Python cv2.imread() Examples

def convert_images2bmp():
    # cv2.imread() jpg at 230 img/s, *.bmp at 400 img/s
    for path in ['../coco/images/val2014/', '../coco/images/train2014/']:
        folder = os.sep + Path(path).name
        output = path.replace(folder, folder + 'bmp')
        if os.path.exists(output):
            shutil.rmtree(output)  # delete output folder
        os.makedirs(output)  # make new output folder

        for f in tqdm(glob.glob('%s*.jpg' % path)):
            save_name = f.replace('.jpg', '.bmp').replace(folder, folder + 'bmp')
            cv2.imwrite(save_name, cv2.imread(f))

    for label_path in ['../coco/trainvalno5k.txt', '../coco/5k.txt']:
        with open(label_path, 'r') as file:
            lines = file.read()
        lines = lines.replace('2014/', '2014bmp/').replace('.jpg', '.bmp').replace(
            '/Users/glennjocher/PycharmProjects/', '../')
        with open(label_path.replace('5k', '5k_bmp'), 'w') as file:
            file.write(lines) 

def main():
	imagePath = "img.jpg"
	
	img = cv2.imread(imagePath)
	gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
	
	generate_histogram(gray)
	
	cv2.imwrite("before.jpg", gray)

	gray = cv2.equalizeHist(gray)
	
	generate_histogram(gray)
	
	cv2.imwrite("after.jpg",gray)
	
	return 0 

def main():
	#IMG PATHS
	imagePath = "test3.jpg"
	cascPath = "cascades/haarcascade_pedestrian.xml"

	pplCascade = cv2.CascadeClassifier(cascPath)
	image = cv2.imread(imagePath)
	gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
	
	gray = normalize_grayimage(gray)
	 
	pedestrians = pplCascade.detectMultiScale(
		gray,
		scaleFactor=1.2,
		minNeighbors=10,
		minSize=(32,96),
		flags = cv2.cv.CV_HAAR_SCALE_IMAGE
	)

	print "Found {0} ppl!".format(len(pedestrians))

	#Draw a rectangle around the detected objects
	for (x, y, w, h) in pedestrians:
		cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)

	cv2.imwrite("saida.jpg", image)
	cv2.imshow("Ppl found", image)
	cv2.waitKey(0)
	
	return 0 

def get_data(path, activation):
    '''Get the dataset
    '''
    data = []
    image_names = []
    for filename in os.listdir(path):
        img = cv2.imread(os.path.join(path,filename), cv2.IMREAD_GRAYSCALE)
        image_names.append(filename)
        if img is not None:
            data.append(img)

    data = np.asarray(data)

    if activation == 'sigmoid':
        data = data.astype(np.float32)/(255.0)
    elif activation == 'tanh':
        data = data.astype(np.float32)/(255.0/2) - 1.0

    data = data.reshape((data.shape[0], 1, data.shape[1], data.shape[2]))

    np.random.seed(1234)
    p = np.random.permutation(data.shape[0])
    X = data[p]

    return X, image_names 

def __getitem__(self, idx):
        images, masks = [], []

        for (image_path, mask_path) in zip(self.image_path_list[idx * self.batch_size: (idx + 1) * self.batch_size],
                                           self.mask_path_list[idx * self.batch_size: (idx + 1) * self.batch_size]):
            image = cv2.imread(image_path, 1)
            mask = cv2.imread(mask_path, 0)

            image = self._padding(image)
            mask = self._padding(mask)

            # augumentation
            augmentation = self.transformer(image=image, mask=mask)
            image = augmentation['image']
            mask = self._get_result_map(augmentation['mask'])

            images.append(image)
            masks.append(mask)

        images = np.array(images)
        masks = np.array(masks)
        images = pinput(images)

        return images, masks 

def load_image(img_path, net_input_shape):
    imgBGR = cv2.imread(img_path)
    img = cv2.resize(imgBGR, net_input_shape)
    # BGR -> RGB
    #img = img[:,:, (2, 1, 0)]

