Automatic extraction and intelligent scoring system for handwritten Chinese characters or components and strokes

Abstract

The invention discloses an automatic extraction and intelligent scoring system for handwritten Chinese characters or components and strokes. The automatic extraction and intelligent scoring system comprises an automatic extraction module for calligraphy practicing book images, an automatic extraction module for single Chinese characters, a Chinese character recognition module and a Chinese character scoring module. The automatic extraction module for calligraphy practicing books carries out preprocessing, image capture, correction, error reporting and format judgment on uploaded handwritten Chinese character photos, and the accuracy and the automation effect of image extraction are improved through the complete process. The automatic extraction module for single Chinese characters comprises a special processing method for pencil character extraction, so that a pencil character image can be effectively extracted; the established deep learning recognition model can quickly recognize handwritten Chinese characters, including space recognition; and Chinese character scoring adopts a structure+content comprehensive scoring method, the structure is the length and width values of Chinesecharacters, and the content is determined through cosine similarity. According to the method, the handwritten character pictures which are randomly uploaded can be automatically extracted and scored,and the method is suitable for low-age students who begin to learn Chinese characters and is greatly helpful for daily calligraphy practicing of calligraphy enthusiasts.

Description

technical field [0001] The invention relates to an automatic extraction and intelligent scoring system of handwritten Chinese characters or radicals and strokes, in particular to an automatic extraction and intelligent scoring system for handwritten Chinese characters or radicals and strokes based on an ordinary calligraphy practice book, and belongs to the technical field of artificial intelligence text image processing. Background technique [0002] Chinese character writing is a tradition of Chinese culture with a long history. In the fields of Chinese character application proficiency testing and Chinese character application teaching, how to effectively judge the standardization of written Chinese characters is a relatively complicated subject. On the one hand, the education department, teachers and parents are paying more and more attention to calligraphy education. "Writing Chinese characters well" is the basic quality of every Chinese, and it is also the inheritance o...

AI Technical Summary

Problems solved by technology

At the same time, when students practice calligraphy, they often use copybooks to imitate and gradually improve their writing level. This is a conventional method, and it has also achieved a relatively ideal effect to a certain extent, but there are still some problems with this method: 1. The writing effect All are evaluated by the teacher, and different teachers may have different standards. Even the same teacher may give different evaluations at different times, which is highly subjective; 2. Lack of quantitative and visual evaluation methods. The content of the content is only sensory knowledge, but there is no quantitative and visual judgment. If things go on like this, it is difficult for them to evaluate their writing level, and they tend to lack motivation to practice calligraphy, and gradually lose interest in calligraphy practice

"A Method for Intelligent Evaluation of Chinese Character Writing Quality" (202010433699.6), "Digital Writing Practice Method and System" (201710762777.5), "A Smart Writing Scoring System and Method" (201710032399.5), "A Writing Practice System and Method" ( 201710404401.7), "A Writing Practice Scoring Method and Writing Practice Device" (201610957317.3), etc., for users, it not only increases the cost of equipment purchase, but also greatly reduces the experience

Third, due to the single automatic image extraction method of the exercise book, there will be great limitations on the selection of paper and format of the exercise book, and users cannot obtain a better user experience

Fourth, the automatic extraction of single Chinese characters in most patents is simple, and is mainly aimed at the extraction of Chinese characters with water brushes, and rarely mentions the extraction of pencil characters

When the user uses a pencil to practice handwriting, due to the lack of a good automatic extraction unit for Chinese characters, the grid border cannot be effectively removed, resulting in poor display effect and affecting the normal progress of the subsequent process; at the same time, due to the existence of shadows, it will lead to binarization. Chinese characters become blurred, and some strokes become thinner or missing, which brings great challenges to the stability of scoring results

[0005] 2. The intelligence of Chinese character scoring in the existing patents is insufficient, and there is no Chinese character recognition module based on the popular artificial intelligence technology, that is, a high-accuracy recognition module for handwritten Chinese characters or radicals and strokes, which highlights the intelligence of existing patents status quo

There are also some patents that do not have the function of Chinese character recognition, and can only be scored for some specific calligraphy practice books, such as "An artificial intelligence scoring system and method for calligraphy practice calligraphy with copybooks" (201910427401.8). The style of the exercise book is fixed, and the first The columns are all standard characters, and the first character in each line of the exercise book is used as the standard character for comparison and scoring with the subsequent handwritten Chinese characters

[0006] 3. The existing patented Chinese character scoring module mostly uses simple coincidence to evaluate the effect of Chinese characters. This method does not verify that the evaluation results are consistent with professional calligraphy evaluation, lacks certain scientificity, and cannot reflect whether the entire font is good or bad for Chinese characters the intuitive impact of

In the published patents CN201510565555, CN201911199560, and CN201910427401, the simple area overlap degree cannot reflect the similarity between handwritten characters and standard characters as a whole

Images