Our face recognition algorithm has achieved 99.78% in LFW benchmark, which is in level 3 - the world’s top level.
LFW database consists of face photographs designed for studying the problem of unconstrained face recognition.
The data set contains more than 13,000 images of celebrities collected from the web.
Most of the databases used for benchmark of face recognition have been created under controlled conditions to facilitate the study of specific parameters on the face recognition problem.
These parameters include such variables as position, pose, lighting, expression, background, camera quality, occlusion, age, and gender.
The LFW database exhibits “natural” variability in pose, lighting, focus, resolution, facial expression, age, gender, race, accessories, make-up, occlusions, background, and photographic quality encountered by people in their everyday lives.
Face recognition algorithms from the World’s famous corporations, universities and institutions like Google and Baidu have participated in LFW database benchmark and LFW has been the most popular evaluation benchmark for face recognition in real situation.
In LFW benchmark, face recognition algorithms are to judge whether randomly chosen pairs of face images belong to the same person or not.
We have developed a facial feature extraction model based on Deep Neural Network.
The deep neural networks used for feature extraction model have been trained on a database which consists of 3,100,000 photos of 59,000 celebrities collected from the Web.
We trained two different embedding models based on 8 patchs of face region achieved  99.77%,  99.75%  pair-wise classification accuracy respectively. 
In each model which is composed of 8 DNNs, the feature vectors from 8 DNNs are concatenated and transformed to low-dimensional  vector by subspace method and metric learning.
And then distance between two feature vectors is measured by Euclidean distance mesure.
The final distance between two faces is computed by linearly combination of distances from two models.

The following table shows top 6 stae-of-the-art performance in LFW benchmark.

Our face recognition algorithm has been tested under Unrestricted, Labeled Outside Data protocol of LFW benchmark.
This protocol is to test the accuracy in the 6000-pair verification task.
Figure 1 shows examples of correctly classified pairs from LFW database by our face recognition algorithm.
The example images shown in Figure 1 are considered difficult to recognize because of various pose, expression and occlusion.

Figure 1. Examples of correctly classified pairs of the same person.
Figure 2 shows all misclassified pairs.
Our algorithm produced 13 misclassified pairs out of 6,000 and 5 of them are mislabeled in the database, which means the actual number of misclassified pairs is 8.


(b)False Acepted Pairs
Figure 2. Pairs Failed in LFW benchmark. (a) False Reject Pairs. (b) False Accept Pairs. The score under the image is the distance between two feature vectors from above pair.
In the figure, the ones in red boundary are mislabeled pairs.