Automatic image capture mode based on changes in a target region

Abstract

A series of frames or live images received by a camera can be processed by an automatic image capture system to determine when an automatic image capture should take place. The system can detect when a scene change occurs by comparison of data for two or more frames, and for particular regions in those frames. If a scene change for the specified region is followed by a stabilization of the scene in that region, the system can trigger an auto-capture of at least the stabilized region of the scene, without the need for any user input.

Description

BACKGROUND[0001]Computing devices that include cameras have become increasingly common and mobile, and include devices such as laptop computers, tablet PCs, digital camera devices, mobile phones, ultra-mobile PCs, as well as other mobile data, messaging, and / or communication devices. Users may make use of cameras associated with computing devices to take various pictures of scenery as well as capture images of presentations, whiteboards, business cards, documents, sketches, paintings, and so forth. The users can then refer to the captured images to recall information contained therein such as diagrams, pictures, lists and other text, and so forth. In many cases, users intend to make use of information from captured images in their own documents, notes, and / or presentations.[0002]A traditional technique utilized to capture images involves the use of photo applications that rely on user input to capture a scene. In other words, the user must launch the camera and / or application, point...

AI Technical Summary

Problems solved by technology

Unfortunately, operating the phone single handed and clicking the photo to achieve a stable, clean photo while maintaining focus on the desired object on the screen remains challenging.

In addition, arranging for a repeated image capture of a particular object without requiring user input has been difficult to achieve.

In many cases, this follow-up input can lead to a destabilization of the camera, a change in the focus of the camera, blurriness in the image, or a delay that means the specific scenery is missed or no longer framed correctly.

Furthermore, in cases where there are multiple images to be captured of various scenes, the process can become repetitive, time-consuming, and tiresome to a user.

During the scanning of images, end-users can be slowed or hindered in cases where there are multiple potential regions available for scanning.

Like a slow shutter speed, a long lag time can cause reduced image quality due to blur from vibration of the camera during image capture.

However, use of a tripod requires preparation, which is inconvenient, and therefore tripods are generally not a feasible solution for camera-phone photography.

Consequently, camera-phones are typically not equipped with a tripod screw, or other mounting hardware, thus precluding attachment of a tripod or other stabilizing structure to overcome image quality disadvantages inherent in the construction of cameras that are integrated with mobile devices.

In one implementation, these image data are not yet considered “captured” because they are not being finalized or subject to certain post-demosaicing processes that can be computationally intensive and need not be performed unless the image is intended to be converted into a final image (“captured”) and stored.

This can greatly decrease the time needed to collect desired content from an image.

For example, some mobile or special purpose operating systems may not provide the frameworks / middleware 1618.

Images