Search - background text extraction

Search - background text extraction - List

[matlab] Connected-Component-based-text-region-extraction. DL : 0: The basic steps of the connected-component text extraction algorithm are given below, and diagrammed in Figure 10. The details are discussed in the following sections. 1. Convert the input image to YUV color space. The luminance(Y) value is used for further processing. The output is a gray image. 2. Convert the gray image to an edge image. 3. Compute the horizontal and vertical projection profiles of candidate text regions using a histogram with an appropriate threshold value. 4. Use geometric properties of text such as width to height ratio of characters to eliminate possible non-text regions. 5. Binarize the edge image enhancing only the text regions against a plain black background. 6. Create the Gap Image (as explained in the next section) using the gap-filling process and use this as a reference to further eliminate non-text regions the output. -The basic steps of the connected-component text extraction algorithm are given below, and diagrammed in Figure 10. The details are discussed in the following sections. 1. Convert the input image to YUV color space. The luminance(Y) value is used for further processing. The output is a gray image. 2. Convert the gray image to an edge image. 3. Compute the horizontal and vertical projection profiles of candidate text regions using a histogram with an appropriate threshold value. 4. Use geometric properties of text such as width to height ratio of characters to eliminate possible non-text regions. 5. Binarize the edge image enhancing only the text regions against a plain black background. 6. Create the Gap Image (as explained in the next section) using the gap-filling process and use this as a reference to further eliminate non-text regions the output.
Date : 2026-01-12 Size : 41kb User : Lee Kurian
[matlab] Edge-based-text-region-extraction-from-natural-im DL : 0: The basic steps of the edge-based text extraction algorithm are given below 1. Create a Gaussian pyramid by convolving the input image with a Gaussian kernel and successively down-sample each direction by half. (Levels: 4) 2. Create directional kernels to detect edges at 0, 45, 90 and 135 orientations. 3. Convolve each image in the Gaussian pyramid with each orientation filter. 4. Combine the results of step 3 to create the Feature Map. 5. Dilate the resultant image using a sufficiently large structuring element (7x7 [1]) to cluster candidate text regions together. 6. Create final output image with text in white pixels against a plain black background.
Date : 2026-01-12 Size : 2kb User : Lee Kurian