segment (Q6032890)

**Author**: University of Massachusetts Vision Group, Carla Brodley \N**Source**: [UCI](http://archive.ics.uci.edu/ml/datasets/image+segmentation) - 1990 \N**Please cite**: [UCI](http://archive.ics.uci.edu/ml/citation_policy.html) \N\N**Image Segmentation Data Set**\NThe instances were drawn randomly from a database of 7 outdoor images. The images were hand-segmented to create a classification for every pixel. Each instance is a 3x3 region.\N \N### Attribute Information \N\N1. region-centroid-col: the column of the center pixel of the region.\N2. region-centroid-row: the row of the center pixel of the region.\N3. region-pixel-count: the number of pixels in a region = 9.\N4. short-line-density-5: the results of a line extractoin algorithm that \N counts how many lines of length 5 (any orientation) with\N low contrast, less than or equal to 5, go through the region.\N5. short-line-density-2: same as short-line-density-5 but counts lines\N of high contrast, greater than 5.\N6. vedge-mean: measure the contrast of horizontally\N adjacent pixels in the region. There are 6, the mean and \N standard deviation are given. This attribute is used as\N a vertical edge detector.\N7. vegde-sd: (see 6)\N8. hedge-mean: measures the contrast of vertically adjacent\N pixels. Used for horizontal line detection. \N9. hedge-sd: (see 8).\N10. intensity-mean: the average over the region of (R + G + B)/3\N11. rawred-mean: the average over the region of the R value.\N12. rawblue-mean: the average over the region of the B value.\N13. rawgreen-mean: the average over the region of the G value.\N14. exred-mean: measure the excess red: (2R - (G + B))\N15. exblue-mean: measure the excess blue: (2B - (G + R))\N16. exgreen-mean: measure the excess green: (2G - (R + B))\N17. value-mean: 3-d nonlinear transformation\N of RGB. (Algorithm can be found in Foley and VanDam, Fundamentals\N of Interactive Computer Graphics)\N18. saturatoin-mean: (see 17)\N19. hue-mean: (see 17)