Gros Collin, Straub Jeremy
Department of Computer Science, Texas Tech University, United States.
Department of Computer Science, North Dakota State University, United States.
Data Brief. 2018 Dec 21;22:522-529. doi: 10.1016/j.dib.2018.12.060. eCollection 2019 Feb.
Facial and other human recognition techniques are being used for a growing number of applications, ranging from device security to surveillance video identification to forensics. Data sets are required to test recognitions algorithms. This data set facilitates the evaluation of the impact of multiple factors on algorithm performance. The data set includes images taken under five different lighting levels (which vary in light brightness and temperature), seven different lighting positions and five different subject positions. The data set includes data collected for all combinations of the foregoing three collection variables, for a total of 175 images per subject. In addition, sets of data under three different occlusion conditions (no occlusion, glasses and hat) have been collected. Each data set includes images taken under all lighting level, lighting position and subject position combinations, for a total of 525 images of each subject. The images are all taken in the same location with the same background and camera equipment.
面部识别和其他人体识别技术正被应用于越来越多的领域，从设备安全到监控视频识别再到法医学。需要数据集来测试识别算法。该数据集有助于评估多种因素对算法性能的影响。该数据集包括在五种不同光照水平（光照亮度和温度各不相同）、七种不同光照位置和五种不同主体位置下拍摄的图像。该数据集包含针对上述三个采集变量的所有组合收集的数据，每个主体总共175张图像。此外，还收集了三种不同遮挡条件（无遮挡、戴眼镜和戴帽子）下的数据集。每个数据集包括在所有光照水平、光照位置和主体位置组合下拍摄的图像，每个主体总共525张图像。所有图像均在同一地点、相同背景和相同摄像设备下拍摄。
