Apparatus and method for transforming image in mobile device

• US 8,265,415 B2
• Filed: 12/17/2008
• Issued: 09/11/2012
• Est. Priority Date: 12/17/2007
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Choi, Yoon-Seok, Koo, Bon Ki, Lee, Ji Hyung, Kim, Bo Youn, Kim, Hee Jeong, Park, Il Kyu, Lee, Seung Wook, Shin, Seung Hyup
• Primary Examiner(s): Couso, Yon
• Application Number:
  US12/314,857
• Publication Number:
  US 20090154841A1
• Time in Patent Office: 1,364 Days
• Field of Search: 382/264, 382/260, 382/266, 382/276, 382/277, 382/307
• US Class Current: 382/264
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 2200/32 involving image mosaicing

Abstract

An apparatus for transforming an image in a mobile device is disclosed. The apparatus comprises a pen style transformation unit for transforming an original image to a pen style image using a separated Gaussian filter and outputting pen style image, a cartoon style transformation unit for transforming the original image to a cartoon style image and outputting the cartoon style image, a mosaic creation unit for creating a photomosaic to which the original image is applied based on an optimum photo image set and outputting the created photo mosaic by applying the created photo mosaic to the original image, and an image output unit for outputting the images output from the pen style transformation unit, the cartoon style transformation unit, and the mosaic creation unit to an output unit.

Claims

1. An apparatus for transforming an image in a mobile device, the apparatus comprising:

a pen style transformation unit for transforming an original image to a pen style image which is drawn by a pen using a separated Gaussian filter and outputting the pen style image;

a cartoon style transformation unit for transforming the original image to a cartoon style image having characteristics of a cartoon and outputting the cartoon style image;

a mosaic creation unit for creating a photo mosaic of images in a mosaic pattern to which the original image is applied based on an optimum photo image set and outputting the created photo mosaic by applying the created photo mosaic to the original image; and

an image output unit for outputting the images output from the pen style transformation unit, the cartoon style transformation unit, and the mosaic creation unit to an output unit.

2. The apparatus of claim 1, wherein the separated Gaussian filter includes a horizontal Gaussian blur filter and a vertical Gaussian blur filter.

3. The apparatus of claim 2, wherein the pen style transformation unit includes:

a means for calculating an intermediate value by applying the horizontal Gaussian blur filter to the original image; and

a means for calculating a final value by applying the vertical Gaussian blur filter to the intermediate value.

4. The apparatus of claim 3, wherein the pen style transformation unit includes:

a temporary memory space having rows and columns of a size of m by l obtained by transposing rows and columns of a size of l by m of the original image;

a means for storing in the temporary memory space a transposed intermediate value obtained by transposing the rows and columns of the intermediate value; and

a means for calculating the final value by applying the vertical Gaussian blur filter in a direction of the rows of the temporary memory space to the transposed intermediate value.

5. The apparatus of claim 1, wherein the cartoon style transformation unit includes:

a smoother for smoothing the original image;

a quantizer for quantizing the smoothed original image and reducing the number of distinct colors used in an smoothed image thereof;

a contour extractor for extracting contours of spaces for the colors;

an abstractor for abstracting key features of the contours extracted by the contour extractor; and

a cartoonizer for creating a cartoon image using information about the abstracted contours and information about the original image and for outputting the created cartoon image to the output unit.

6. The apparatus of claim 5, wherein the cartoon style transformation unit further includes:

an edge extractor for extracting edge information from the smoothed image, and

wherein the cartoonizer combines the edge information with the cartoon image and outputs the cartoon image combined with the edge information to the image outputter.

7. The apparatus of claim 6, the cartoon style transformation unit further includes:

an edge abstractor for abstracting key features of the edge shape extracted by the edge extractor, and

wherein the cartoon style transformation unit combines the abstracted edge information with the cartoon image and outputs the cartoon image combined with the abstracted edge information to the image output unit.

8. The apparatus of claim 5, wherein the smoother reduces the original image at a specific ratio and then smoothes the original image.

9. The apparatus of claim 8, wherein the quantizer restores a size of the smoothed image to a size of the original image, and then quantizes the smoothed original image.

10. The apparatus of claim 1, wherein the optimum photo image set is a set of images extracted from an image set for creation of an entire mosaic through a featured image optimizing technology.