Method and system for processing scanned images

1. A method of locating one or more content portions of an image, the image including a plurality of pixel values, the method comprising automatically performing the following steps using a processor:

receiving the plurality of pixel values, the pixel values characterizing the image captured by an imager of a computed-radiography scanner;

determining a pixel threshold value using the pixel values so that the pixel threshold value corresponds to a background range of the pixel values by at least

determining a histogram of the image, the histogram including pixel values and corresponding pixel counts and slopes; and

determining a peak pixel value using the slopes, so that the peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, by at least

determining a plurality of peak pixel values using the slopes, so that each peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, and

selecting the one of the peak pixel values closest to a background pixel value as the peak pixel value;

comparing the determined pixel threshold value to the pixel values so that a background set of the pixel values and a content set of the pixel values are determined;

determining a plurality of boundaries between the background and content sets of pixel values;

determining the one or more content portions using the determined boundaries;

determining respective bounding boxes for the determined one or more content portions;

providing a visual indication of at least one of the determined bounding boxes on a display; and

extracting image data corresponding to one of the content portions from the image and storing the extracted image data in a tangible, non-transitory computer-readable storage medium.

2. The method as claimed in claim 1 , wherein the determining-pixel-threshold-value step further includes determining a pixel value of a negative-to-positive transition of the slopes, the determined pixel value being farther from a background pixel value than the determined peak pixel value, so that the determined pixel value is the pixel threshold value.

3. The method as claimed in claim 1 , wherein the comparing step includes thresholding the pixel values to produce a thresholded image in which pixels in the content set have a first pixel value and pixels in the background set have a second, different pixel value.

4. The method as claimed in claim 3 , wherein the determining- boundaries step includes:

locating one or more edges aligned within a first angle range in the thresholded image;

locating one or more edges aligned within a second, different angle range in the thresholded image; and

producing a boundary image, so each pixel in the boundary image has a first pixel value if that pixel corresponds to any of the located edges, and has a second, different pixel value otherwise.

5. The method as claimed in claim 4 , wherein the boundary image is a binary image, the first pixel value is unity, and the second pixel value is zero.

6. The method as claimed in claim 4 , wherein the determining-content-portions step includes:

determining a starting pixel from the pixels having the first pixel value in the boundary image;

tracing a path along adjacent pixels having the first pixel value in the boundary image starting from the starting pixel and extending until the starting pixel is reached or until no adjacent pixels are available, wherein the tracing visits each pixel in the boundary image at most once;

determining whether a second starting pixel is present in the pixels having the first pixel value in the boundary image and not visited during prior tracing; and

if a second starting pixel is present, repeating the tracing and determining-second-starting-pixel steps so that one or more paths are defined including respective, different starting pixels, each path representative of one of the content portions.

7. The method as claimed in claim 6 , wherein the determining-bounding-boxes step includes:

determining respective centers and respective extents of the paths; and

determining corners of the bounding boxes using the centers and extents, so that each bounding box encloses a respective one of the paths.

8. The method as claimed in claim 7 , further including determining whether each bounding box is substantially rectangular, and determining that each path corresponds to a content portion if and only if the corresponding bounding box is substantially rectangular.

9. The method as claimed in claim 7 , wherein the step of determining the centers and the extents of the paths includes computing respective centroids, respective orientations, and respective extrema of pixel locations of each of the paths.

10. The method as claimed in claim 1 , including receiving metadata corresponding to the one of the content portions and storing the metadata in association with the extracted image data in the storage medium.

11. The method as claimed in claim 1 , including interrogating a computed-radiography plate with an imager and providing the image corresponding to a latent image on the plate.

12. A computed-radiography scanner, comprising:

an imager;

a transport configured to operatively arrange a plurality of plates with respect to the imager so that a single image of the plates can be captured; and

a processor configured to automatically:

determine a pixel threshold value using a plurality of pixel values in the single image so that the pixel threshold value corresponds to a background range of the pixel values by at least

determining a histogram of the image, the histogram including pixel values and corresponding pixel counts and slopes; and

determining a peak pixel value using the slopes, so that the peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, by at least

determining a plurality of peak pixel values using the slopes, so that each peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, and

selecting the one of the peak pixel values closest to a background pixel value as the peak pixel value;

compare the determined pixel threshold value to the pixel values so that a background set of the pixel values and a content set of the pixel values are determined;

determine a plurality of boundaries between the background and content sets of pixel values;

determine the one or more content portions using the determined boundaries;

determine respective bounding boxes for the determined one or more content portions.

13. The scanner as claimed in claim 12 , wherein the scanner does not include an alignment fixture for aligning the plates on the transport.

14. The scanner as claimed in claim 12 , including an electronic display, the processor further configured to automatically present on the display a visual representation of the single image and at least one of the determined bounding boxes.

15. The scanner as claimed in claim 12 , including a tangible, non-transitory computer-readable storage medium, the processor further configured to automatically extract image data corresponding to one of the content portions from the image and store the extracted image data in the storage medium.

16. A method of locating one or more content portions of an image, the image including a plurality of pixel values, the method comprising automatically performing the following steps using a processor:

receiving the plurality of pixel values, the pixel values characterizing the image captured by an imager of a computed-radiography scanner;

determining a pixel threshold value using the pixel values by at least

determining a histogram of the image, the histogram including pixel values and corresponding pixel counts and slopes; and

determining a peak pixel value using the slopes, so that the peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, by at least

determining a plurality of peak pixel values using the slopes, so that each peak pixel value corresponds to a slope higher in magnitude than a median of magnitudes of the slopes, and

selecting the one of the peak pixel values closest to a background pixel value as the peak pixel value;

determining a plurality of boundaries between portions in the image data, the portions delimited by the pixel threshold value;

determining the one or more content portions using the determined boundaries;

determining respective bounding boxes for the determined one or more content portions;

providing a visual indication of at least one of the determined bounding boxes on a display; and

extracting image data corresponding to one of the content portions from the image and storing the extracted image data in a tangible, non-transitory computer-readable storage medium.