Tensorflow: how to rotate an image to increase data?

Question

In a tensor stream, I would like to rotate the image from a random angle to increase the data. But I do not find this conversion in the tf.image module.

Answer 1

Update : see @astromme below. Tensorflow now supports rotation images natively.

What you can do when there is no native method in tensorflow is something like this:

from PIL import Image sess = tf.InteractiveSession() # Pass image tensor object to a PIL image image = Image.fromarray(image.eval()) # Use PIL or other library of the sort to rotate rotated = Image.Image.rotate(image, degrees) # Convert rotated image back to tensor rotated_tensor = tf.convert_to_tensor(np.array(rotated)) 

Answer 2

This can be done in tensorflow now :

 tf.contrib.image.rotate(images, degrees * math.pi / 180, interpolation='BILINEAR') 

Answer 3

Since I wanted to rotate the tensors, I came up with the following code fragment that rotates the tensor [height, width, depth] by a given angle:

 def rotate_image_tensor(image, angle, mode='black'): """ Rotates a 3D tensor (HWD), which represents an image by given radian angle. New image has the same size as the input image. mode controls what happens to border pixels. mode = 'black' results in black bars (value 0 in unknown areas) mode = 'white' results in value 255 in unknown areas mode = 'ones' results in value 1 in unknown areas mode = 'repeat' keeps repeating the closest pixel known """ s = image.get_shape().as_list() assert len(s) == 3, "Input needs to be 3D." assert (mode == 'repeat') or (mode == 'black') or (mode == 'white') or (mode == 'ones'), "Unknown boundary mode." image_center = [np.floor(x/2) for x in s] # Coordinates of new image coord1 = tf.range(s[0]) coord2 = tf.range(s[1]) # Create vectors of those coordinates in order to vectorize the image coord1_vec = tf.tile(coord1, [s[1]]) coord2_vec_unordered = tf.tile(coord2, [s[0]]) coord2_vec_unordered = tf.reshape(coord2_vec_unordered, [s[0], s[1]]) coord2_vec = tf.reshape(tf.transpose(coord2_vec_unordered, [1, 0]), [-1]) # center coordinates since rotation center is supposed to be in the image center coord1_vec_centered = coord1_vec - image_center[0] coord2_vec_centered = coord2_vec - image_center[1] coord_new_centered = tf.cast(tf.pack([coord1_vec_centered, coord2_vec_centered]), tf.float32) # Perform backward transformation of the image coordinates rot_mat_inv = tf.dynamic_stitch([[0], [1], [2], [3]], [tf.cos(angle), tf.sin(angle), -tf.sin(angle), tf.cos(angle)]) rot_mat_inv = tf.reshape(rot_mat_inv, shape=[2, 2]) coord_old_centered = tf.matmul(rot_mat_inv, coord_new_centered) # Find nearest neighbor in old image coord1_old_nn = tf.cast(tf.round(coord_old_centered[0, :] + image_center[0]), tf.int32) coord2_old_nn = tf.cast(tf.round(coord_old_centered[1, :] + image_center[1]), tf.int32) # Clip values to stay inside image coordinates if mode == 'repeat': coord_old1_clipped = tf.minimum(tf.maximum(coord1_old_nn, 0), s[0]-1) coord_old2_clipped = tf.minimum(tf.maximum(coord2_old_nn, 0), s[1]-1) else: outside_ind1 = tf.logical_or(tf.greater(coord1_old_nn, s[0]-1), tf.less(coord1_old_nn, 0)) outside_ind2 = tf.logical_or(tf.greater(coord2_old_nn, s[1]-1), tf.less(coord2_old_nn, 0)) outside_ind = tf.logical_or(outside_ind1, outside_ind2) coord_old1_clipped = tf.boolean_mask(coord1_old_nn, tf.logical_not(outside_ind)) coord_old2_clipped = tf.boolean_mask(coord2_old_nn, tf.logical_not(outside_ind)) coord1_vec = tf.boolean_mask(coord1_vec, tf.logical_not(outside_ind)) coord2_vec = tf.boolean_mask(coord2_vec, tf.logical_not(outside_ind)) coord_old_clipped = tf.cast(tf.transpose(tf.pack([coord_old1_clipped, coord_old2_clipped]), [1, 0]), tf.int32) # Coordinates of the new image coord_new = tf.transpose(tf.cast(tf.pack([coord1_vec, coord2_vec]), tf.int32), [1, 0]) image_channel_list = tf.split(2, s[2], image) image_rotated_channel_list = list() for image_channel in image_channel_list: image_chan_new_values = tf.gather_nd(tf.squeeze(image_channel), coord_old_clipped) if (mode == 'black') or (mode == 'repeat'): background_color = 0 elif mode == 'ones': background_color = 1 elif mode == 'white': background_color = 255 image_rotated_channel_list.append(tf.sparse_to_dense(coord_new, [s[0], s[1]], image_chan_new_values, background_color, validate_indices=False)) image_rotated = tf.transpose(tf.pack(image_rotated_channel_list), [1, 2, 0]) return image_rotated 

