Built libraries and public C headers. 12ms per frame on CPU only, no GPU required. Over 8 years and more than 100 units deployed.
To manufacturers and system integrators who want to incorporate AI inspection features into devices that handle images: DeepAge Sensor is provided as a pre-built inference library (Windows/UNIX). You only need to reference one public C header (extern "C"). It works simply by linking in C/C++ or loading with ctypes in Python. The CPU version requires no GPU, CUDA, or drivers, and operates at 12ms per image (the GPU version operates at 2ms). Training is done on our cloud, and only the model file is distributed to the devices, so there is no need to rebuild the device software every time the model is updated. An unsupervised anomaly detection library (.uai) can also be used with the same API structure. We will provide a library and sample model for evaluation, so you can first check if create→load→inference works in your environment. OEM/white label offerings are available. Your company will handle primary support, while we will provide secondary support.
Inquire About This Product
basic information
【Provided Items】Built inference library (GPU version and CPU version) + public C header (inference.hpp) + model files (.ai/.uai) + complete self-test for operation confirmation 【Operating Requirements】CPU version: No GPU, CUDA, or driver required (12ms per image) / GPU version: NVIDIA sm_86 or later, CUDA 13.2 series (2ms per image) 【OS】Windows / UNIX (Linux x86_64) 【API】Four stages: create → load → inference → close (6 functions). Unsupervised anomaly detection follows the same structure 【Model Update】Only file replacement is needed. No need to rebuild the device software 【Support Responsibility】Primary: Your company / Secondary: Our company (technical separation and bug response)
Price information
OEM royalty (based on the ratio to the equipment's main price) individual quotation / evaluation library and sample model provided.
Price range
P3
Delivery Time
P3
※The initial model creation is free (accuracy report in as little as one week).
Applications/Examples of results
- OEM integration of AI inspection functions into products of inspection equipment manufacturers (over 100 units implemented since the start of provision in 2018, 8 years ago) - Supports both retrofitting inspection options to existing models and standard installation in next-generation models - Proven track record of deployment in equipment for overseas markets, including China
Detailed information
-
8 years of experience with over 100 devices installed and key specifications.
-
Three learning methods. The unsupervised anomaly detection library has the same API structure.
-
Learning is done in the cloud, and inference is performed only by the device's CPU. Model updates are done solely by replacing files.
-
1. Receipt of evaluation library 2. Operation confirmation with self-test 3. Application integration 4. Model creation in actual work (first time free)
-
6 industries and various defects addressed (solder defects/scratches/dents/burrs/chips/foreign objects/missing items/printing defects)
catalog（2）
Download All Catalogs
Company information
We provide services that utilize data. The value generated from data has been increasing day by day. While there may be a focus on chasing numbers in sales targets and marketing, the importance of processing large amounts of data with computers to create new value has not been emphasized as much. Technology is evolving every day. We have become capable of gathering various data in the cloud and processing large volumes of data. However, even with an understanding of such technologies and their value, practical implementation is still not sufficiently realized. We will accurately understand the current issues, sincerely consider whether artificial intelligence and new technologies can solve them, and communicate our findings to the world in the most optimal way.
![[VE Evaluation] Weather Risk Management Mobile 'KIYOMASA PRO'](https://image.www.ipros.com/public/product/image/2110087/IPROS2916142205131244335.png?w=280&h=280)
