In [1]:
import numpy
from scipy import ndimage
import pandas
from geoh5 import kea
from geoh5.kea import common as kc
# https://github.com/sixy6e/image-processing
from image_processing.segmentation import Segments
In this example we'll create a segmented array, and compute some basic statistics for every segment (min, max, mean, standard deviation, total, area), and output both the segmented array and the associated dataframe (as a raster attribute table) to disk.
The sieving filter will remove segements containing < 30 pixels.
In [2]:
# data dimensions and datatype
dims = (1000, 1000)
dtype = 'int32'
# create some random data and segment via value > 5000
seg_data = numpy.random.randint(0, 10001, dims).astype('uint32')
seg_data, nlabels = ndimage.label(seg_data > 5000)
# create some random data to calculate stats against
data = numpy.random.ranf(dims)
# create a segments class object
seg = Segments(seg_data, include_zero=True)
In [3]:
# initial number of segments
print "Number of segments: {}".format(seg.n_segments)
In [4]:
# remove segments containing < 30 pixels
seg.sieve(30)
print "Number of segments: {}".format(seg.n_segments)
In [5]:
# basic stats (min, max, mean, standard deviation, total, area)
stats_table = seg.basic_statistics(data, dataframe=True)
In [6]:
# join via segment id, specifying 'outer' will account for empty segments
df = pandas.DataFrame({"Histogram": seg.histogram})
df["Segment_IDs"] = df.index
stats_table = pandas.merge(df, stats_table, how='outer', on="Segment_IDs")
nrows = stats_table.shape[0]
In [7]:
# assign random colours to each segment
stats_table.insert(1, "Red", numpy.random.randint(0, 256, (nrows)))
stats_table.insert(2, "Green", numpy.random.randint(0, 256, (nrows)))
stats_table.insert(3, "Blue", numpy.random.randint(0, 256, (nrows)))
stats_table.insert(4, "Alpha", 255)
In [8]:
# define the output image specifications
kwargs = {'width': dims[1],
'height': dims[0],
'count': 1,
'compression': 4,
'chunks': (100, 100),
'blocksize': 100,
'dtype': seg_data.dtype.name}
In [9]:
with kea.open('sieve-example.kea', 'w', **kwargs) as src:
src.write(seg.array, 1)
# define the layer type as thematic (labelled, classified etc)
src.write_layer_type(1, kc.LayerType.thematic)
# write the stats table as an attribute table
usage = {"Red": "Red",
"Green": "Green",
"Blue": "Blue",
"Alpha": "Alpha",
"Histogram": "PixelCount"}
src.write_rat(stats_table, 1, usage=usage)
In [10]:
with kea.open('sieve-example.kea') as ds:
tbl = ds.read_rat()
In [11]:
tbl.head(5)
Out[11]:
In [12]:
stats_table.head(5)
Out[12]:
In [ ]: