A method of automatically capturing images with precision uses an intelligent mobile device having a camera loaded with an appropriate image capture application. When a user initializes the application, the camera starts taking images of the object. Each image is qualified to determine whether it is in focus and entirely within the field of view of the camera. Two or more qualified images are captured and stored for subsequent processing. The qualified images are aligned with each other by an appropriate perspective transformation so they each fill a common frame. Averaging of the aligned images reduces noise and a sharpening filter enhances edges, which produces a sharper image. The processed image is then converted into a two-level, black and white image which may be presented to the user for approval prior to submission via wireless or WiFi to a remote location.