1. Basic principles
In the grayscale image, the pixel values of the range [0, 255], i.e., a total of 256 gray levels. In the computer, we use eight bits to represent each pixel value. It is possible to extract different bit levels of grayscale. Bit-level stratification can be used for picture compression : only a bit higher storage layer (Why use a higher level, rather than the lower layer by binary conversion, we know that a greater contribution to a higher level in the value of?); Such as the use of the high four bits layer represents the original eight bit-planes.
2. Test results
FIG derived skimage
3. Code
1 def extract_bit_layer(input_image, layer_num): 2 ''' 3 提取比特层 4 :param input_image: 原图像 5 :param layer_num: 提取层 6 :return: 提取到的比特层 7 ''' 8 input_image_cp = np.copy(input_image) # 输入图片的副本 9 10 if layer_num == 1: 11 input_image_cp = np.where((input_image_cp >= 0) & (input_image_cp < 2), 255, 0) 12 elif layer_num == 2: 13 input_image_cp = np.where((input_image_cp >= 2) & (input_image_cp < 4), 255, 0) 14 elif layer_num == 3: 15 input_image_cp = np.where((input_image_cp >= 4) & (input_image_cp < 8), 255, 0) 16 elif layer_num == 4: 17 input_image_cp = np.where((input_image_cp >= 8) & (input_image_cp < 16), 255, 0) 18 elif layer_num == 5: 19 input_image_cp = np.where((input_image_cp >= 16) & (input_image_cp < 32), 255, 0) 20 elif layer_num == 6: 21 input_image_cp = np.where((input_image_cp >= 32) & (input_image_cp < 64), 255, 0) 22 elif layer_num == 7: 23 input_image_cp = np.where((input_image_cp >= 64) & (input_image_cp < 128), 255, 0) 24 elif layer_num == 8: 25 input_image_cp = np.where((input_image_cp >= 128) & (input_image_cp < 256), 255, 0) 26 else: 27 print("please enter the number of bit layers from 1 to 8") 28 29 output_image = input_image_cp 30 31 return output_image