Eye detection/blink detection technology
Eye detection/blink detection technology
By using the "eye detection technology" (RGB version), you can detect "blinking," "viewing distance," and "eye feature points" with a webcam.
The "joint patent technology" and "eye detection technology (RGB version)" utilizing "deep learning" developed by Panasonic and our company are highly versatile elemental technologies that allow for easy measurement of "blinking," "eye feature points," and "viewing distance (the distance from the camera to the eye)" using web cameras or device cameras on PCs. The detection uses a learning model based on deep learning, and we have compressed the learning model to achieve a processing speed of 50 to 60 ms per frame even with CPU processing (on our company's Windows machine with an 8th generation Core i7 CPU). We offer an SDK and an application, with the application supporting CSV output and recording functions, making it suitable for more than just real-time verification. The application is available in both "camera input version" and "file input version."
Inquire About This Product
basic information
Features of "Eye Detection/Blink Detection Technology" 1. Easily usable with WEB cameras/smartphone cameras Developed to be usable with familiar "visible light cameras (RGB)." (Can be used with glasses) 2. Capable of detecting "blinks," "viewing distance," and "presence of glasses" By detecting eye feature points and estimating viewing distance for each frame, it becomes possible to detect "blinks." Additionally, it can determine whether glasses are present and whether they are clear lens glasses or sunglasses. 3. Unique algorithm x deep learning (mask-friendly) By combining a unique "image processing method, detection algorithm" with deep learning, we have achieved high-precision detection of information related to human eyes. Detection is also possible while wearing a mask. 4. Optimized for edge AI, with a deep learning model capable of fast processing using only CPU By compressing the deep learning training model as much as possible, it can be processed quickly without a GPU. With recent Core i5/i7 processors, processing can be achieved at 50-60ms per frame.
Price information
Please contact us. For more details, please visit our website.
Price range
P2
Delivery Time
P1
Applications/Examples of results
◆Uses - Various applications for detecting blinking - Various applications for measuring the distance between the eyes and smartphones or PCs
News about this product（1）
Company information
We research, develop, and provide core technologies for human sensing, built on deep-learning-based image processing. ◆ Liveness Detection (Anti-Spoofing) Technology This technology combines "Fake Face Detection," which determines whether a face presented on a photograph or a smartphone screen is a spoof or a real person, and "Action Detection," which determines whether the user performs the instructed action, to prevent spoofing. https://bio-check.pas-ta.io/ ◆ Eye Detection / Blink Detection Technology This highly versatile core technology measures "blinks," "eye feature points," and "viewing distance (the distance from the camera to the eye)" using a webcam or a PC's built-in camera. https://pupil.pas-ta.io/ ◆ Gaze Detection Technology This technology analyzes camera input or video files to detect a person's "gaze direction" and "face orientation." https://eyetrack.pas-ta.io/ ◆ Iris Recognition Technology This recognition technology uses the unique pattern of the "iris" in a person's eye, which is not duplicated between individuals. It is currently provided only to partners engaged in the joint development of iris capture cameras. https://iris.pas-ta.io/
