# Face Verification on LFW BLUFR protocol (test) Source: [Face Verification on LFW BLUFR protocol (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:04.751Z Evaluation of face verification performance on the Labeled Faces in the Wild (LFW) dataset specifically using the BLUFR protocol on the test set, measured by Verification Rate at a 0.1% False Acceptance Rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Face Verification | | Dataset (including any stated split) | LFW BLUFR protocol (test) | | Metric | VR @ FAR=0.1% | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [VR @ FAR=0.1%](): Higher is better; unit: PERCENT. ## Recorded results | Method | VR @ FAR=0.1% | Result date | Report paper | | --- | --- | --- | --- | | Proposed Deep Model | 87.65 | Not recorded | 68fa61fe1e209131ce9f6faa | | Proposed Deep Model | 83.39 | Not recorded | 68fa61fe1e209131ce9f6faa | | Li et al. | 80.26 | Not recorded | 68fa61fe1e209131ce9f6faa | | COTS | 58.56 | Not recorded | 68fa61fe1e209131ce9f6faa | | HDLBP+JB | 41.66 | Not recorded | 68fa61fe1e209131ce9f6faa | | HDLBP+LDA | 36.12 | Not recorded | 68fa61fe1e209131ce9f6faa | ### Proposed Deep Model VR @ FAR=0.1%: 87.65. Result ID: 698bd0e77a967eddb7718e36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of nets":"7","metric":"Cosine"}. This record does not assert independent reproduction. ### Proposed Deep Model VR @ FAR=0.1%: 83.39. Result ID: 698bd0e77a967eddb7718e35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"number of nets":"1","metric":"Cosine"}. This record does not assert independent reproduction. ### Li et al. VR @ FAR=0.1%: 80.26. Result ID: 698bd0e77a967eddb7718e33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setting":"Joint-Bayes"}. This record does not assert independent reproduction. ### COTS VR @ FAR=0.1%: 58.56. Result ID: 698bd0e77a967eddb7718e34. [Reporting paper]() Recorded evaluation configuration: {"Training Setting":"N/A"}. This record does not assert independent reproduction. ### HDLBP+JB VR @ FAR=0.1%: 41.66. Result ID: 698bd0e77a967eddb7718e31. [Reporting paper]() Recorded evaluation configuration: {"Training Setting":"Joint-Bayes"}. This record does not assert independent reproduction. ### HDLBP+LDA VR @ FAR=0.1%: 36.12. Result ID: 698bd0e77a967eddb7718e32. [Reporting paper]() Recorded evaluation configuration: {"Training Setting":"LDA"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.