def include_image_level_features(orig_imga,fvector_l,featsel):
# include grayscale values ?
f_input_gray = featsel['input_gray']
if f_input_gray is not None:
shape = f_input_gray
#print orig_imga.shape
fvector_l += [sp.misc.imresize(colorconv.gray_convert(orig_imga), shape).ravel()]
# include color histograms ?
f_input_colorhists = featsel['input_colorhists']
if f_input_colorhists is not None:
nbins = f_input_colorhists
colorhists = sp.empty((3,nbins), 'f')
if orig_imga.ndim == 3:
for d in xrange(3):
h = sp.histogram(orig_imga[:,:,d].ravel(),
bins=nbins,
range=[0,255])
binvals = h[0].astype('f')
colorhists[d] = binvals
else:
raise ValueError, "orig_imga.ndim == 3"
#h = sp.histogram(orig_imga[:,:].ravel(),
# bins=nbins,
# range=[0,255])
#binvals = h[0].astype('f')
#colorhists[:] = binvals
#feat_l += [colorhists.ravel()]
fvector_l += [colorhists.ravel()]
return fvector_l
def image_preprocessing(arr,params):
arr = sp.atleast_3d(arr)
smallest_edge = min(arr.shape[:2])
rep = params
preproc_lsum = rep['preproc']['lsum_ksize']
if preproc_lsum is None:
preproc_lsum = 1
smallest_edge -= (preproc_lsum-1)
normin_kshape = rep['normin']['kshape']
smallest_edge -= (normin_kshape[0]-1)
filter_kshape = rep['filter']['kshape']
smallest_edge -= (filter_kshape[0]-1)
normout_kshape = rep['normout']['kshape']
smallest_edge -= (normout_kshape[0]-1)
pool_lsum = rep['pool']['lsum_ksize']
smallest_edge -= (pool_lsum-1)
arrh, arrw, _ = arr.shape
if smallest_edge <= 0 and rep['conv_mode'] == 'valid':
if arrh > arrw:
new_w = arrw - smallest_edge + 1
new_h = int(np.round(1.*new_w * arrh/arrw))
print new_w, new_h
raise
elif arrh < arrw:
new_h = arrh - smallest_edge + 1
new_w = int(np.round(1.*new_h * arrw/arrh))
print new_w, new_h
raise
else:
pass
# TODO: finish image size adjustment
assert min(arr.shape[:2]) > 0
# use the first 3 channels only
orig_imga = arr.astype("float32")[:,:,:3]
# make sure that we don't have a 3-channel (pseudo) gray image
if orig_imga.shape[2] == 3 \
and (orig_imga[:,:,0]-orig_imga.mean(2) < 0.1*orig_imga.max()).all() \
and (orig_imga[:,:,1]-orig_imga.mean(2) < 0.1*orig_imga.max()).all() \
and (orig_imga[:,:,2]-orig_imga.mean(2) < 0.1*orig_imga.max()).all():
orig_imga = sp.atleast_3d(orig_imga[:,:,0])
# rescale to [0,1]
#print orig_imga.min(), orig_imga.max()
if orig_imga.min() == orig_imga.max():
raise MinMaxError("[ERROR] orig_imga.min() == orig_imga.max() "
"orig_imga.min() = %f, orig_imga.max() = %f"
% (orig_imga.min(), orig_imga.max())
)
orig_imga -= orig_imga.min()
orig_imga /= orig_imga.max()
# -- color conversion
# insure 3 dims
#print orig_imga.shape
if orig_imga.ndim == 2 or orig_imga.shape[2] == 1:
orig_imga_new = sp.empty(orig_imga.shape[:2] + (3,), dtype="float32")
orig_imga.shape = orig_imga_new[:,:,0].shape
orig_imga_new[:,:,0] = 0.2989*orig_imga
orig_imga_new[:,:,1] = 0.5870*orig_imga
orig_imga_new[:,:,2] = 0.1141*orig_imga
orig_imga = orig_imga_new
if params['color_space'] == 'rgb':
orig_imga_conv = orig_imga
# elif params['color_space'] == 'rg':
# orig_imga_conv = colorconv.rg_convert(orig_imga)
elif params['color_space'] == 'rg2':
orig_imga_conv = colorconv.rg2_convert(orig_imga)
elif params['color_space'] == 'gray':
orig_imga_conv = colorconv.gray_convert(orig_imga)
orig_imga_conv.shape = orig_imga_conv.shape + (1,)
elif params['color_space'] == 'opp':
orig_imga_conv = colorconv.opp_convert(orig_imga)
elif params['color_space'] == 'oppnorm':
orig_imga_conv = colorconv.oppnorm_convert(orig_imga)
elif params['color_space'] == 'chrom':
orig_imga_conv = colorconv.chrom_convert(orig_imga)
# elif params['color_space'] == 'opponent':
# orig_imga_conv = colorconv.opponent_convert(orig_imga)
# elif params['color_space'] == 'W':
# orig_imga_conv = colorconv.W_convert(orig_imga)
elif params['color_space'] == 'hsv':
orig_imga_conv = colorconv.hsv_convert(orig_imga)
else:
raise ValueError, "params['color_space'] not understood"
return orig_imga,orig_imga_conv