With adding depth data to color data, it is possible to increase recognition accuracy significantly. Depth image mostly uses for calculating range or distance between object and sensor. Also they are used for making 3-D models of objects and increasing accuracy. Depending on the sensor’s depth quality, the recognition accuracy changes. Age estimation is useful for calculating the aging effects using prior patterns, which are recorded during years from subjects. In this paper, age estimation occurs using summation of RGB image edges gray value and summation of depth image’s entropy edges. Furthermore, a new face detection and extraction method for depth images is represented, which is based on standard deviation filter, ellipse fitting and some pre-post processing techniques. The advantage of this method is its speed and single image aspect capability. In this approach, there is no need to learning and classification process. Proposed method is between 10 to 20 times faster but lower accurate. System is validated with some benchmark color and color-depth (RGB-D) face databases, and in comparing with other age estimation methods, returned satisfactory and promising results. Because of the high speed in this method, it is possible to use it on real time applications. It is mentionable that this paper is the first age estimation research on RGB-D images.