Character splitting method for image and character recognition
A text recognition and character technology, applied in the field of image recognition, can solve the problems that the quality of segmentation affects the text recognition effect, and it is difficult to segment the effect, and achieves the effect of good segmentation effect, high accuracy, and increased accuracy.
Pending Publication Date: 2017-05-31
成都数联铭品科技有限公司
View PDF10 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, when the text in the image is glued together and the image contains Chinese characters with a left-right structure, it is difficult to achieve a good segmentation effect with a simple projection method; it is for this reason that segmentation has always been a difficulty in OCR recognition , the quality of segmentation will directly affect the text recognition effect
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0073] As shown in Figure 3, when recognizing the text in the image, after the image text is binarized, the text line in the image is segmented through row projection, and the column projection is performed on each line of text image to find out The initial segmentation point is to initially segment the text image according to the initial segmentation to form sub-images, and mark out numbers, letters and punctuation sub-images in the segmented sub-images.
[0074] On this basis, the text character sub-pictures other than numbers, letters and punctuation are judged and processed, (the sub-pictures after the segmentation may segment the characters that are glued together (the characters after the glue segmentation are such as Figure 4 Shown)), the judgment process is as follows: Does the unmarked sub-picture width in the sequence satisfy L≤1.2h? Segment sub-pictures that do not meet the above conditions: use the following formula to judge the segmentation point:
[0075] f(x)...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to the field of image recognition processing and in particular relates to a character splitting method for image and character recognition. The splitting quality of a split sub-picture is judged layer by layer by utilizing a corresponding rule condition; the split sub-picture is subjected to corresponding processing and the splitting quality of the split sub-picture is guaranteed through a layer-by-layer screening and processing manner; furthermore, conditions are prepared for a final recognition rate. Compared with a traditional splitting method, the method provided by the invention introduces a corrected value on the basis of an amplitude value; a distance between a splitting position and a character edge is used as a considering factor for determining a splitting point, so that the accuracy is higher; when a special structure character is met, a plurality of relatively small values appear; or when an extreme point is met, an optimized splitting point can be rapidly found through the formula, the splitting accuracy is increased and the splitting efficiency is improved; the splitting effect on conglutination characters is better.
Description
technical field [0001] The invention relates to the field of image recognition, in particular to a character segmentation method for image text recognition. Background technique [0002] With the development of society and the advancement of science and technology, the amount of knowledge created by humans is increasing exponentially. Before the emergence of electronic books, most of the knowledge was passed down in the form of books. China has produced a large number of excellent Books, these books have been damaged to varying degrees in the long river of history, so it is imminent to digitally store these books; Due to the large number of books and the fact that the early printed books did not have the author's electronic manuscripts, it is necessary to digitize paper books. [0003] Optical character recognition software is a powerful tool for converting paper books to electronic documents. It mainly uses a large number of character samples to generate corresponding mode...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/34G06K9/00
CPCG06V30/40G06V10/267G06V30/10
Inventor 景亮刘世林唐涔轩康青杨
Owner 成都数联铭品科技有限公司