Image processing method for deriving text characteristic image from input image and related apparatus

The image processing method of claim 1, further comprising:

• performing a chroma detection upon the input image to derive a second text characteristic image, wherein the chroma detection comprises:
• for each pixel within the text characteristic image:
• categorizing the pixel as a text characteristic pixel if the chrominance of the pixel is within a text chrominance range;
• and
• outputting all text characteristic pixels to generate the second text characteristic image;
• and
• deriving a third text characteristic image according to the first text characteristic image and the second text characteristic image.

The image processing method of claim 1, wherein the first edge detecting process comprises:

• for each pixel within the input image:
• categorizing the pixel as a high-luminance pixel if a luminance of the pixel is higher than the first upper threshold;
• and
• categorizing the pixel as a low-luminance pixel if the luminance of the pixel is lower than the first lower threshold;
• performing a dilation process upon each high-luminance pixel and each low-luminance pixel within the input image, comprising:
• categorizing all non-high-luminance pixels distant from the high-luminance pixel by a specific range as high-luminance pixels;
• and
• categorizing all non-low-luminance pixels distant from the low-luminance pixel by a specific range as low-luminance pixels;
• and
• for all high-luminance pixels and low-luminance pixel within the input image after the dilation process, deriving the first edge image according to each pixel that is categorized as a high-luminance pixel and a low-luminance pixel simultaneously in space.

The image processing method of claim 1, wherein the second edge detecting process comprises:

• for each pixel within the input image:
• categorizing the pixel as a high-luminance pixel if a luminance of the pixel is higher than a second upper threshold;
• and
• categorizing the pixel as a low-luminance pixel if the luminance of the pixel is lower than a second lower threshold;
• performing a dilation process upon each high-luminance pixel and each low-luminance pixel within the input image, comprising:
• categorizing all non-high-luminance pixels distant from the high-luminance pixel by a specific range as high-luminance pixels;
• and
• categorizing all non-low-luminance pixels distant from the low-luminance pixel by a specific range as low-luminance pixels;
• and
• for all high-luminance pixels and low-luminance pixel within the input image after the dilation process, deriving the second edge image according to each pixel that is categorized as a high-luminance pixel and a low-luminance pixel simultaneously in space.

An apparatus for deriving text characteristic images from an input image, comprising:

• a plurality of edge detection modules, for performing a plurality of edge detecting processes upon the input image to generate a plurality of edge images, respectively, wherein the edge detection modules comprise:
• a first edge detection module, for performing a first edge detecting process upon the input image to derive a first edge image of the edge images according to a first upper threshold and a first lower threshold, wherein the first upper threshold is larger than the first lower threshold;
• and
• a second edge detection module, for performing a second edge detecting process upon the input image to derive a second edge image of the edge images according to a second upper threshold and a second lower threshold, wherein the second upper threshold is larger than the second lower threshold, the second upper threshold is smaller than the first upper threshold and the second lower threshold is smaller than the first lower threshold;
• and
• a synthesizing module, coupled to the edge detection modules, for deriving a first text characteristic image according to the edge images.