HISTOGRAM-BASED IMAGE SEGMENTATION

摘要

Systems, apparatuses, and/or methods may provide for segmenting an image by generating a histogram of its pixel values, dividing the histogram into class intervals, and then iteratively computing new, shifted weighted means and shifted class interval boundaries for the class intervals until a predetermined level of convergence to a limit is obtained. The pixels may then be updated to a last weighted mean for class intervals to which they belong, providing segmentation. Similarly, any data may be segmented to provide computational efficiency.

主权项

1. A system to segment an image using mean shifting, comprising:
a camera to capture an image that comprises pixels having pixel values;a processor to control:
a histogram generator to generate a histogram of the pixel values and to divide the histogram into two or more class intervals, wherein each class interval has boundaries and a width; a mean determiner to compute an initial mean and subsequently to compute a weighted mean for each class interval; a class interval mean updater to iteratively update the weighted mean of each class interval to a most recently computed weighted mean if a magnitude of a difference between the weighted mean and a previous mean is greater than a limit, wherein the previous mean is the initial mean when the initial mean has most recently been computed or a previously computed weighted mean when the previously computed weighted mean has most recently been computed; a class interval boundary updater to update the boundaries of each class interval based on a respective width and a respective most recently computed weighted mean for each class interval if the magnitude of the difference is greater than the limit; a pixel value updater to update the pixel values of each class interval to a last computed weighted mean for a respective class interval if the magnitude of the difference is not greater than the limit; and a display to display a segmented image based on the updated pixel values.