Contrast Limited Adaptive Histogram Equalization

Contrast Limited Adaptive Histogram Equalization (CLAHE) is a variant of adaptive histogram equalization that avoids over-amplifying contrast. It operates on small image regions called tiles rather than on the entire image, then combines neighboring tiles with bilinear interpolation to remove artificial boundaries. This can improve image contrast.

Usage

layer_contrast_limited_adaptive_histogram_equalization(
  object,
  value_range = c(0L, 255L),
  clip_limit = 4,
  tile_grid_size = c(8L, 8L),
  data_format = NULL,
  ...
)

Arguments

object: Object to compose the layer with. A tensor, array, or sequential model.
value_range: Two numbers giving the lower and upper limits of input values. Defaults to c(0, 255).
clip_limit: Number that limits noise amplification in near-constant regions. Defaults to 4.
tile_grid_size: Two integers, (height, width), giving the number of tiles into which to divide the image. Defaults to c(8, 8).
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 compatibility.

Value

The return value depends on the value provided for the first argument. If object is:

a keras_model_sequential(), then the layer is added to the sequential model (which is modified in place). To enable piping, the sequential model is also returned, invisibly.
a keras_input(), then the output tensor from calling layer(input) is returned.
NULL or missing, then a Layer instance is returned.

Details

Note: This layer computes histograms using backend one-hot operations, which can be highly memory intensive. Large batches or high-resolution images can lead to high memory consumption or out-of-memory errors.

Input shape

A 3D unbatched or 4D batched tensor with shape (..., height, width, channels) when data_format = "channels_last", or (..., channels, height, width) when data_format = "channels_first".

Output shape

A tensor with the same rank and shape as the input.

Examples

image <- op_reshape(op_arange(16, dtype = "float32"), c(1, 4, 4, 1))
output <- image |>
  layer_contrast_limited_adaptive_histogram_equalization(
    value_range = c(0, 15),
    tile_grid_size = c(2, 2)
  )
shape(output)

## shape(1, 4, 4, 1)

Other image preprocessing layers:
layer_aug_mix()
layer_auto_contrast()
layer_center_crop()
layer_cut_mix()
layer_equalization()
layer_max_num_bounding_boxes()
layer_mix_up()
layer_rand_augment()
layer_random_color_degeneration()
layer_random_color_jitter()
layer_random_elastic_transform()
layer_random_erasing()
layer_random_gaussian_blur()
layer_random_grayscale()
layer_random_hue()
layer_random_invert()
layer_random_perspective()
layer_random_posterization()
layer_random_saturation()
layer_random_sharpness()
layer_random_shear()
layer_rescaling()
layer_resizing()
layer_solarization()

Other preprocessing layers:
layer_aug_mix()
layer_auto_contrast()
layer_category_encoding()
layer_center_crop()
layer_cut_mix()
layer_discretization()
layer_equalization()
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_elastic_transform()
layer_random_erasing()
layer_random_flip()
layer_random_gaussian_blur()
layer_random_grayscale()
layer_random_hue()
layer_random_invert()
layer_random_perspective()
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_adaptive_average_pooling_1d()
layer_adaptive_average_pooling_2d()
layer_adaptive_average_pooling_3d()
layer_adaptive_max_pooling_1d()
layer_adaptive_max_pooling_2d()
layer_adaptive_max_pooling_3d()
layer_add()
layer_additive_attention()
layer_alpha_dropout()
layer_attention()
layer_aug_mix()
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_cut_mix()
layer_dense()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_equalization()
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_elastic_transform()
layer_random_erasing()
layer_random_flip()
layer_random_gaussian_blur()
layer_random_grayscale()
layer_random_hue()
layer_random_invert()
layer_random_perspective()
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_reversible_embedding()
layer_rms_normalization()
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()