    ## Method 1
    # imgT = np.transpose(img, (2, 0, 1))  # c,w,h
    # imgF = np.asarray(imgT, dtype=np.float32)
    # mean = [[[88.159309]], [[97.966286]], [[103.66106]]] # Caffe image mean
    # imgS = np.subtract(imgF,mean)

    ## Method 2
    imgF = np.asarray(img, dtype=np.float32)
    mean = [128.0, 128.0, 128.0] # Caffe image mean
    # mean = [88.159309, 97.966286, 103.66106] # Caffe image mean
    imgSS = np.subtract(imgF, mean)/128.0
    imgS = np.transpose(imgSS, (2, 0, 1))  # c,w,h

    # RGB_MEAN_PIXELS = np.array([88.159309, 97.966286, 103.66106]).reshape((1,1,1,3)).astype(np.float32)

    return imgBGR, np.ascontiguousarray(imgS, dtype=np.float32) # avoid error: ndarray is not contiguous 

def __getitem__(self, index):
        datafiles = self.files[index]
        image = cv2.imread(datafiles["img"], cv2.IMREAD_COLOR)
        size = image.shape
        name = osp.splitext(osp.basename(datafiles["img"]))[0]
        image = np.asarray(image, np.float32)
        image -= self.mean
        
        img_h, img_w, _ = image.shape
        pad_h = max(self.crop_h - img_h, 0)
        pad_w = max(self.crop_w - img_w, 0)
        if pad_h > 0 or pad_w > 0:
            image = cv2.copyMakeBorder(image, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT, 
                value=(0.0, 0.0, 0.0))
        image = image.transpose((2, 0, 1))
        return image, name, size 

def __read__(file, label):
    image = cv2.imread(file.decode(), cv2.IMREAD_GRAYSCALE)
    image = np.expand_dims(image, 2)
    image = np.float32(image) / 255.
    return (image, label) 

def __getitem__(self, index):
        datafiles = self.files[index]
        image = cv2.imread(datafiles["img"], cv2.IMREAD_COLOR)
        image = cv2.resize(image, None, fx=0.5, fy=0.5, interpolation=cv2.INTER_LINEAR)
        size = image.shape
        name = osp.splitext(osp.basename(datafiles["img"]))[0]
        image = np.asarray(image, np.float32)
        image = (image - image.min()) / (image.max() - image.min())
        
        img_h, img_w, _ = image.shape
        pad_h = max(self.crop_h - img_h, 0)
        pad_w = max(self.crop_w - img_w, 0)
        if pad_h > 0 or pad_w > 0:
            image = cv2.copyMakeBorder(image, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT, 
                value=(0.0, 0.0, 0.0))
        image = image.transpose((2, 0, 1))
        return image, np.array(size), name 

def pull_item(self, index):
        img_id = self.ids[index]

        target = ET.parse(self._annopath % img_id).getroot()
        img = cv2.imread(self._imgpath % img_id)
        height, width, channels = img.shape

        if self.target_transform is not None:
            target = self.target_transform(target, width, height)

        if self.transform is not None:
            target = np.array(target)
            img, boxes, labels = self.transform(img, target[:, :4], target[:, 4])
            # to rgb
            img = img[:, :, (2, 1, 0)]
            # img = img.transpose(2, 0, 1)
            target = np.hstack((boxes, np.expand_dims(labels, axis=1)))
        return torch.from_numpy(img).permute(2, 0, 1), target, height, width
        # return torch.from_numpy(img), target, height, width 

def _get_image_blob(roidb, scale_inds):
  """Builds an input blob from the images in the roidb at the specified
  scales.
  """
  num_images = len(roidb)
  processed_ims = []
  im_scales = []
  for i in range(num_images):
    im = cv2.imread(roidb[i]['image'])
    if roidb[i]['flipped']:
      im = im[:, ::-1, :]
    target_size = cfg.TRAIN.SCALES[scale_inds[i]]
    im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
                    cfg.TRAIN.MAX_SIZE)
    im_scales.append(im_scale)
    processed_ims.append(im)

