chief Operations Officer of Aizip. There is a huge gap between a demo model on a given dataset and a production model for real-world applications. For the VWW model, as shared by Rea, the Aizip team spent significant time and resources to tackle low light conditions and night vision environments, in addition to using a large amount of diversified image backgrounds for training and validation testing. The experience and expertise they gained in the VWW model has been used to enhance the robustness of other Aizip Intelligent Vision (AIV) models.
Aizip’s robust AIV models have been qualified by its customers and have started volume shipping, according to Taixiang Shi, who leads the customer support team at Aizip. “The vision models have been tested extensively in normal and challenging conditions, and the customers are happy with what they have seen with our models. We’ve seen strong growth in computer vision markets, such as smart home and intelligent manufacturing.” Aizip is in a leading position to support its customers to win in this fast-growing market.
Together with the volume shipping of Aizip Intelligent Audio (AIA) models that Aizip announced last quarter, the company is providing a comprehensive suite of production-quality models for the IoT market. Aizip provides TinyML models to its IC partners and module and system customers worldwide and is committed to developing low-cost and high-performance intelligence for the benefit of society worldwide. For more information, please contact info@aizip.ai.
* * *
About Aizip, Inc.
Aizip, Inc., develops AI models for edge applications. Based in Silicon Valley, Aizip provides models with superior performance, quick turnaround time, and excellent ROI. These models can be used in a wide range of applications for an intelligent, automated, and connected world. For more information, visit www.aizip.ai.