Therefore, our system can be used by biologists, researchers, and gamekeepers to estimate population sizes faster and more precisely than the current frameworks. In three experiments we show that the presented framework outperforms previous approaches in the field of great ape identification and achieves promising results. We thoroughly evaluate our proposed algorithms on two datasets of captive and free-living chimpanzee individuals which were annotated by experts. We present an automated framework for photo identification of chimpanzees including face detection, face alignment, and face recognition. To overcome the limitations of our previous work, we combine holistic global features and locally extracted descriptors using a decision fusion scheme. In this paper we do not only summarize our earlier work in the field, we also extend our previous approaches towards a more robust system which is less prone to difficult lighting situations, various poses, and expressions as well as partial occlusion by branches, leafs, or other individuals. Based on the assumption that humans and great apes share similar properties of the face, we proposed to adapt and extend face detection and recognition algorithms, originally developed to recognize humans, for chimpanzee identification. To overcome the burden of time-consuming routine work, we have recently started to develop computer vision algorithms for automated chimpanzee detection and identification of individuals.
#Chimpanzee vs human face manual#
However, the manual analysis of the resulting image and video material is extremely tedious, time consuming, and cost intensive. To overcome the catastrophic decline of biodiversity, biologists and gamekeepers recently started to use remote cameras and recording devices for wildlife monitoring in order to estimate the size of remaining populations. Consequently, there is an urgent need to protect the remaining populations of threatened species. Parr will present this new data at the upcoming "Mind of the Chimpanzee" conference, an international multidisciplinary conference on chimpanzee cognition being held March 22-25 at the Lincoln Park Zoo in Chicago.Due to the ongoing biodiversity crisis, many species including great apes like chimpanzees are on the brink of extinction. This is how we determined when the chimpanzees were using a single feature or if they needed more than one feature to match the similar expressions," said Sheila Sterk, a senior animal behavior management specialist on Parr's team. The chimpanzees then were asked to match the new expression to the original one. "After the chimpanzees matched similar images, we separated individual features of the original animated expression, such as a raised brow, by frame and pieced the frames back together to create a variation of the original expression. Using Chimp FACS, the chimpanzees in the study observed anatomically correct 3D animations of chimpanzee facial expressions and then were asked to match the similar ones. To facilitate her studies, Parr developed the Chimpanzee Facial Action Coding System (Chimp FACS) to directly compare documented expressions of humans and chimpanzees. Ultimately, we want to better understand what people are feeling and expressing emotionally because it helps us empathize with one another," Parr continued.
"Sometimes it's easy to read what people are feeling, but at other times, we have to look at multiple places on their faces. This is similar to what researchers see in human emotional expressions. While some expressions, such as a playful look, can be identified using a single feature, other expressions, such as when a chimp bares his teeth, require looking at numerous characteristics within the face, including the eyes and lips." According to Parr, "This discovery is an important step to help researchers recognize facial movements and understand why they are important.
0 kommentar(er)