  # Create a blob to hold the input images
  blob = im_list_to_blob(processed_ims)

  return blob, im_scales 

def load_image(img_path, net_input_shape):
    imgBGR = cv2.imread(img_path)
    img = cv2.resize(imgBGR, net_input_shape)
    # BGR -> RGB
    #img = img[:,:, (2, 1, 0)]

    ## Method 1
    # imgT = np.transpose(img, (2, 0, 1))  # c,w,h
    # imgF = np.asarray(imgT, dtype=np.float32)
    # mean = [[[88.159309]], [[97.966286]], [[103.66106]]] # Caffe image mean
    # imgS = np.subtract(imgF,mean)

    ## Method 2
    imgF = np.asarray(img, dtype=np.float32)
    mean = [128.0, 128.0, 128.0] # Caffe image mean
    # mean = [88.159309, 97.966286, 103.66106] # Caffe image mean
    imgSS = np.subtract(imgF, mean)/128.0
    imgS = np.transpose(imgSS, (2, 0, 1))  # c,w,h

    # RGB_MEAN_PIXELS = np.array([88.159309, 97.966286, 103.66106]).reshape((1,1,1,3)).astype(np.float32)

    return imgBGR, np.ascontiguousarray(imgS, dtype=np.float32) # avoid error: ndarray is not contiguous 

def processFrames(self):
        try:
            for img in self.anotations_list:
                img = img.split(';')
                # print(img)
                # ret,imgcv = cap.read()
                if self.video:
                    ret,imgcv = self.cap.read()
                else:
                    imgcv = cv2.imread(os.path.join('../',self.config["dataset"],img[0]))
                result = self.tfnet.return_predict(imgcv)
                print(result)
                imgcv = self.drawBoundingBox(imgcv,result)        
                cv2.imshow('detected objects',imgcv)
                if cv2.waitKey(10) == ord('q'):
                    print('exitting loop')
                    break
        except KeyboardInterrupt:
            cv2.destroyAllWindows()
            print('exitting program') 

def make_edge_smooth(dataset_name, img_size) :
    check_folder('./dataset/{}/{}'.format(dataset_name, 'trainB_smooth'))

    file_list = glob('./dataset/{}/{}/*.*'.format(dataset_name, 'trainB'))
    save_dir = './dataset/{}/trainB_smooth'.format(dataset_name)

    kernel_size = 5
    kernel = np.ones((kernel_size, kernel_size), np.uint8)
    gauss = cv2.getGaussianKernel(kernel_size, 0)
    gauss = gauss * gauss.transpose(1, 0)

    for f in tqdm(file_list) :
        file_name = os.path.basename(f)

        bgr_img = cv2.imread(f)
        gray_img = cv2.imread(f, 0)

        bgr_img = cv2.resize(bgr_img, (img_size, img_size))
        pad_img = np.pad(bgr_img, ((2, 2), (2, 2), (0, 0)), mode='reflect')
        gray_img = cv2.resize(gray_img, (img_size, img_size))

        edges = cv2.Canny(gray_img, 100, 200)
        dilation = cv2.dilate(edges, kernel)

        gauss_img = np.copy(bgr_img)
        idx = np.where(dilation != 0)
        for i in range(np.sum(dilation != 0)):
            gauss_img[idx[0][i], idx[1][i], 0] = np.sum(
                np.multiply(pad_img[idx[0][i]:idx[0][i] + kernel_size, idx[1][i]:idx[1][i] + kernel_size, 0], gauss))
            gauss_img[idx[0][i], idx[1][i], 1] = np.sum(
                np.multiply(pad_img[idx[0][i]:idx[0][i] + kernel_size, idx[1][i]:idx[1][i] + kernel_size, 1], gauss))
            gauss_img[idx[0][i], idx[1][i], 2] = np.sum(
                np.multiply(pad_img[idx[0][i]:idx[0][i] + kernel_size, idx[1][i]:idx[1][i] + kernel_size, 2], gauss))

        cv2.imwrite(os.path.join(save_dir, file_name), gauss_img) 

def pull_item(self, index):
        img_id = self.ids[index]

        target = ET.parse(self._annopath % img_id).getroot()
        img = cv2.imread(self._imgpath % img_id)
        height, width, channels = img.shape

