layer_equalization: Preprocessing layer for histogram equalization on image...

In rstudio/keras: R Interface to 'Keras'

Preprocessing layer for histogram equalization on image channels.

Description

Histogram equalization is a technique to adjust image intensities to enhance contrast by effectively spreading out the most frequent intensity values. This layer applies equalization on a channel-wise basis, which can improve the visibility of details in images.

This layer works with both grayscale and color images, performing equalization independently on each color channel. At inference time, the equalization is consistently applied.

Note: This layer is safe to use inside a tf.data pipeline (independently of which backend you're using).

Input Shape

3D (unbatched) or 4D (batched) tensor with shape: ⁠(..., height, width, channels)⁠, in "channels_last" format, or ⁠(..., channels, height, width)⁠, in "channels_first" format.

Output Shape

3D (unbatched) or 4D (batched) tensor with shape: ⁠(..., target_height, target_width, channels)⁠, or ⁠(..., channels, target_height, target_width)⁠, in "channels_first" format.

Usage

layer_equalization(
  object,
  value_range = list(0L, 255L),
  bins = 256L,
  data_format = NULL,
  ...
)

Arguments

object	Object to compose the layer with. A tensor, array, or sequential model.
value_range	Optional list/tuple of 2 floats specifying the lower and upper limits of the input data values. Defaults to ⁠[0, 255]⁠. If the input image has been scaled, use the appropriate range (e.g., ⁠[0.0, 1.0]⁠). The equalization will be scaled to this range, and output values will be clipped accordingly.
bins	Integer specifying the number of histogram bins to use for equalization. Defaults to 256, which is suitable for 8-bit images. Larger values can provide more granular intensity redistribution.
data_format	String, one of "channels_last" (default) or "channels_first". The ordering of the dimensions in the inputs. "channels_last" corresponds to inputs with shape ⁠(batch, height, width, channels)⁠ while "channels_first" corresponds to inputs with shape ⁠(batch, channels, height, width)⁠.
...	For forward/backward compatability.

Examples

# Create an equalization layer for standard 8-bit images
equalizer <- layer_equalization()

# An image with uneven intensity distribution
image <- np_array(...) # your input image

# Apply histogram equalization
equalized_image <- equalizer(image)

# For images with custom value range
custom_equalizer <- layer_equalization(
    value_range=c(0.0, 1.0),  # for normalized images
    bins=128  # fewer bins for more subtle equalization
)
custom_equalized <- custom_equalizer(normalized_image)

See Also

Other image preprocessing layers:
layer_auto_contrast()
layer_center_crop()
layer_max_num_bounding_boxes()
layer_mix_up()
layer_rand_augment()
layer_random_color_degeneration()
layer_random_color_jitter()
layer_random_grayscale()
layer_random_hue()
layer_random_posterization()
layer_random_saturation()
layer_random_sharpness()
layer_random_shear()
layer_rescaling()
layer_resizing()
layer_solarization()

Other preprocessing layers:
layer_auto_contrast()
layer_category_encoding()
layer_center_crop()
layer_discretization()
layer_feature_space()
layer_hashed_crossing()
layer_hashing()
layer_integer_lookup()
layer_max_num_bounding_boxes()
layer_mel_spectrogram()
layer_mix_up()
layer_normalization()
layer_rand_augment()
layer_random_brightness()
layer_random_color_degeneration()
layer_random_color_jitter()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_grayscale()
layer_random_hue()
layer_random_posterization()
layer_random_rotation()
layer_random_saturation()
layer_random_sharpness()
layer_random_shear()
layer_random_translation()
layer_random_zoom()
layer_rescaling()
layer_resizing()
layer_solarization()
layer_stft_spectrogram()
layer_string_lookup()
layer_text_vectorization()

Other layers:
Layer()
layer_activation()
layer_activation_elu()
layer_activation_leaky_relu()
layer_activation_parametric_relu()
layer_activation_relu()
layer_activation_softmax()
layer_activity_regularization()
layer_add()
layer_additive_attention()
layer_alpha_dropout()
layer_attention()
layer_auto_contrast()
layer_average()
layer_average_pooling_1d()
layer_average_pooling_2d()
layer_average_pooling_3d()
layer_batch_normalization()
layer_bidirectional()
layer_category_encoding()
layer_center_crop()
layer_concatenate()
layer_conv_1d()
layer_conv_1d_transpose()
layer_conv_2d()
layer_conv_2d_transpose()
layer_conv_3d()
layer_conv_3d_transpose()
layer_conv_lstm_1d()
layer_conv_lstm_2d()
layer_conv_lstm_3d()
layer_cropping_1d()
layer_cropping_2d()
layer_cropping_3d()
layer_dense()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_feature_space()
layer_flatten()
layer_flax_module_wrapper()
layer_gaussian_dropout()
layer_gaussian_noise()
layer_global_average_pooling_1d()
layer_global_average_pooling_2d()
layer_global_average_pooling_3d()
layer_global_max_pooling_1d()
layer_global_max_pooling_2d()
layer_global_max_pooling_3d()
layer_group_normalization()
layer_group_query_attention()
layer_gru()
layer_hashed_crossing()
layer_hashing()
layer_identity()
layer_integer_lookup()
layer_jax_model_wrapper()
layer_lambda()
layer_layer_normalization()
layer_lstm()
layer_masking()
layer_max_num_bounding_boxes()
layer_max_pooling_1d()
layer_max_pooling_2d()
layer_max_pooling_3d()
layer_maximum()
layer_mel_spectrogram()
layer_minimum()
layer_mix_up()
layer_multi_head_attention()
layer_multiply()
layer_normalization()
layer_permute()
layer_rand_augment()
layer_random_brightness()
layer_random_color_degeneration()
layer_random_color_jitter()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_grayscale()
layer_random_hue()
layer_random_posterization()
layer_random_rotation()
layer_random_saturation()
layer_random_sharpness()
layer_random_shear()
layer_random_translation()
layer_random_zoom()
layer_repeat_vector()
layer_rescaling()
layer_reshape()
layer_resizing()
layer_rnn()
layer_separable_conv_1d()
layer_separable_conv_2d()
layer_simple_rnn()
layer_solarization()
layer_spatial_dropout_1d()
layer_spatial_dropout_2d()
layer_spatial_dropout_3d()
layer_spectral_normalization()
layer_stft_spectrogram()
layer_string_lookup()
layer_subtract()
layer_text_vectorization()
layer_tfsm()
layer_time_distributed()
layer_torch_module_wrapper()
layer_unit_normalization()
layer_upsampling_1d()
layer_upsampling_2d()
layer_upsampling_3d()
layer_zero_padding_1d()
layer_zero_padding_2d()
layer_zero_padding_3d()
rnn_cell_gru()
rnn_cell_lstm()
rnn_cell_simple()
rnn_cells_stack()

rstudio/keras documentation built on Feb. 4, 2025, 1:11 p.m.