DCT
2:21-cv-02252
FaceTec Inc v. iProov Ltd
I. Executive Summary and Procedural Information
- Parties & Counsel:
- Plaintiff: FaceTec, Inc. (Delaware)
- Defendant: iProov LTD (United Kingdom)
- Plaintiff’s Counsel: Weide & Miller, Ltd.; One LLP
- Case Identification: 2:21-cv-02252, D. Nev., 12/28/2021
- Venue Allegations: Plaintiff alleges venue is proper because Defendant has transacted business and committed acts of patent infringement in the District of Nevada. As a foreign entity, Defendant may be sued in any judicial district.
- Core Dispute: Plaintiff alleges that Defendant’s “Liveness Assurance” biometric software infringes a patent related to 3D liveness detection technology.
- Technical Context: The technology involves using software to verify that a person presenting their face for biometric authentication is a live human and not a 2D artifact like a photo or video, a critical security measure for remote account access and identity verification.
- Key Procedural History: The complaint alleges that Defendant’s employees participated in Plaintiff’s confidential “Spoof Bounty Program,” which granted them access to Plaintiff’s software and technology. Plaintiff claims Defendant then used information learned from this program to reverse engineer and develop its own competing product. Plaintiff alleges it sent a cease and desist letter in September 2021, providing Defendant with pre-suit notice of the patent-in-suit.
Case Timeline
| Date | Event |
|---|---|
| 2014-08-28 | Earliest Priority Date for '471 Patent |
| 2019-10-01 | FaceTec launches "Spoof Bounty Program" (approx. date) |
| 2020-06-01 | iProov employee allegedly begins "Level 5" attacks (approx. date) |
| 2021-01-31 | iProov employee allegedly concludes participation (approx. date) |
| 2021-01-01 | iProov releases "Liveness Assurance" software (approx. date) |
| 2020-09-15 | U.S. Patent No. 10,776,471 Issues |
| 2021-09-09 | FaceTec sends cease and desist letter to iProov |
| 2021-12-28 | Complaint Filed |
II. Technology and Patent(s)-in-Suit Analysis
U.S. Patent No. 10,776,471 - "Facial Recognition Authentication System Including Path Parameters," Issued September 15, 2020
The Invention Explained
- Problem Addressed: The patent describes a need for a reliable and convenient method to authenticate users for digital accounts that overcomes the security flaws of two-dimensional facial recognition, which can be spoofed by photographs or video recordings. ('471 Patent, col. 2:1-2).
- The Patented Solution: The invention uses a standard camera on a computing device to capture at least two images of a user's face at different distances. By moving the device closer or farther away, the system can analyze the resulting "fish-eye" distortion effect, where facial features change in relative proportion. This predictable distortion, which does not occur when imaging a flat photo, is used to confirm the presence of a live, three-dimensional person. ('471 Patent, col. 27:46-col. 28:54; Abstract).
- Technical Importance: This approach enables 3D liveness detection using the ubiquitous 2D cameras and motion sensors found in modern smart devices, eliminating the need for specialized and expensive hardware like infrared or stereoscopic cameras. (Compl. ¶16).
Key Claims at a Glance
- The complaint asserts "at least claim 10" of the '471 patent. (Compl. ¶37).
- Independent Claim 10 is a method claim with the following essential elements:
- Capturing a first image of a user at a first distance.
- Processing the first image to create first data.
- Moving the camera to a second, different distance.
- Capturing a second image of the user at the second distance.
- Processing the second image to create second data.
- Comparing the first and second data to determine if "expected distortion" exists, indicating three-dimensionality.
- Authenticating the user when the comparison reveals this expected distortion.
III. The Accused Instrumentality
Product Identification
- The accused instrumentality is Defendant's "Liveness Assurance" software product. (Compl. ¶3).
Functionality and Market Context
- The complaint alleges that "Liveness Assurance" is a biometric liveness detection software that directly competes with Plaintiff's product. (Compl. ¶3). Its stated purpose is to verify that a face presented to a device is a live human and not a spoof artifact like a photo or mask. (Compl. ¶28). The complaint alleges that the accused product incorporates a technique, referred to as "Camera Cycling," that requires users to provide images of their face from at least two different distances to perform the liveness check. (Compl. ¶31). The complaint includes a visual that simulates the principle of perspective distortion by showing how a face's proportions change between a "First Image" taken from farther away and a "Second Image" taken from a closer distance. (Compl. p. 5).
