Image analysis – Histogram processing – For setting a threshold
Patent
1987-05-22
1988-06-28
Boudreau, Leo H.
Image analysis
Histogram processing
For setting a threshold
382 50, G06K 900
Patent
active
047544902
ABSTRACT:
The present invention is a technique for use in image processing for extracting feature information from an array of pixels. Each pixel within the array of pixels has a pixel value selected from among a plurality of possible pixel values. As the pixels are recalled from the array of pixels in a raster scan fashion a pixel address memory is incremented to contain a current pixel address indicative of the location of the current pixel. If the current pixel is the first occurrence of its pixel value, the current pixel address is stored in a first occurrence pointer memory at a memory location corresponding to the current pixel value. The current pixel address is stored within a last occurrence pointer memory at the memory location corresponding to the current pixel value. The current pixel address is stored in a memory location within a linked-list memory corresponding to a pixel address stored within the last occurrence pointer memory at a memory location corresponding to the current pixel address. This process builds within the linked-list memory a plurality of linked chains from the first occurrence of a particular pixel value, through successive occurrences of the pixel value for the entire array of pixels.
REFERENCES:
patent: 4075604 (1978-02-01), Degasperi
patent: 4365304 (1982-12-01), Ruhman et al.
patent: 4509195 (1985-04-01), Nadler
patent: 4606065 (1986-08-01), Beg et al.
patent: 4630306 (1986-12-01), West et al.
Boudreau Leo H.
Environmental research Institute of Michigan
LandOfFree
Linked-list image feature extraction does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Linked-list image feature extraction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Linked-list image feature extraction will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1920208