We have been engaged in in-depth analysis and research on humanoid detection and tracking,face detection and tracking, face key point detection, face attribute recognition, face verification and recognition, generic object detection and division, video behavior analysis and retrieval, human posture evaluation, REID, binocular stereo vision, cross-camera linkage tracking and other aspects, achieved impressive results and successfully applied in different environmental areas of different industries.
The ULUCU face recognition algorithm uses the latest neural network and face technology to conduct in-depth research and commercialization of face detection, attribute analysis, face key point detection, face verification, and face recognition. This meets the needs of personnel identification in different scenarios.
Detect face in picture, make precise positioning and mark face coordinates.
Face Attribute Analysis
Detect face in picture and analyze a series of features including age, gender, emotion, appearance and other properties in multiple dimensions.
Face Key Point Detection
Locate and detect key points of a face in picture including outline, eyebrows, eyes, nose and mouth.
Detection scenarios target at whether it is an "immortal" living body and proposing score-based reference.
Conduct 1:N retrieval in large-scaled face database, find out one or more faces with the highest similarity, and support rapid search in MEGA face database.
Conduct 1:1 comparative verification to information of two faces, and get face similarity to determine whether it is the same person.
Have made analysis and experiments on various network structures, cost functions and training methods, accumulating rich experience.
Through the research on various latest neural network architectures, various models are designed to adapt to different operating environments, and can flexibly run on server-side, front-end industrial control machines, and front-end embedded devices.
FRVT Top 10 In The World
In July 2019, ULUFACE Listed in top ten in FRVT, the most authoritative face recognition algorithm test in the world.(FRVT, hosted by National Institute of Standards and Technology (NIST) directly subordinated to U.S. Department of Commerce, is established mainly to build up national metering benchmark and standard to improve national technology foundation and improve industry products and services. )
MEGAFACE Top 5 In The World
In July 2018, ULUFACE face recognition technology MEGAFACE ranks in the top five in the world.(MEGAFACE CHALLENGE is the first contest to evaluate MEGA face recognition algorithm in the world, released and maintained by University of Washington Computer Science and Engineering Laboratory.)