Clusters the unique colors of an image using the K-means algorithm.

Arguments

• image is any 3- or 4-band Vix.Vips.Image.t/0 with {:u, 8} band format.

• options is a keyword list of options passed to Scholar.Cluster.KMeans.fit/2.

Returns

• {:ok, model} where model is a fitted Scholar.Cluster.KMeans or

• {:error, reason}.

Examples

iex> image = Image.open!("./test/support/images/Kip_small.jpg")
iex> {:ok, model} = Image.Scholar.k_means(image, num_clusters: 3, key: Nx.Random.key(42))
iex> Nx.shape(model.clusters)
{3, 3}

@spec unique_color_count(image_or_tensor :: Vix.Vips.Image.t() | Nx.Tensor.t()) ::
  {:ok, non_neg_integer()} | {:error, Image.Error.t()}

Returns the number of unique colors in an image.

Prefer this over unique_colors/1 when only the count is needed.

Arguments

• image_or_tensor is any 3- or 4-band Vix.Vips.Image.t/0 with {:u, 8} band format, or the {height, width, bands} tensor of such an image as returned by Image.to_nx/2. Pass the tensor when one is already to hand, to avoid converting the image twice.

Returns

• {:ok, count} or

• {:error, reason}.

Example

iex> Image.Scholar.unique_color_count(Image.new!(4, 4, color: :red))
{:ok, 1}

Returns the unique colors in an image and the count of each color.

Arguments

• image is any 3- or 4-band Vix.Vips.Image.t/0 with {:u, 8} band format.

Returns

• {:ok, {color_count_tensor, unique_colors_tensor}} or

• {:error, reason}.

Examples

iex> image = Image.new!(8, 8, color: [10, 20, 30])
iex> {:ok, {counts, colors}} = Image.Scholar.unique_colors(image)
iex> {Nx.shape(counts), Nx.shape(colors)}
{{1}, {1, 3}}