Iranian kinect face database (IKFDB): a color‑depth based face database collected by kinect v.2 sensor

摘要

This study presents a new color-depth based face database gathered from different genders and age ranges from Iraniansubjects. Using suitable databases, it is possible to validate and assess available methods in different research fields. Thisdatabase has application in different fields such as face recognition, age estimation and Facial Expression Recognitionand Facial Micro Expressions Recognition. Image databases based on their size and resolution are mostly large. Colorimages usually consist of three channels namely Red, Green and Blue. But in the last decade, another aspect of imagetype has emerged, named “depth image”. Depth images are used in calculating range and distance between objectsand the sensor. Depending on the depth sensor technology, it is possible to acquire range data differently. Kinect sensorversion 2 is capable of acquiring color and depth data simultaneously. Facial expression recognition is an importantfield in image processing, which has multiple uses from animation to psychology. Currently, there is a few numbers ofcolor-depth (RGB-D) facial micro expressions recognition databases existing. With adding depth data to color data, theaccuracy of final recognition will be increased. Due to the shortage of color-depth based facial expression databasesand some weakness in available ones, a new and almost perfect RGB-D face database is presented in this paper, coveringMiddle-Eastern face type. In the validation section, the database will be compared with some famous benchmark facedatabases. For evaluation, Histogram Oriented Gradients features are extracted, and classification algorithms such asSupport Vector Machine, Multi-Layer Neural Network and a deep learning method, called Convolutional Neural Networkor are employed. The results are so promising.