def ssearch_fast(filename, seg_dir='/home/sai/Documents/selective_search/VOC2007/segments/', save_name=None):
''' Helper function for calling ssearch in fast mode '''
a = time.time()
blob_array = []
priority = []
img = plt.imread(filename)
cc = convert_colorspace(img, ['hsv', 'LAB'])
seg_dir = '/home/sai/Documents/selective_search/VOC2007/segments/'
seg_filename = [seg_dir + 'HSV/50/' + filename[-10:-4] + '.mat', seg_dir + 'HSV/100/' + filename[-10:-4] +
'.mat', seg_dir + 'LAB/50/' + filename[-10:-4] + '.mat', seg_dir + 'LAB/100/' + filename[-10:-4] + '.mat']
for i, _file in enumerate(seg_filename):
_img = cc[i / 2]
_blob_array = _ssearch(_img, load_segment_mask(_file), sim_feats=[sf.color_hist_sim(
), sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape)])
blob_array.append(_blob_array)
priority.append(np.arange(len(_blob_array), 0, -
1).clip(0, (len(_blob_array) + 1) / 2))
_blob_array = _ssearch(_img, load_segment_mask(_file), sim_feats=[
sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape)])
blob_array.append(_blob_array)
priority.append(np.arange(len(_blob_array), 0, -
1).clip(0, (len(_blob_array) + 1) / 2))
bboxes = remove_duplicate(blob_array, priority)
print('Computed %d proposals' % (len(bboxes)))
np.savetxt(save_name + '.txt', bboxes)
print('Time taken: %f' % (time.time() - a))
def demo(image_name,color_space_list=None,ks=None,sim_feats_list=None,net='vgg16', cpu_mode=True):
''' Object Recognition Demo : Selective Search + RCNN
parameters
----------
image_name : filename of image stored in 'Data/img'
color_space_list : list of colorspaces to be used. Refer color_utils for list of possible colorspaces.
Default : [ 'HSV', 'LAB']
ks : list felzenszwalb scale/threshold and minimum segment size.
Default : [50, 100]
'''
blob_array = []
priority = []
img = plt.imread('Data/img/' + image_name + '.jpg')
seg_dir = 'Data/segments/'
if color_space_list is None: color_space_list = ['HSV','LAB']
if ks is None: ks = [50,100]
if sim_feats_list is None: sim_feats_list = [[ sf.color_hist_sim(), sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape) ],[ sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape) ]]
cc = convert_colorspace(img,color_space_list)
seg_filename = [seg_dir + 'HSV/50/' + image_name +'.mat',seg_dir + 'HSV/100/' + image_name +'.mat', seg_dir + 'LAB/50/' + image_name +'.mat',seg_dir + 'LAB/100/' + image_name +'.mat']
for i in range(len(color_space_list)):
for j in range(len(ks)):
for k in range(len(sim_feats_list)):
_img = cc[i]
_file = "%s%s/%d/%s.mat"%(seg_dir,color_space_list[i].upper(),ks[j],image_name)
if not os.path.exists(_file):
segment_mask = felzenszwalb(_img,scale=ks[j],sigma=0.8,min_size=ks[j])
_temp_dict = dict()
_temp_dict['blobIndIm'] = segment_mask + 1
scipy.io.savemat(_file,_temp_dict)
_blob_array = ssearch._ssearch(_img,ssearch.load_segment_mask(_file),sim_feats = sim_feats_list[k])
blob_array.append(_blob_array)
priority.append( np.arange(len(_blob_array),0,-1).clip(0,(len(_blob_array)+1)/2))
bboxes = ssearch.remove_duplicate(blob_array,priority)
bbox_dict = {}
bbox_dict['boxes'] = np.vstack([np.asarray(bboxes)[:,2],np.asarray(bboxes)[:,1],np.asarray(bboxes)[:,4],np.asarray(bboxes)[:,3]]).T
print('\nComputed %d proposals'%(len(bboxes)))
scipy.io.savemat('Data/Boxes/' + image_name + '.mat',bbox_dict)
rcnn.rcnn_demo(image_name,net=net, cpu_mode=cpu_mode)
def ssearch_fast(filename, seg_dir="/home/sai/Documents/selective_search/VOC2007/segments/", save_name=None):
""" Helper function for calling ssearch in fast mode """
a = time.time()
blob_array = []
priority = []
img = plt.imread(filename)
cc = convert_colorspace(img, ["hsv", "LAB"])
seg_dir = "/home/sai/Documents/selective_search/VOC2007/segments/"
seg_filename = [
seg_dir + "HSV/50/" + filename[-10:-4] + ".mat",
