IMAGE PROCESSING METHOD AND IMAGE PROCESSING APPARATUS

• US 20110116141A1
• Filed: 01/14/2010
• Published: 05/19/2011
• Est. Priority Date: 11/13/2009
• Status: Active Grant

• Current Assignee: Primax Electronics Limited
• Original Assignee: Primax Electronics Limited
• Inventors: Wang, Chiung-Sheng, Lin, Sung-Hui, Cho, Li-Kai, Chien, Hui-Jan, Chen, Tsai-Hsing
• Granted Patent: US 8,233,713 B2
• Time in Patent Office: Days
• US Class Current: 358/462
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

An image processing method, for receiving an input image and separating pixels having text characteristics and pixels having figure characteristics, includes: applying a first filtering processing for the input image to derive a first image processing result; applying a second filtering processing for the first image processing result to derive a second image processing result, wherein a distribution of filtering parameters of the first filtering processing is different from a distribution of filtering parameters of the second filtering processing; deriving a set of first reference values according to the first image processing result and the second image processing result; and determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the first reference values and a predetermined threshold.

Claims

1. An image processing method, for receiving an input image and separating pixels having text characteristics and pixels having figure characteristics, comprising:

applying a first filtering processing for the input image to derive a first image processing result;

applying a second filtering processing for the first image processing result to derive a second image processing result, wherein a distribution of filtering parameters of the first filtering processing is different from a distribution of filtering parameters of the second filtering processing;

deriving a set of first reference values according to the first image processing result and the second image processing result; and

determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the first reference values and a predetermined threshold.

2. The image processing method of claim 1, wherein the step of determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the first reference values and a predetermined threshold comprises:

applying a third filtering processing for the set of first reference values to derive a set of second reference values, wherein a distribution of filtering parameters of the third filtering processing is different from a distribution of filtering parameters of the first filtering processing and the second filtering processing; and

determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the second reference values and the predetermined threshold.

3. The image processing method of claim 2, wherein the distribution of filtering parameters of the third filtering processing is a Gaussian distribution.

4. The image processing method of claim 1, wherein the set of first reference values is determined from a difference between a first luminance value of each pixel in the first image processing result and a second luminance value of a corresponding pixel located at an identical position in the second image processing result.

5. The image processing method of claim 1, wherein the second filtering processing is an average filtering processing.

6. The image processing method of claim 1, wherein the distribution of filtering parameters of the first filtering processing forms a matrix, the matrix comprises a plurality of entries, a center entry of the matrix has a filtering parameter maximum value, edge entries and internal entries of the matrix are different in sign, and each entry in a direction from the center entry to each edge entry has a filtering parameter whose magnitude increases with a decreasing distance between the entry and the center entry.

7. The image processing method of claim 1, further comprising:

for each pixel within the input image;

outputting a text data or a figure data corresponding to the pixel according to whether the pixel is a text pixel or a figure pixel.

8. The image processing method of claim 7, wherein the text data is generated from the input image via a text filtering processing.

9. The image processing method of claim 7, wherein the figure data comprises a luminance data and a chroma data, the luminance data is generated according to the second image processing result, and the chroma data is generated from the input image via a figure filtering processing.

10. An image processing apparatus, for receiving an input image and separating pixels having text characteristics and pixels having figure characteristics, comprising:

a first filtering module, for applying a first filtering processing for the input image to derive a first image processing result;

a second filtering module, coupled to the first filtering module, for applying a second filtering processing for the first image processing result to derive a second image processing result, wherein a distribution of filtering parameters of the first filtering processing is different from a distribution of filtering parameters of the second filtering processing;

a calculation module, coupled to the first filtering module and the second filtering module, for deriving a set of first reference values according to the first image processing result and the second image processing result; and

a determining module, coupled to the calculation module, for determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the first reference values and a predetermined threshold.

11. The image processing apparatus of claim 10, wherein the determining module comprises:

a third filtering module, coupled to the calculation module, for applying a third filtering processing for the set of first reference values to derive a set of second reference values, wherein a distribution of filtering parameters of the third filtering processing is different from a distribution of filtering parameters of the first filtering processing and the second filtering processing; and

a separation module, coupled to the third filtering module, for determining whether each pixel within the input image is a text pixel or a figure pixel according to at least the set of the second reference values and the predetermined threshold.

12. The image processing apparatus of claim 11, wherein the third filtering module is a Gaussian filter.

13. The image processing apparatus of claim 10, wherein the set of first reference values are determined from a difference between a first luminance value of each pixel in the first image processing result and a second luminance value of a corresponding pixel located at an identical position in the second image processing result.

14. The image processing apparatus of claim 10, wherein the second filtering module is an averaging filter.

15. The image processing apparatus of claim 10, wherein the distribution of filtering parameters of the first filtering processing forms a matrix, the matrix comprises a plurality of entries, a center entry of the matrix has a filtering parameter maximum value, edge entries and internal entries of the matrix are different in sign, and each entry in a direction from the center entry to each edge entry has a filtering parameter whose magnitude increases with a decreasing distance between the entry and the center entry.

16. The image processing apparatus of claim 10, further comprising:

an outputting module, coupled to the input image and the determining module, for processing each pixel within the input image to output a text data or a figure data corresponding to the pixel according to whether the pixel is a text pixel or a figure pixel.

17. The image processing apparatus of claim 16, wherein the text data is generated from the input image via a text filtering processing.

18. The image processing apparatus of claim 16, wherein the figure data comprises a luminance data and a chroma data, the luminance data is generated according to the second image processing result, and the chroma data is generated from the input image via a figure filtering processing.