An image sensing device is configured as follows. Namely, the device includes a recording unit configured to record correspondence data formed by making an action state of the object and voice information recorded prior to the shooting to correspond to each other, a voice determination unit configured to determine whether the voice acquired by a voice acquisition unit contains the voice information which forms the correspondence data, an action state determination unit configured to, when the voice acquired by the voice acquisition unit contains the voice information which forms the correspondence data, determine whether the action state of the object that corresponds to the voice information and an actual action state of the object match each other, and a control unit configured to, when the action state of the object that corresponds to the voice information and the actual action state of the object match each other, control shooting processing.