        if self.target_transform is not None:
            target = self.target_transform(target, width, height)

        if self.transform is not None:
            target = np.array(target)
            img, boxes, labels = self.transform(img, target[:, :4], target[:, 4])
            # to rgb
            img = img[:, :, (2, 1, 0)]
            # img = img.transpose(2, 0, 1)
            target = np.hstack((boxes, np.expand_dims(labels, axis=1)))

        if(img_id[0][(len(img_id[0]) - 7):]=='VOC2007'):
            semi = np.array([1])
        else:
            semi = np.array([0])
            target = np.zeros([1, 5])
        return torch.from_numpy(img).permute(2, 0, 1), target, height, width, semi
        # return torch.from_numpy(img), target, height, width 

def crop_images_random(path='../images/', scale=0.50):  # from utils.utils import *; crop_images_random()
    # crops images into random squares up to scale fraction
    # WARNING: overwrites images!
    for file in tqdm(sorted(glob.glob('%s/*.*' % path))):
        img = cv2.imread(file)  # BGR
        if img is not None:
            h, w = img.shape[:2]

            # create random mask
            a = 30  # minimum size (pixels)
            mask_h = random.randint(a, int(max(a, h * scale)))  # mask height
            mask_w = mask_h  # mask width

            # box
            xmin = max(0, random.randint(0, w) - mask_w // 2)
            ymin = max(0, random.randint(0, h) - mask_h // 2)
            xmax = min(w, xmin + mask_w)
            ymax = min(h, ymin + mask_h)

            # apply random color mask
            cv2.imwrite(file, img[ymin:ymax, xmin:xmax]) 

def __getitem__(self, index):
        datafiles = self.files[index]
        image = cv2.imread(datafiles["img"], cv2.IMREAD_COLOR)
        label = cv2.imread(datafiles["label"], cv2.IMREAD_GRAYSCALE)
        label = self.id2trainId(label)
        size = image.shape
        name = datafiles["name"]
        if self.scale:
            image, label = self.generate_scale_label(image, label)
        image = np.asarray(image, np.float32)
        image -= self.mean
        img_h, img_w = label.shape
        pad_h = max(self.crop_h - img_h, 0)
        pad_w = max(self.crop_w - img_w, 0)
        if pad_h > 0 or pad_w > 0:
            img_pad = cv2.copyMakeBorder(image, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT, 
                value=(0.0, 0.0, 0.0))
            label_pad = cv2.copyMakeBorder(label, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT,
                value=(self.ignore_label,))
        else:
            img_pad, label_pad = image, label

        img_h, img_w = label_pad.shape
        h_off = random.randint(0, img_h - self.crop_h)
        w_off = random.randint(0, img_w - self.crop_w)
        # roi = cv2.Rect(w_off, h_off, self.crop_w, self.crop_h);
        image = np.asarray(img_pad[h_off : h_off+self.crop_h, w_off : w_off+self.crop_w], np.float32)
        label = np.asarray(label_pad[h_off : h_off+self.crop_h, w_off : w_off+self.crop_w], np.float32)
        #image = image[:, :, ::-1]  # change to BGR
        image = image.transpose((2, 0, 1))
        if self.is_mirror:
            flip = np.random.choice(2) * 2 - 1
            image = image[:, :, ::flip]
            label = label[:, ::flip]

        return image.copy(), label.copy(), np.array(size), name 

def one_pic_to_video(image_path, output_video_path, fps, time):
    """
    一张图片合成视频
    one_pic_to_video('./../source/1.jpeg', './../source/output.mp4', 25, 10)
    :param path: 图片文件路径
    :param output_video_path:合成视频的路径
    :param fps:帧率
    :param time:时长
    :return:
    """

    image_clip = ImageClip(image_path)
    img_width, img_height = image_clip.w, image_clip.h

    # 总共的帧数
    frame_num = (int)(fps * time)

    img_size = (int(img_width), int(img_height))

    fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')

    video = cv2.VideoWriter(output_video_path, fourcc, fps, img_size)

    for index in range(frame_num):
        frame = cv2.imread(image_path)
        # 直接缩放到指定大小
        frame_suitable = cv2.resize(frame, (img_size[0], img_size[1]), interpolation=cv2.INTER_CUBIC)