Answer 4

Rotate and crop in TensorFlow

I personally needed to rotate the image and crop the black borders in TensorFlow, as shown below. And I could implement this function as shown below.

 def _rotate_and_crop(image, output_height, output_width, rotation_degree, do_crop): """Rotate the given image with the given rotation degree and crop for the black edges if necessary Args: image: A 'Tensor' representing an image of arbitrary size. output_height: The height of the image after preprocessing. output_width: The width of the image after preprocessing. rotation_degree: The degree of rotation on the image. do_crop: Do cropping if it is True. Returns: A rotated image. """ # Rotate the given image with the given rotation degree if rotation_degree != 0: image = tf.contrib.image.rotate(image, math.radians(rotation_degree), interpolation='BILINEAR') # Center crop to ommit black noise on the edges if do_crop == True: lrr_width, lrr_height = _largest_rotated_rect(output_height, output_width, math.radians(rotation_degree)) resized_image = tf.image.central_crop(image, float(lrr_height)/output_height) image = tf.image.resize_images(resized_image, [output_height, output_width], method=tf.image.ResizeMethod.BILINEAR, align_corners=False) return image def _largest_rotated_rect(w, h, angle): """ Given a rectangle of size wxh that has been rotated by 'angle' (in radians), computes the width and height of the largest possible axis-aligned rectangle within the rotated rectangle. Original JS code by 'Andri' and Magnus Hoff from Stack Overflow Converted to Python by Aaron Snoswell Source: http://stackoverflow.com/questions/16702966/rotate-image-and-crop-out-black-borders """ quadrant = int(math.floor(angle / (math.pi / 2))) & 3 sign_alpha = angle if ((quadrant & 1) == 0) else math.pi - angle alpha = (sign_alpha % math.pi + math.pi) % math.pi bb_w = w * math.cos(alpha) + h * math.sin(alpha) bb_h = w * math.sin(alpha) + h * math.cos(alpha) gamma = math.atan2(bb_w, bb_w) if (w < h) else math.atan2(bb_w, bb_w) delta = math.pi - alpha - gamma length = h if (w < h) else w d = length * math.cos(alpha) a = d * math.sin(alpha) / math.sin(delta) y = a * math.cos(gamma) x = y * math.tan(gamma) return ( bb_w - 2 * x, bb_h - 2 * y ) 

If you need further implementation of the example and visualization in TensorFlow, you can use this repository . I hope this can be useful for other people.

Answer 5

Here @ zimmermc answer updated to Tensorflow v0.12

Changes:

• pack() now stack()

