Method and device for determining region structure complexity and locating text region
A technology with a complex area structure and structure, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of low accuracy of text areas and low accuracy of area structure complexity, and reduce the need for positioning as non-text areas chance, effects that increase accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] Such as Figure 5 As shown, it is a schematic diagram of a method for determining the complexity of a region structure in Embodiment 1 of the present application, and the method includes the following steps:
[0063] Step 101: Determine the connected components in the candidate region of the digital image.
[0064] Step 102: Extract the contour of the connected components, and perform polygonal approximation on the extracted contour to obtain a polygon reflecting the contour.
[0065] Preferably, polygonal approximation is performed on the contour, specifically including:
[0066] The first step is to determine the maximum width of the contour and the maximum tolerance error of the polygonal approximation corresponding to the maximum width.
[0067] The larger the maximum width of the contour, the larger the corresponding maximum tolerance error of polygonal approximation, and the smaller the maximum width, the smaller the corresponding maximum tolerance error of poly...
Embodiment 2
[0116] Based on the method for determining the complexity of the region structure in Embodiment 1 of the present application, Embodiment 2 proposes a method for locating text regions, the method comprising:
[0117] The first step is to determine the region structure complexity of the candidate region by using the method for determining region structure complexity in Step 101 to Step 103 in Embodiment 1 of the present application or the preferred method for determining region structure complexity in Embodiment 1.
[0118] The second step is to judge whether the determined regional structure complexity is greater than the set threshold, and if it is greater than the set threshold, then execute the third step; otherwise, execute the fourth step.
[0119] The set threshold can be determined according to empirical values, or can be determined according to the size of the candidate area. The larger the candidate area, the larger the set threshold; the smaller the candidate area, the...
Embodiment 3
[0125] Such as Figure 11 As shown, it is a schematic structural diagram of a device for determining the complexity of a region structure in Embodiment 3 of the present application. The device includes: a connected component determination module 11, a contour extraction module 12, a polygon approximation module 13, and a concave vertex determination module 14 and the region structure complexity determination module 15, wherein:
[0126] The connected component determination module 11 is configured to determine the connected components in the candidate regions of the digital image.
[0127] The contour extraction module 12 is configured to extract the contour of the connected components determined by the connected component determination module 11 .
[0128] The polygon approximation module 13 is configured to perform polygon approximation on the contour extracted by the contour extraction module 12 to obtain a polygon reflecting the contour.
[0129] The concave vertex deter...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More