        # 把图片写进视频
        # 重复写入多少次
        video.write(frame_suitable)

    # 释放资源
    video.release()

    return VideoFileClip(output_video_path) 

def __getitem__(self, index):
        datafiles = self.files[index]
        image = cv2.imread(datafiles["img"], cv2.IMREAD_COLOR)
        size = image.shape
        name = osp.splitext(osp.basename(datafiles["img"]))[0]
        image = np.asarray(image, np.float32)
        image -= self.mean
        
        img_h, img_w, _ = image.shape
        pad_h = max(self.crop_h - img_h, 0)
        pad_w = max(self.crop_w - img_w, 0)
        if pad_h > 0 or pad_w > 0:
            image = cv2.copyMakeBorder(image, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT, 
                value=(0.0, 0.0, 0.0))
        image = image.transpose((2, 0, 1))
        return image, name, size 

def __getitem__(self, index):
        datafiles = self.files[index]
        image = cv2.imread(datafiles["img"], cv2.IMREAD_COLOR)
        label = cv2.imread(datafiles["label"], cv2.IMREAD_GRAYSCALE)
        size = image.shape
        name = datafiles["name"]
        if self.scale:
            image, label = self.generate_scale_label(image, label)
        image = np.asarray(image, np.float32)
        image -= self.mean
        img_h, img_w = label.shape
        pad_h = max(self.crop_h - img_h, 0)
        pad_w = max(self.crop_w - img_w, 0)
        if pad_h > 0 or pad_w > 0:
            img_pad = cv2.copyMakeBorder(image, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT, 
                value=(0.0, 0.0, 0.0))
            label_pad = cv2.copyMakeBorder(label, 0, pad_h, 0, 
                pad_w, cv2.BORDER_CONSTANT,
                value=(self.ignore_label,))
        else:
            img_pad, label_pad = image, label

        img_h, img_w = label_pad.shape
        h_off = random.randint(0, img_h - self.crop_h)
        w_off = random.randint(0, img_w - self.crop_w)
        # roi = cv2.Rect(w_off, h_off, self.crop_w, self.crop_h);
        image = np.asarray(img_pad[h_off : h_off+self.crop_h, w_off : w_off+self.crop_w], np.float32)
        label = np.asarray(label_pad[h_off : h_off+self.crop_h, w_off : w_off+self.crop_w], np.float32)
        #image = image[:, :, ::-1]  # change to BGR
        image = image.transpose((2, 0, 1))
        if self.is_mirror:
            flip = np.random.choice(2) * 2 - 1
            image = image[:, :, ::flip]
            label = label[:, ::flip]

        return image.copy(), label.copy(), np.array(size), name 

def test_resize_short(self):
        try:
            import cv2
        except ImportError:
            return
        for img in TestImage.IMAGES:
            cv_img = cv2.imread(img)
            mx_img = mx.nd.array(cv_img[:, :, (2, 1, 0)])
            h, w, _ = cv_img.shape
            for _ in range(3):
                new_size = np.random.randint(1, 1000)
                if h > w:
                    new_h, new_w = new_size * h // w, new_size
                else:
                    new_h, new_w = new_size, new_size * w // h
                for interp in range(0, 2):
                    # area-based/lanczos don't match with cv2?
                    cv_resized = cv2.resize(cv_img, (new_w, new_h), interpolation=interp)
                    mx_resized = mx.image.resize_short(mx_img, new_size, interp)
                    assert_almost_equal(mx_resized.asnumpy()[:, :, (2, 1, 0)], cv_resized, atol=3) 

def image_channel_means(image_filenames):
    '''
    Calculate the means of RGB channels in image dataset.
    Support extremely large images of different sizes and arbitrarily large number of images.
    image_filenames: list of image filenames
    '''

    num_pixels = 0
    channel_sums = np.zeros(3, dtype=object)

