Language
Country/Area
No result found
The Origins of Facial Recognition Technology: How It Was Born in the 1960s?
The history of facial recognition technology can be traced back to the 1960s, when a group of pioneers began exploring how to use computers to recognize faces. This technology was originally developed as a computer application, and with the advancement of technology, it is now widely used in smartphones, surveillance systems, and various modern technologies. However, little is known about the origins and development of this technology.
The development of the earliest automatic facial recognition systems originated mainly from the research of Woody Bledsoe, Helen Chan Wolf, and Charles Bisson. Their main goal was to teach computers to recognize faces.
In the 1960s, their facial recognition project was called "human-machine integration" because before computers could perform recognition, humans first needed to determine the coordinates of facial features in photos. This process relies on manual intervention, so the efficiency is relatively limited. Using a graphics tablet, humans locate the coordinates of facial features such as the center of the pupil, the inner and outer corners of the eyes, and the shape of the hairline. These coordinates are used to calculate various distances, including the width of the mouth and eyes. As the database grows, computers can compare these distances and try to find potential matches.
In 1970, Takeo Kanade publicly demonstrated for the first time a facial matching system that could automatically locate anatomical features such as the jaw and calculate the distance ratio between facial features.
As research deepened, facial recognition systems gradually matured in the 1980s and 1990s. For example, the U.S. Defense Advanced Research Projects Agency launched the FERET program in 1993 to develop "automatic facial recognition capabilities" to assist security and law enforcement personnel. This initiative became the cornerstone of modern facial recognition technology and spawned several companies specializing in facial recognition technology. Subsequently, many state DMV offices began implementing automatic facial recognition systems to prevent people from obtaining multiple driver's licenses using different identities, further promoting the use of the technology.
In the 1990s, the development of facial recognition technology began to encompass a variety of new methods, including principal component analysis (PCA) and linear discriminant analysis (LDA). These technologies significantly improve facial recognition accuracy.
In the 21st century, with the rise of machine learning technologies such as deep learning, facial recognition systems continue to evolve. These new technologies can maintain a high level of recognition under various conditions. In 2015, the implementation of the Viola-Jones algorithm made real-time face detection possible, significantly broadening the application scope of facial recognition technology.
However, the development of facial recognition technology has not been without controversy, with many concerned that the technology will invade personal privacy and may lead to misidentification and racial discrimination.
In recent years, society's attention to this technology has been increasing, and many cities have banned the use of facial recognition systems. In 2021, Meta Platforms decided to shut down its Facebook facial recognition system, which is regarded as one of the most important changes in the history of facial recognition technology. The withdrawal of other companies such as IBM also reflects the ethical considerations of this technology.
Facial recognition technology has evolved from its initial limitations to now ubiquitous applications, covering security surveillance, social media and identity verification.
As technology continues to evolve and social needs change, facial recognition technology may be further integrated into our daily lives. However, what is the future of this technology? Will personal privacy be protected while maintaining convenience?
