A facial recognition app, recently developed by scientists, will make it easier to identify（辨认）pandas.
Wan Yongqing, a Beijing photographer, visits Sichuan Province to take photos of pandas every other year. He has watched them for more than a decade. "My friends say I'm a big panda fan. It is a shame that I find all pandas look the same, with black eyes and white fur. It does not matter as all the pandas are cute to me, "he said.
Yet, identifying one panda from another does matter to researchers, according to Zhang Zhihe, chief of the Chengdu panda research base.
"Identifying individual pandas is important for conservation（保护） management and research. For captive（圈养的） pandas, it is important for their daily feeding schedules, family background and data management. For wild pandas, it helps researchers study their population structure and provides scientific support for their protection and management, "he said.
China has carried out four scientific surveys on wild pandas, and now has a big databank about them. The number of wild pandas in China is mostly known. However, it is still difficult to determine the age, sex, health and other specific information about the population.
"It's difficult track and watch the structure because wild pandas tend to live alone, deep in the mountains, and their living environment is vast," Zhang added.
In 2017, the Chengdu base began researching individual panda identification technology by analyzing images. Over the past two years, they have built a databank of more than 120,000 images, over 10,00 video clips, and completed organizing nearly 10,000 images.
Using the databank, researchers have started a facial recognition app that can accurately recognize captive pandas by analyzing and comparing the unique features of panda faces.
Panda researchers hope the data and AI technology will help them analyze data for both captive and wild pandas.
