One REST call tells face recognition and eKYC systems whether a live person is in front of the camera, from a single still image. No client library to install.

TSUKUBA, IBARAKI, JAPAN, October 15, 2026 /EINPresswire.com/ — Swallow Incubate Co., Ltd., a Japanese developer of computer-vision AI for human sensing, today announced that its Liveness Detection API now runs the latest generation of the company’s anti-spoofing model and is open to developers worldwide with a free tier. With a single REST API call, the service tells a face recognition system or an eKYC (online identity verification) flow whether the face in front of the camera belongs to a live person or is a presentation attack: a printed photo, or a photo shown on a smartphone or tablet screen.

Face recognition is now used to open doors, record attendance, and verify identities online. One of the simplest ways to defeat it is to show the camera someone else’s picture. Liveness detection stops this at the moment of capture.

Swallow Incubate’s liveness detection technology is already in production in Japan, in authentication solutions for major medical institutions, access control terminals, and time and attendance terminals. The API delivers the same detection technology over the cloud.

One still image, one API call

Developers send a Base64-encoded JPEG or PNG image (up to 10 MB) to POST /v1/check/liveness and receive a JSON response containing a real-or-spoof verdict, a spoofing likelihood score from 0.0 to 1.0, face brightness, and the detected face position. There is no client library to embed, no build environment to maintain, and no per-OS binaries to manage. The service is operated with a target response time of 500 ms or less per request.

Latest model built for unseen conditions

The latest anti-spoofing model focuses on generalization: stable decisions not only on the data it was validated on, but also in unfamiliar capture environments and against new attack patterns. In an internal evaluation using approximately one million frames of the company’s own test data, the model achieved 99.9% detection accuracy.

Note: This figure comes from an internal evaluation using the company’s own test data at the standard decision threshold. It is not a value certified by a third-party accreditation body.

Start free, no sales call required

A Free plan includes 50 calls per month for evaluation. Paid plans start at $180 per month for 1,000 calls, and only successful responses count toward usage. Sign-up is fully self-service: there is no need to contact sales, request a quote, or negotiate a contract, and developers can send their first request the same day.

Designed with data protection in mind

The service is hosted in Tokyo, Japan. Images submitted for evaluation are held in memory only for the duration of processing and are not persistently stored. The service is designed and operated with the company’s obligations as a data processor under the GDPR in mind, and a Data Processing Agreement (DPA) is available on request. Swallow Incubate is also working toward ISO/IEC 27001 (ISMS) certification. The service is operated with a target monthly uptime of 99.5%.

Availability

Plans, pricing, and sign-up: https://bio-check.pas-ta.io/en/
API reference, quickstart, and sample code: https://docs.pas-ta.io/liveness/en/
Demo video: https://youtu.be/4aT4CqQoUmQ

About Swallow Incubate

Founded in 2013 and headquartered in Tsukuba, Japan, Swallow Incubate researches and develops computer-vision AI in the field of human sensing. The company holds patents jointly filed with Panasonic Corporation in Japan and overseas, and provides proprietary technologies including liveness detection, blink detection, gaze detection, and iris recognition.

Swallow Incubate operates under licenses and sublicenses to certain intellectual property rights held by other parties, for the purpose of utilizing and promoting such intellectual property. Information in this release is current as of the date of publication and is subject to change without notice.

Technical Support Office
Swallow Incubate Co., Ltd.
support@swallow-incubate.com
Visit us on social media:
X

Detecting presentation attacks: printed photos and screens

Legal Disclaimer:

EIN Presswire provides this news content “as is” without warranty of any kind. We do not accept any responsibility or liability
for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this
article. If you have any complaints or copyright issues related to this article, kindly contact the author above.

Media gallery

About The Author
Written By: EIN Presswire