§
Luxuse
Patent Intelligence
Sign In
← Back to Patent Explorer
US5245672A Expired / Lapsed US ⏱️ 0.0 years remaining

Object/anti-object neural network segmentation

Assignee: United States Department of Commerce
•
Filing: 1992-03-09
•
Granted: 1993-09-14
•
Expires: 2012-03-09
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract The system of the present invention applies self-organizing and/or supervd learning network methods to the problem of segmentation. The segmenter receives a visual field, implemented as a sliding window and distinguishes occurrences of complete characters from occurrences of parts of neighboring characters. Images of isolated whole characters are true objects and the opposite of true objects are anti-objects, centered on the space between two characters. The window is moved across a line of text producing a sequence of images and the segmentation system distinguishes true objects from anti-objects. Frames classified as anti-objects demarcate character boundaries, and frames classified as true objects represent detected character images. The system of the present invention may be a feedforward adaption using a symmetric triggering network. Inputs to the network are applied directly to the separate associative memories of the network. The associative memories produce a best match pattern output for each part of the input data. The associative memories provide two or more subnetworks which define data subsets, such as objects or anti-objects, according to previously learned examples. Multi-layer perceptron architecture may also be used in the system of the present invention rather than the symmetrically triggered feedforward adaptation with tradeoffs in training time but advantages in speed.

Inventors

  • 👤 Charles L. Wilson
  • 👤 Michael D. Garris
  • 👤 Robert A. Wilkinson, Jr.

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-10-24 23:54
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40; G06V30/41; G06V30/414; G06F; G06F18/00; G06F18/20; G06F18/24; G06F18/243; G06F18/24317; G06V30/10; G06V30/18; G06V30/1801; G06V30/18019; G06V30/18038; G06V30/18048; G06V30/18057

Claims Analysis

Total Claims: 16
Claim 1
Independent Claim 91 words
A segmentation network for segmenting an image having features including a plurality of characters and a plurality of negative spaces between said characters, comprising: input means for receiving an input signal representative of an image to be segmented; means for extracting said features in response to said input signal; classifying means for classifying said extracted features; negative space determining means for determining a negative space of said plurality of negative spaces between said characters; and, said classifying means having means for preventing classification in accordance with said negative space determining means.
Claim 2
Dependent Claim 91 words
A segmentation network for segmenting an image having features including a plurality of characters and a plurality of negative spaces between said characters, comprising: input means for receiving an input signal representative of an image to be segmented; means for extracting said features in response to said input signal; classifying means for classifying said extracted features; negative space determining means for determining a negative space of said plurality of negative spaces between said characters; and, said classifying means having means for preventing classification in accordance with said negative space determining means.
Claim 3
Dependent Claim 23 words
The segmentation network of claim 1, including self-organizing associative memory means comprising means for extracting said features and classifying said extracted features simultaneously.
Claim 4
Dependent Claim 18 words
The segmentation network of claim 2, wherein said negative space determining means comprises associative memory anti-object detection means.
Claim 5
Dependent Claim 22 words
The segmentation network of claim 3, wherein said associative memory anti-object detection means comprises means for detecting the anti-object of said image.
Claim 6
Dependent Claim 17 words
The segmentation network of claim 4, further comprising associative memory object detection means for determining said characters.
Claim 7
Dependent Claim 19 words
The segmentation network of claim 5, wherein said object detection means and said anti-object detection means are triggered symmetrically.
Claim 8
Dependent Claim 24 words
The segmentation system of claim 5, wherein differing associative memory detection means uses separate matching functions and stores objects and anti-objects in optimum metaclasses.
Claim 9
Dependent Claim 16 words
The segmentation system of claim 5, wherein differing associative memory detection means use separate learning rules.
Claim 10
Dependent Claim 26 words
The segmentation network of claim 5, wherein said associative memory object detection means and said associative memory object detection means operate in parallel on parallel data.
Claim 11
Dependent Claim 20 words
The segmentation network of claim 1, including multi-layer perceptron means wherein said means for extracting said features comprises a filter.
Claim 12
Dependent Claim 13 words
The segmentation network of claim 10, wherein said filter comprises a Karhunen-Loeve filter.
Claim 13
Dependent Claim 13 words
The segmentation network of claim 10, wherein said filter comprises a Gabor filter.
Claim 14
Dependent Claim 25 words
The segmentation network of claim 10, wherein said means for preventing classification comprises negative space gate means for controlling classification in accordance with anti-object detection.
Claim 15
Dependent Claim 19 words
The segmentation network of claim 1, wherein said extracted features correspond to both said characters and said negative spaces.
Claim 16
Dependent Claim 24 words
The segmentation network of claim 1, wherein all negative spaces of said plurality of negative spaces are represented as a single generalized negative space.

References Cited (Backward Citations)

US3295106A Cited
US4510617A Cited
US4790024A Cited
US4817169A Cited
US4827529A Cited
US4809344A Cited
US5014327A Cited
US5020117A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 1996-09-13 1997-03-15 1997-09-14 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2000-09-13 2001-03-15 2001-09-14 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2004-09-13 2005-03-15 2005-09-14 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag