3+N layer mixed raster content (MRC) images and processing thereof
A method for processing image data includes using advantages of both a three-layer MRC model and an N-layer MRC model to create a new 3+N layer MRC model and to generate a 3+N layer MRC image. The method includes providing input image data; segmenting the input image data to generate: (i) a background layer representing the background and the pictorial attributes of the image data, (ii) one or more binary foreground layers, (iii) a selector layer, and (iv) a contone foreground layer representing the foreground attributes of the image data on the background layer; and integrating the background layer, the selector layer, the contone foreground layer, and the one or more binary foreground layers into a data structure having machine-readable information for storage in a memory device. Each binary foreground layer includes one or more pixel clusters representing text pixels of a particular color in the input image data.
1. A method for processing image data, comprising:
using at least one processor to perform the following:
providing input image data;
extracting at least text and line art features from the input image data into a text image data;
subtracting the text image data from the input image data to obtain a first background layer, the first background layer comprising text and line art features not extracted from the input image data and pictorial features of the input image data;
processing the text image data to generate:
one or more first binary foreground layers, wherein each first binary foreground layer comprises one or more pixel clusters representing text and line art pixels of a particular color in the text image data;
segmenting the first background layer to generate:
a second background layer representing the background attributes of the first background layer;
a second contone foreground layer representing the foreground attributes of the first background layer; and
a selector layer for identifying one or more foreground attributes of the second contone foreground layer not included in the second background layer; and
integrating the second background layer, the selector layer, the second contone foreground layer, and the one or more first binary foreground layers into a data structure having machine-readable information for storage in a memory device.
2. The method according to claim 1 , wherein the second contone foreground layer comprises text-on-tint information, pictorial color information, and pictorial edge information.
3. The method according to claim 1 , wherein the second background layer comprises pictorial and background information.
4. The method according to claim 1 , wherein segmenting the text image data to generate one or more first binary foreground layers is based on the color and spatial proximity of different text and line art features.
5. The method according to claim 1 , wherein extracting at least text and line art features from the input image data is performed on white-colored areas or background areas.
6. A data structure having machine-readable information for storage in a memory device that when implemented by a processor render an image, the data structure comprising:
one or more binary foreground layers, wherein each binary foreground layer comprises one or more pixel clusters representing text and line art pixels of a particular color in an image;
a contone foreground layer representing the foreground attributes of a first background layer of the image, wherein the first background layer comprises text and line art features of the image not included in the binary foreground layers and pictorial features of the image;
a second background layer representing the background attributes of the first background layer; and
a selector layer for identifying one or more foreground attributes of the contone foreground layer not included in the second background layer.