Method and apparatus for image processing

US9799098B2 · kind B2 · utility

Assignees

• Massachusetts Institute of Technology · US
• Max-Planck-Gesellschaft zur Föderung der Wissenschaften e.V. · US

Inventors

• H. Sebastian Seung · Cambridge, US
• Joseph F. Murray · San Diego, US
• Viren Jain · Cambridge, US
• Srinivas Turaga · Kanchinakote, IN
• Moritz Helmstaedter · Heidelberg, DE
• Winfried Denk · Berkeley Heights, US

Key dates

• Filing date: Apr 24, 2008
• Grant date: Oct 24, 2017
• Expiry date: Jul 30, 2031

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/20084
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Identifying objects in images is a difficult problem, particularly in cases an original image is noisy or has areas narrow in color or grayscale gradient. A technique employing a convolutional network has been identified to identify objects in such images in an automated and rapid manner. One example embodiment trains a convolutional network including multiple layers of filters. The filters are trained by learning and are arranged in successive layers and produce images having at least a same resolution as an original image. The filters are trained as a function of the original image or a desired image labeling; the image labels of objects identified in the original image are reported and may be used for segmentation. The technique can be applied to images of neural circuitry or electron microscopy, for example. The same technique can also be applied to correction of photographs or videos.