Image analysis – Image segmentation
Patent
1995-11-30
1998-01-20
Coles, Sr., Edward L.
Image analysis
Image segmentation
358464, H04N 140
Patent
active
057108307
ABSTRACT:
A method and apparatus for processing a greyscale input of an image, particularly of a shipping label, into a binary output image in which foreground information is segmented from the background information and contrasts between adjacent regions having different background densities are obliterated is described. A neuron employing a 5.times.5 input neighborhood having a unique neuron activation function is shown. No explicit line process is employed. Output is biased toward a particular one of the output values by employing non-linear feedback as a function of both the grey scale value for the pixel corresponding to the label site being updated and the most recent value of the label site. The otherwise strong contribution from a gradient term in the energy function is suppressed by a shunting inhibition when the shunting inhibition function detects that the pixel lies on or near a boundary between adjacent regions of differing background intensities.
REFERENCES:
patent: 4509195 (1985-04-01), Nadler
patent: 4550435 (1985-10-01), Hayman
patent: 4589141 (1986-05-01), Christian et al.
patent: 4941122 (1990-07-01), Weideman
patent: 5091965 (1992-02-01), Kobayashi et al.
patent: 5093803 (1992-03-01), Howard et al.
patent: 5129040 (1992-07-01), Hanazato et al.
patent: 5140670 (1992-08-01), Chua et al.
patent: 5162899 (1992-11-01), Naka et al.
patent: 5168352 (1992-12-01), Naka et al.
patent: 5179596 (1993-01-01), Weingard
patent: 5216751 (1993-06-01), Gardner et al.
patent: 5218440 (1993-06-01), Mathur
patent: 5239593 (1993-08-01), Wittner et al.
patent: 5245672 (1993-09-01), Wilson et al.
patent: 5248873 (1993-09-01), Allen et al.
patent: 5257343 (1993-10-01), Kyuma et al.
patent: 5274744 (1993-12-01), Yu et al.
patent: 5583659 (1996-12-01), Lee et al.
patent: 5630037 (1997-05-01), Schindler
L.F. Holeva, Foreground-Background Segmentation of OCR Labels by a Single Layer Recurrent Neural Network-Unpublished.
P.L. Kienker, T.J. Sejnowski, G.H. Hinton, L.H. Schumacher, Separating figure from ground with a parallel network, Perception, vol. 15, pp. 197-216, 1986.
T. Poggio, E.B. Gamble, J.J. Little, Parallel Integration of Vision Modules, Science, vol. 242, pp. 436-440, 1988.
L.F. Holeva, N.Kadaba, An Image Filtering Module using Neural Networks for an Optical Character Recognizing System, Math, Modeling and Sci. Computing, pp. 504-510, Principia Scientia, 1993.
M.M. Menon, An Efficient MRF Image-Restoration Technique Using Deterministic Scale-Based Optimization, The Lincoln Laboratory Journal, vol. 6, No. 1, 1993.
International Preliminary Examination Report for PCT No./US95/12817, which is related to the present Application.
Neural Networks for Computing, Snowbird, Apr. 13-16, 1986, No. 1986, 1986 Denker J.S., pp. 129-134, XP 000040996, Divko R et al `Stochastic Spin Models for Pattern Recognition`, see p. 132, paragraph 3--p. 134, paragraph 2.
Pattern Recognition, vol. 25, No. 2, 1 Feb. 1992; pp. 197-209, XP 000263525; Shiaw-Shian Yu et al, `Relaxation by the Hopfield Neural Network`.
Brinich Stephen
Coles Sr. Edward L.
United Parcel Service
LandOfFree
Method of and apparatus for segmenting foreground and background does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of and apparatus for segmenting foreground and background, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of and apparatus for segmenting foreground and background will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-731376