A system and method for converting a film camera into a digital camera uses an electronic device placed in a space of the camera that normally contains film. The device includes an image sensing array arranged in optical communication with a lens of the camera when a shutter is open. An audio sensor is used to detect sounds within the camera, and an acoustic pattern recognizer with a built-in training mode is used to determine if the detected sounds correspond with the shutter operation. The image sensing array is switched into an image capture mode when the acoustic pattern recognizer determines that the shutter is being opened. When the shutter is opened, a read-out circuit captures multiple image frames from the image sensing array. An image processor associated with the image sensing array processes the captured images using advanced image processing algorithms.