• split order of modified parameters

   def rotate_image_tensor(image, angle, mode='white'): """ Rotates a 3D tensor (HWD), which represents an image by given radian angle. New image has the same size as the input image. mode controls what happens to border pixels. mode = 'black' results in black bars (value 0 in unknown areas) mode = 'white' results in value 255 in unknown areas mode = 'ones' results in value 1 in unknown areas mode = 'repeat' keeps repeating the closest pixel known """ s = image.get_shape().as_list() assert len(s) == 3, "Input needs to be 3D." assert (mode == 'repeat') or (mode == 'black') or (mode == 'white') or (mode == 'ones'), "Unknown boundary mode." image_center = [np.floor(x/2) for x in s] # Coordinates of new image coord1 = tf.range(s[0]) coord2 = tf.range(s[1]) # Create vectors of those coordinates in order to vectorize the image coord1_vec = tf.tile(coord1, [s[1]]) coord2_vec_unordered = tf.tile(coord2, [s[0]]) coord2_vec_unordered = tf.reshape(coord2_vec_unordered, [s[0], s[1]]) coord2_vec = tf.reshape(tf.transpose(coord2_vec_unordered, [1, 0]), [-1]) # center coordinates since rotation center is supposed to be in the image center coord1_vec_centered = coord1_vec - image_center[0] coord2_vec_centered = coord2_vec - image_center[1] coord_new_centered = tf.cast(tf.stack([coord1_vec_centered, coord2_vec_centered]), tf.float32) # Perform backward transformation of the image coordinates rot_mat_inv = tf.dynamic_stitch([[0], [1], [2], [3]], [tf.cos(angle), tf.sin(angle), -tf.sin(angle), tf.cos(angle)]) rot_mat_inv = tf.reshape(rot_mat_inv, shape=[2, 2]) coord_old_centered = tf.matmul(rot_mat_inv, coord_new_centered) # Find nearest neighbor in old image coord1_old_nn = tf.cast(tf.round(coord_old_centered[0, :] + image_center[0]), tf.int32) coord2_old_nn = tf.cast(tf.round(coord_old_centered[1, :] + image_center[1]), tf.int32) # Clip values to stay inside image coordinates if mode == 'repeat': coord_old1_clipped = tf.minimum(tf.maximum(coord1_old_nn, 0), s[0]-1) coord_old2_clipped = tf.minimum(tf.maximum(coord2_old_nn, 0), s[1]-1) else: outside_ind1 = tf.logical_or(tf.greater(coord1_old_nn, s[0]-1), tf.less(coord1_old_nn, 0)) outside_ind2 = tf.logical_or(tf.greater(coord2_old_nn, s[1]-1), tf.less(coord2_old_nn, 0)) outside_ind = tf.logical_or(outside_ind1, outside_ind2) coord_old1_clipped = tf.boolean_mask(coord1_old_nn, tf.logical_not(outside_ind)) coord_old2_clipped = tf.boolean_mask(coord2_old_nn, tf.logical_not(outside_ind)) coord1_vec = tf.boolean_mask(coord1_vec, tf.logical_not(outside_ind)) coord2_vec = tf.boolean_mask(coord2_vec, tf.logical_not(outside_ind)) coord_old_clipped = tf.cast(tf.transpose(tf.stack([coord_old1_clipped, coord_old2_clipped]), [1, 0]), tf.int32) # Coordinates of the new image coord_new = tf.transpose(tf.cast(tf.stack([coord1_vec, coord2_vec]), tf.int32), [1, 0]) image_channel_list = tf.split(image, s[2], 2) image_rotated_channel_list = list() for image_channel in image_channel_list: image_chan_new_values = tf.gather_nd(tf.squeeze(image_channel), coord_old_clipped) if (mode == 'black') or (mode == 'repeat'): background_color = 0 elif mode == 'ones': background_color = 1 elif mode == 'white': background_color = 255 image_rotated_channel_list.append(tf.sparse_to_dense(coord_new, [s[0], s[1]], image_chan_new_values, background_color, validate_indices=False)) image_rotated = tf.transpose(tf.stack(image_rotated_channel_list), [1, 2, 0]) return image_rotated 

Answer 6

You can use tf.image.rot90(image,k=1,name=None) to rotate an image or a packet of images counterclockwise with a magnification of 90 degrees.

k indicates the number of 90 degree turns you want to make.

In the case of a single image, image is a 3-D Tensor of shape [height, width, channels] and in the case of an image pack, image is a 4-D Tensor of shape [batch, height, width, channels]

Answer 7

for tensor flow 2.0:

 import tensorflow_addons as tfa tfa.image.transform_ops.rotate(image, radian)