    for image_filename in tqdm(image_filenames):
        image = cv2.imread(image_filename)
        channel_sums += np.sum(image, axis=(0, 1))
        num_pixels += np.prod(image.shape[:2])

    channel_means = (channel_sums / num_pixels).astype(float)

    return channel_means 

def draw():
    filenames = [os.path.splitext(f)[0] for f in glob.glob("for_task3/*.txt")]
    txt_files = [s + ".txt" for s in filenames]
    for txt in txt_files:
        image = cv2.imread('test_original/'+ txt.split('/')[1].split('.')[0]+'.jpg', cv2.IMREAD_COLOR)
        with open(txt, 'r') as txt_file:
            for line in csv.reader(txt_file):
                box = [int(string, 10) for string in line[0:8]]
                if len(line) < 9:
                    print(txt)
                cv2.rectangle(image, (box[0], box[1]), (box[4], box[5]), (0,255,0), 2)
                font = cv2.FONT_HERSHEY_SIMPLEX
                cv2.putText(image, line[8].upper(), (box[0],box[1]), font, 0.5, (0, 0, 255), 1, cv2.LINE_AA)
        cv2.imwrite('task2_result_draw/'+ txt.split('/')[1].split('.')[0]+'.jpg', image) 

def reWriteImgWithMask(srcpath, dstpath, gtpath, srcform, dstform):
    namelist = GetFileFromThisRootDir(gtpath)
    for fullname in namelist:
        objects = parse_bod_poly(fullname)
        mask_polys = []
        for obj in objects:
            clsname = obj['name']
            matches = re.findall('area|mask', clsname)
            if 'mask' in matches:
                #print('mask:')
                mask_polys.append(shgeo.Polygon(obj['poly']))
            elif 'area' in matches:
                #print('area:')
                mask_polys.append(shgeo.Polygon(obj['poly']))
        basename = mybasename(fullname)
        imgname = os.path.join(srcpath, basename + srcform)
        img = cv2.imread(imgname)
        dstname = os.path.join(dstpath, basename + dstform)
        if len(mask_polys) > 0:
            saveimageWithMask(img, dstname, mask_polys) 

def generator(vis=False):
    image_list = np.array(get_training_data())
    print('{} training images in {}'.format(image_list.shape[0], DATA_FOLDER))
    index = np.arange(0, image_list.shape[0])
    while True:
        np.random.shuffle(index)
        for i in index:
            try:
                im_fn = image_list[i]
                im = cv2.imread(im_fn)
                h, w, c = im.shape
                im_info = np.array([h, w, c]).reshape([1, 3])

                _, fn = os.path.split(im_fn)
                fn, _ = os.path.splitext(fn)
                txt_fn = os.path.join(DATA_FOLDER, "label", fn + '.txt')
                if not os.path.exists(txt_fn):
                    print("Ground truth for image {} not exist!".format(im_fn))
                    continue
                bbox = load_annoataion(txt_fn)
                if len(bbox) == 0:
                    print("Ground truth for image {} empty!".format(im_fn))
                    continue

                if vis:
                    for p in bbox:
                        cv2.rectangle(im, (p[0], p[1]), (p[2], p[3]), color=(0, 0, 255), thickness=1)
                    fig, axs = plt.subplots(1, 1, figsize=(30, 30))
                    axs.imshow(im[:, :, ::-1])
                    axs.set_xticks([])
                    axs.set_yticks([])
                    plt.tight_layout()
                    plt.show()
                    plt.close()
                yield [im], bbox, im_info

            except Exception as e:
                print(e)
                continue 

def draw():
    f = open(box_path + 'jpglist.txt')

    # read each image and its label
    line = f.readline()
    line_num =0
    while line:
        line_num=line_num+1
        print('Image:', line_num)
        name = line.strip('\n')
        img = cv2.imread(image_path + name)
        img_size = img.shape
        img_size = img_size[0]*img_size[1]

