Color Recognition

Uploadcare Image Transformations features the main_colors operation extracting a specified number of prevailing colors from an image. The operation is implemented as a URL directive following our general image transformations workflow.

-/main_colors/:number_of_colors/

main_colors is useful for analyzing dominant colors of an image, matching colors between images, building image-based palettes or doing something fancy with your site or app coloring scheme.

Note, the main_colors operation should come last in your image URL.

:number_of_colors — a number of prevailing colors you’d like to extract from an image: a smaller palette is derived, consisting of colors that are a fine match when representing your input. :number_of_colors may be omitted, the default value of 4 is used in the case.

main_colors returns a JSON containing an array of 8-bit RGB values specific to the found dominant colors. For example, for this input image, the operation with no specified parameters will return this JSON,

/:uuid/-/preview/-/main_colors/
{
  "width": 2000,
  "main_colors": [
    [138, 142, 143],
    [85, 74, 65],
    [193, 211, 224],
    [49, 42, 36]
  ],
  "height": 2000,
  "id": "/153d750a-049f-44dc-8372-853f49320bad/-/preview/",
  "original": {
    "width": 2000,
    "geo_location": null,
    "orientation": null,
    "datetime_original": null,
    "format": "JPEG",
    "id": "153d750a-049f-44dc-8372-853f49320bad",
    "height": 2000
  }
}

Note, the main_colors algorithm involves random number generation, which may lead to slightly different results when applied to a single image repeatedly.

Technically, the operation is an optimized variation of the Local K-means color image quantization algorithm. The algorithm is adapted to a wide variety of input image data and provides results intuitive in terms of human perception.