seg_dir + "HSV/100/" + filename[-10:-4] + ".mat",
seg_dir + "LAB/50/" + filename[-10:-4] + ".mat",
seg_dir + "LAB/100/" + filename[-10:-4] + ".mat",
]
for i, _file in enumerate(seg_filename):
_img = cc[i / 2]
_blob_array = _ssearch(
_img,
load_segment_mask(_file),
sim_feats=[sf.color_hist_sim(), sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape)],
)
blob_array.append(_blob_array)
priority.append(np.arange(len(_blob_array), 0, -1).clip(0, (len(_blob_array) + 1) / 2))
_blob_array = _ssearch(
_img,
load_segment_mask(_file),
sim_feats=[sf.texture_hist_sim(), sf.size_sim(img.shape), sf.fill_sim(img.shape)],
)
blob_array.append(_blob_array)
priority.append(np.arange(len(_blob_array), 0, -1).clip(0, (len(_blob_array) + 1) / 2))
bboxes = remove_duplicate(blob_array, priority)
print("Computed %d proposals" % (len(bboxes)))
np.savetxt(save_name + ".txt", bboxes)
print("Time taken: %f" % (time.time() - a))
def segment_image(image, color_space_list = ['HSV','LAB'],
ks = [50,100]):
blob_array =[]
priority = []
seg_masks = []
converted_images = convert_colorspace(image,color_space_list)
sim_feats_list = [ sf.color_hist_sim(), sf.texture_hist_sim(),
sf.size_sim(image.shape), sf.fill_sim(image.shape) ]
for img in converted_images:
for j in ks:
print("segmenting",j)
segmented_mask = felzenszwalb(img,j,sigma = 0.8,
min_size = j)
print("blobbing",j)
blobs = ssearch._ssearch(img,segmented_mask,sim_feats =
sim_feats_list)
blob_array.append(blobs)
priority.append(
np.arange(len(blobs),0,-1).clip(0,(len(blobs)+1)/2))
seg_masks.append(segmented_mask)
blob_array = ssearch.remove_duplicate(blob_array)
return blob_array
def demo(image_name,
color_space_list=None,
ks=None,
sim_feats_list=None,
net='vgg16',
cpu_mode=True):
''' Object Recognition Demo : Selective Search + RCNN
parameters
----------
image_name : filename of image stored in 'Data/img'
color_space_list : list of colorspaces to be used. Refer color_utils for list of possible colorspaces.
Default : [ 'HSV', 'LAB']
ks : list felzenszwalb scale/threshold and minimum segment size.
Default : [50, 100]
'''
blob_array = []
priority = []
img = plt.imread('Data/img/' + image_name + '.jpg')
seg_dir = 'Data/segments/'
if color_space_list is None: color_space_list = ['HSV', 'LAB']
if ks is None: ks = [50, 100]
if sim_feats_list is None:
sim_feats_list = [[
sf.color_hist_sim(),
sf.texture_hist_sim(),
sf.size_sim(img.shape),
sf.fill_sim(img.shape)
],
[
sf.texture_hist_sim(),
sf.size_sim(img.shape),
sf.fill_sim(img.shape)
]]
cc = convert_colorspace(img, color_space_list)
seg_filename = [
seg_dir + 'HSV/50/' + image_name + '.mat',
seg_dir + 'HSV/100/' + image_name + '.mat',
seg_dir + 'LAB/50/' + image_name + '.mat',
seg_dir + 'LAB/100/' + image_name + '.mat'
]
for i in range(len(color_space_list)):
for j in range(len(ks)):
for k in range(len(sim_feats_list)):
_img = cc[i]
_file = "%s%s/%d/%s.mat" % (
seg_dir, color_space_list[i].upper(), ks[j], image_name)
if not os.path.exists(_file):
segment_mask = felzenszwalb(_img,
scale=ks[j],
sigma=0.8,
min_size=ks[j])
_temp_dict = dict()
_temp_dict['blobIndIm'] = segment_mask + 1
scipy.io.savemat(_file, _temp_dict)
_blob_array = ssearch._ssearch(
_img,
ssearch.load_segment_mask(_file),
sim_feats=sim_feats_list[k])
blob_array.append(_blob_array)
priority.append(
np.arange(len(_blob_array), 0,
-1).clip(0, (len(_blob_array) + 1) / 2))
bboxes = ssearch.remove_duplicate(blob_array, priority)
bbox_dict = {}
bbox_dict['boxes'] = np.vstack([
np.asarray(bboxes)[:, 2],
np.asarray(bboxes)[:, 1],
np.asarray(bboxes)[:, 4],
np.asarray(bboxes)[:, 3]
]).T
print('\nComputed %d proposals' % (len(bboxes)))
scipy.io.savemat('Data/Boxes/' + image_name + '.mat', bbox_dict)
rcnn.rcnn_demo(image_name, net=net, cpu_mode=cpu_mode)
