def main():
# parse arguments
args = _args()
# edit config
if args.config: _editconfig(args)
if not args.quiet: print()
if args.verbose: print('initializing configurations.... done')
# download data
if args.verbose: print('downloading data............... ', end = '')
mldata = skdata.fetch_mldata("MNIST Original")
if args.verbose: print('done')
# separate featues and labels
X = np.array(mldata.data, dtype='int16')
y = np.array(mldata.target, dtype='int')
# update config
if args.verbose: print('updating configurations........ ', end = '')
config = _updateconfig(args=args, data=X)
if args.verbose: print('done')
# preprocess featues
if args.haar:
X = _haar(X, load=args.load, save=args.save, verbose=args.verbose)
elif args.hogs:
X = _hogs(X, load=args.load, save=args.save, verbose=args.verbose)
elif args.sift:
X = _sift(X, load=args.load, save=args.save, verbose=args.verbose)
elif args.surf:
X = _surf(X, load=args.load, save=args.save, verbose=args.verbose)
else:
X = _fscale(X, split=True, verbose=args.verbose)
# create training and cross-validation sets
split_d = config['train_d']
X_train = X[:split_d]
y_train = y[:split_d]
X_valid = X[split_d:]
y_valid = y[split_d:]
# create classifier
if args.lr:
classifier = lm.LogisticRegression(solver='lbfgs', multi_class='multinomial')
elif args.sv:
classifier = sv.LinearSVC()
else:
classifier = lm.LogisticRegression()
# train classifier
if args.verbose: print('training classifier............ ', end = '')
t_beg = time.time()
classifier.fit(X_train, y_train)
t_end = time.time()
if args.verbose: print('done @ %8.2f sec' %(t_end - t_beg))
# save classifier
if args.save:
if args.verbose: print('dumping classifier............. ', end = '')
skex.joblib.dump(classifier, config['clfr_data_path'], compress=9)
if args.verbose: print('done')
# cross-validate classifier
if not args.quiet: print('training error................. ', end = '')
p_train = classifier.predict(X_train)
e_train = round(sum(y_train!=p_train) / len(y_train) * 100, 2)
if not args.quiet: print(str(e_train) + '%')
if not args.quiet: print('cross-validation error......... ', end = '')
p_valid = classifier.predict(X_valid)
e_valid = round(sum(y_valid!=p_valid) / len(y_valid) * 100, 2)
if not args.quiet: print(str(e_valid) + '%')
if args.plot:
train = np.c_[y_train, X_train]
valid = np.c_[y_valid, X_valid]
steps = config['steps_d']
_plot(classifier, train, valid, steps, save=args.save, verbose=args.verbose)
if not args.quiet: print()
def main():
# parse arguments
args = _args()
# begin time
t_beg = time.time()
# load config
config = _configinfo()
preprocess = config['preprocess']
shape_x = config['shape_x']
shape_y = config['shape_y']
clfrpath = config['clfr_data_path']
rootpath = config['root_data_path']
filepath = args.filepath
savename = rootpath + os.path.split(filepath)[-1].split('.')[0]
if args.verbose: print('\ninitializing configurations.... done')
# load classifier
if args.verbose: print('loading classifier............. ', end = '')
if os.path.isfile(clfrpath):
classifier = skex.joblib.load(clfrpath)
if args.verbose: print('done')
else:
if args.verbose: print('not found\n')
sys.exit()
# load image
if args.verbose: print('loading image.................. ', end = '')
if os.path.isfile(filepath):
(_, extn) = os.path.splitext(filepath)
if extn in ['.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff']:
image = cv.imread(filepath)
if args.verbose: print('done')
else:
if args.verbose: print('unsupported format\n')
sys.exit()
else:
if args.verbose: print('not found\n')
sys.exit()
image_input = image.copy()
# convert image to grayscale
if args.verbose: print('converting colorspace.......... ', end = '')
image_gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
if args.verbose: print('done')
# apply guassian blurring to remove noise
if args.verbose: print('removing noise from image...... ', end = '')
image_blur = cv.GaussianBlur(image_gray, (3, 3), 0, 0)
if args.verbose: print('done')
# threshold image
if args.verbose: print('thresholding image............. ', end = '')
(_, image_th) = cv.threshold(image_blur, 95, 255, cv.THRESH_BINARY_INV)
if args.verbose: print('done')
image_rois = image_th.copy()
# find contours
if args.verbose: print('finding contours in image..... ', end = '')
(_, contours, _) = cv.findContours(image_th.copy(), cv.RETR_EXTERNAL, cv.CHAIN_APPROX_NONE)
if args.verbose: print('done')
# find bounding rectangle around each contour
bn_rects = []
for cntr in contours:
bn_rects.append(cv.boundingRect(cntr))
if args.verbose: print('number of objects detected..... %d' %(len(bn_rects)))
# process each bounding rectangle
loop = 0
for rect in bn_rects:
if args.verbose: print('\rprocessing objects............. %d%%'
%(loop*100//len(bn_rects)), end = '')
# attributes of bounding rectangle
x = rect[0]
y = rect[1]
w = rect[2]
h = rect[3]
# ignore tiny objects assuming them as noise
if h <= 8:
continue
# draw bounding rectangle on images
cv.rectangle(image_rois, (x, y), (x+w, y+h), (255, 255, 255), 1)
cv.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)
# extract region of interest from thresholded image using attributes of bounding rectangle
image_roi = image_th[y:y+h, x:x+w]
# pad region of interest
if w >= h:
length = int(1.8 * w)
else:
length = int(1.8 * h)
image_pad = np.zeros((length, length), dtype='uint8')
i = (length - h) // 2
j = (length - w) // 2
image_pad[i:i+h, j:j+w] = image_roi
# resize padded image
image_roi = cv.resize(image_pad, (shape_x, shape_y), interpolation=cv.INTER_AREA)
# perform dilation as morphological transformation
image_roi = cv.dilate(image_roi, (3, 3))
# preprocess roi
image_roi = image_roi.reshape(1, -1)
if preprocess == 'haar': X = _haar(image_roi, load=False)
elif preprocess == 'hogs': X = _hogs(image_roi, load=False)
elif preprocess == 'sift': X = _sift(image_roi, load=False)
elif preprocess == 'surf': X = _surf(image_roi, load=False)
else:X = _fscale(image_roi, load=True)
X = X.reshape(1, -1)
# predict label
pred = classifier.predict(X)
pred = pred[0]
# put predicted label on image
cv.putText(image, str(pred), (x, y-8), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
loop = loop + 1
if args.verbose: print('\rprocessing objects............. done')
# save images
if args.save:
if args.verbose: print('saving images.................. ', end = '')
cv.imwrite(savename+'_1_input.png' , image_input)
cv.imwrite(savename+'_2_gray.png' , image_gray)
cv.imwrite(savename+'_3_blur.png' , image_blur)
cv.imwrite(savename+'_4_th.png' , image_th)
cv.imwrite(savename+'_5_rois.png' , image_rois)
cv.imwrite(savename+'_6_output.png', image)
if args.verbose: print('done')
# end time
t_end = time.time()
if args.verbose: print('processing time................ %.2f sec\n'
%(t_end - t_beg))
# display image with predictions
cv.imshow('DIGIT RECOGNIZER', image)
cv.waitKey(0)
cv.destroyAllWindows()