A method for extracting foreground image and electronic apparatus thereof is provided and implements infrared (IR) technology to perform the foreground image extraction to reduce ambient light effect and background noise. Furthermore, the method and electronic apparatus extract an IR light frame image indicating a light state, an IR dark frame image indicating a dark state, and a color image (e.g., RGB image, YUV image, or etc.) at different IR intensities. Then, the method and electronic apparatus calculate the relationship between the IR light frame image and the IR dark frame image to extract a better background image (including the user's face portion, body portion and hair portion) by a simple algorithm.