        # read each coordinate and draw box
        f_txt = open(image_path + name.strip('.jpg') + '.txt')
        #line_txt = f_txt.readline()  # pass the first ROI information
        line_txt = f_txt.readline()
        while line_txt:
            coor = line_txt.split(',')
            x1 = int(coor[0].strip('\''))
            y1 = int(coor[1].strip('\''))
            x3 = int(coor[4].strip('\''))
            y3 = int(coor[5].strip('\''))
            text = coor[8].strip('\n').strip('\'')
            text_show = text + '(' + str(x1) + ',' + str(y1) +')'

            cv2.rectangle(img, (x1, y1), (x3, y3), (255, 0, 0), 1)
            #cv2.putText(img, text_show, (x1, y1 - 1),
              #          cv2.FONT_HERSHEY_TRIPLEX, 0.35, (0, 0, 255), 1)
            line_txt = f_txt.readline()
        cv2.imwrite(box_path + name, img)
        line = f.readline()
        # img = cv2.imshow('image', img)
        # cv2.waitKey(0) 

def load_image(self, index):
    # loads 1 image from dataset
    img = self.imgs[index]
    if img is None:
        img_path = self.img_files[index]
        img = cv2.imread(img_path)  # BGR
        assert img is not None, 'Image Not Found ' + img_path
        r = self.img_size / max(img.shape)  # size ratio
        if self.augment and r < 1:  # if training (NOT testing), downsize to inference shape
            h, w, _ = img.shape
            img = cv2.resize(img, (int(w * r), int(h * r)), interpolation=cv2.INTER_LINEAR)  # _LINEAR fastest

    # Augment colorspace
    if self.augment:
        augment_hsv(img, hgain=self.hyp['hsv_h'], sgain=self.hyp['hsv_s'], vgain=self.hyp['hsv_v'])

    return img 

def preprocess(self, im, allobj = None):
	"""
	Takes an image, return it as a numpy tensor that is readily
	to be fed into tfnet. If there is an accompanied annotation (allobj),
	meaning this preprocessing is serving the train process, then this
	image will be transformed with random noise to augment training data,
	using scale, translation, flipping and recolor. The accompanied
	parsed annotation (allobj) will also be modified accordingly.
	"""
	if type(im) is not np.ndarray:
		im = cv2.imread(im)

	if allobj is not None: # in training mode
		result = imcv2_affine_trans(im)
		im, dims, trans_param = result
		scale, offs, flip = trans_param
		for obj in allobj:
			_fix(obj, dims, scale, offs)
			if not flip: continue
			obj_1_ =  obj[1]
			obj[1] = dims[0] - obj[3]
			obj[3] = dims[0] - obj_1_
		im = imcv2_recolor(im)

	im = self.resize_input(im)
	if allobj is None: return im
	return im#, np.array(im) # for unit testing 

def save_error(label, error_type, file_path):
    error_path = os.path.join(TEST_OUT_PATH, os.path.join(label, error_type))
    if not os.path.exists(error_path):
        os.makedirs(error_path)
    file_basename = os.path.basename(file_path)
    img = cv2.imread(file_path)
    dst_path = os.path.join(error_path, file_basename)
    cv2.imwrite(dst_path, img) 

def main():
    print('OpenCV version {} '.format(cv2.__version__))

    current_dir = os.path.dirname(__file__)

    author = '021'
    training_folder = os.path.join(current_dir, 'data/training/', author)
    test_folder = os.path.join(current_dir, 'data/test/', author)

    training_data = []
    for filename in os.listdir(training_folder):
        img = cv2.imread(os.path.join(training_folder, filename), 0)
        if img is not None:
            data = np.array(preprocessor.prepare(img))
            data = np.reshape(data, (901, 1))
            result = [[0], [1]] if "genuine" in filename else [[1], [0]]
            result = np.array(result)
            result = np.reshape(result, (2, 1))
            training_data.append((data, result))

    test_data = []
    for filename in os.listdir(test_folder):
        img = cv2.imread(os.path.join(test_folder, filename), 0)
        if img is not None:
            data = np.array(preprocessor.prepare(img))
            data = np.reshape(data, (901, 1))
            result = 1 if "genuine" in filename else 0
            test_data.append((data, result))

    net = network.NeuralNetwork([901, 500, 500, 2])
    net.sgd(training_data, 10, 50, 0.01, test_data)