IV. Analysis of Infringement Allegations
'471 Patent Infringement Allegations
| Claim Element (from Independent Claim 10) | Alleged Infringing Functionality | Complaint Citation | Patent Citation |
|---|---|---|---|
| A method for authenticating three-dimensionality of a user ... capturing at least one first image of the user taken with the camera of the computing device at a first location which is a first distance from the user; | Defendant's "Liveness Assurance" software allegedly includes a user interface that requires users to provide images of their face from at least two different distances. The first image capture constitutes this element. | ¶31 | col. 27:50-54 |
| moving the camera from the first location to a second location ... to change the distance between the user and the camera from the first distance to a second distance; | The process of capturing images at two different distances inherently requires moving the camera (or the user's head) from a first position to a second position. | ¶31 | col. 27:50-54 |
| capturing at least one second image of the user taken with the camera ... at the second distance from the user, the second distance being different than the first distance; | The "Liveness Assurance" software allegedly requires a second image capture at a different distance from the first. | ¶31 | col. 27:50-54 |
| comparing the first data to the second data to determine whether expected distortion exist between the first data and the second data which indicated three-dimensionality of the user; | The complaint alleges that Defendant's product was developed using confidential information about Plaintiff’s technology, which relies on measuring "perspective distortion" between images taken at different distances. The infringement theory is that Defendant's product performs this same comparison. | ¶¶12, 13, 32 | col. 28:46-col. 29:19 |
| authenticating the user when the differences between the first data and the second data have expected distortion... | The purpose of "Liveness Assurance" is to confirm a user is a "real person" and not a spoof artifact, thereby authenticating the user's liveness based on the outcome of its analysis. | ¶28 | col. 29:14-19 |
Identified Points of Contention
- Technical Questions: A primary point of contention may be evidentiary. The complaint alleges that Defendant's product uses the claimed method based on information allegedly learned from Plaintiff's bounty program (Compl. ¶¶30-32), but it does not provide a detailed technical breakdown of how the accused "Liveness Assurance" software actually operates. This raises the question of what evidence Plaintiff will produce to demonstrate that the accused software performs the specific "comparing" step to detect "expected distortion," as required by the claim, rather than an alternative, non-infringing method for liveness detection.
- Scope Questions: The definition of "data" (e.g., "first data," "second data") as used in the claim may become a point of dispute. It is an open question whether the term requires the creation of a specific biometric template or if it could be read more broadly to include cropped or otherwise minimally processed image information.
V. Key Claim Terms for Construction
The Term: "expected distortion"
Context and Importance: This term is central to the invention, as it defines the technical phenomenon used to distinguish a live 3D person from a 2D spoof. The construction of this term will likely determine the scope of infringement, as it defines precisely what the accused product must be "comparing" to infringe.
Intrinsic Evidence for Interpretation:
- Evidence for a Broader Interpretation: The claim language itself is general, which may support an interpretation that covers any predictable difference between two images of a person taken at different distances.
- Evidence for a Narrower Interpretation: The patent specification repeatedly and explicitly describes the "fish-eye" effect, where the "relative dimensions of the person's face appearing different," such as the nose appearing "as much as 30% wider and 15% taller" at close proximity. ('471 Patent, col. 28:46-54). A party could argue this detailed description limits the term to this specific type of proportional distortion.
The Term: "processing the at least one first image or a portion to create first data"
Context and Importance: Practitioners may focus on this term because its definition clarifies the nature of the "data" that is ultimately compared. The case may turn on whether Defendant's software "creates data" in the manner required by the claim.
Intrinsic Evidence for Interpretation:
- Evidence for a Broader Interpretation: The specification suggests the processing could be as simple as locating and cropping a face from an image, stating, "The portion of the photo that contains the detected face may then be cropped, cut, and stored for processing." ('471 Patent, col. 7:48-50). This may support a construction where "data" can be the image portion itself.
- Evidence for a Narrower Interpretation: The specification also defines "facial recognition" as a process that converts facial features into "biometric data, such as numeric data." ('471 Patent, col. 7:31-35). This could support a narrower construction requiring the creation of a distinct biometric template or numeric representation, not just a cropped image.
VI. Other Allegations
- Indirect Infringement: The complaint alleges active inducement, stating that Defendant provides "on screen visual guidance and/or online instructional materials" that instruct customers to use the "Liveness Assurance" product in an infringing manner. (Compl. ¶38). It also alleges contributory infringement, claiming the accused product is a non-staple article of commerce with no substantial non-infringing use. (Compl. ¶39).
- Willful Infringement: The complaint alleges willfulness based on both pre- and post-suit knowledge. Pre-suit knowledge is alleged based on a September 2021 cease-and-desist letter (Compl. ¶37) and, more notably, on Defendant's alleged participation in Plaintiff's "Spoof Bounty Program," through which Defendant allegedly gained direct access to and knowledge of the patented technology before launching its competing product. (Compl. ¶¶27, 32, 44).
VII. Analyst’s Conclusion: Key Questions for the Case
- A central issue will be one of claim construction: can the term "expected distortion," which is described in the patent specification with specific reference to the "fish-eye" effect and proportional changes in facial features, be construed more broadly to cover any predictable difference between images taken at varying distances?
- A key evidentiary question will be one of technical proof: beyond the narrative of reverse engineering, what technical evidence can Plaintiff provide to demonstrate that Defendant's "Liveness Assurance" software performs the specific method of "comparing" data to detect "expected distortion" as required by Claim 10, or does it utilize a technically distinct, non-infringing process to achieve liveness detection?
- A third question, intertwined with the patent claims, will be the impact of the non-patent allegations. The court will need to determine whether the extensive allegations of bad faith conduct, such as breach of contract and misuse of confidential information, can be substantiated and, if so, how that factual context informs the analysis of infringement and willfulness for the patent-specific claims.