Image object labelling and classification using an associative memory

TY - GEN

T1 - Image object labelling and classification using an associative memory

AU - O'Keefe, S. E M

AU - Austin, J.

N1 - © IEE 1995. This paper is a postprint of a paper submitted to and accepted for publication in the Proceedings of the Fifth International Conference on Image Processing and its Applications and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.

PY - 1995

Y1 - 1995

N2 - An essential part of image analysis is the location and identification of objects within the image. Noise and clutter make this identification problematic, and the size of the image may present a computational problem. To overcome these problems, we use a window onto the image to focus onto small areas. Conventionally we still need to know the size of the object we are searching for in order to select a window of the correct size. We describe a method for object location and classification which enables us to use a small window to identify large objects in the image. The window focusses on features in the image, and an associative memory recalls evidence for objects from these features, avoiding the necessity of knowing the dimensions of the objects to be detected.

AB - An essential part of image analysis is the location and identification of objects within the image. Noise and clutter make this identification problematic, and the size of the image may present a computational problem. To overcome these problems, we use a window onto the image to focus onto small areas. Conventionally we still need to know the size of the object we are searching for in order to select a window of the correct size. We describe a method for object location and classification which enables us to use a small window to identify large objects in the image. The window focusses on features in the image, and an associative memory recalls evidence for objects from these features, avoiding the necessity of knowing the dimensions of the objects to be detected.

UR - http://www.scopus.com/inward/record.url?scp=0029224182&partnerID=8YFLogxK

U2 - 10.1049/cp:19950666

DO - 10.1049/cp:19950666

M3 - Conference contribution

AN - SCOPUS:0029224182

SN - 0-85296-642-3

SP - 286

EP - 290

BT - Fifth International Conference on Image Processing and its Applications, 1995

PB - IET

CY - London

T2 - Fifth International Conference on Image Processing and its Applications

Y2 - 4 July 1995 through 6 July 1995

ER -