Picture labeling method based on Chinese herbal medicine image-text modal data

Abstract

The invention discloses a picture labeling method based on Chinese herbal medicine image-text modal data. The method comprises the following steps: S1, extracting image-text labeling pairs from Chinese herbal medicine image-text image data; s2, independently extracting the category labels and the images to make a Chinese herbal medicine image-text annotation data set; and S3, building a Chinese herbal medicine association labeling algorithm model with semantic consistency constraint, and performing training. The method comprises the following steps: extracting pictures and label pairs from image-text modal data, extracting edge binary images of the pictures by using a Sobel operator, extracting foreground and background thresholds of the pictures by using an OTSU algorithm and the like to obtain two groups of data sets of original forms and medicinal forms of the Chinese herbal medicines; the functions of processing, processing, displaying, collecting and the like of the Chinese herbal medicine image-text data are provided and realized by matching with a built single-form algorithm and double-layer algorithm model system and utilizing the system, and the accuracy of the algorithm is continuously optimized by utilizing the collected data, so that the recognition effect is greatly improved.

Description

technical field [0001] The invention relates to the technical field of image labeling, in particular to a picture labeling method based on Chinese herbal medicine graphic and text modal data. Background technique [0002] As an important part of traditional Chinese culture, Chinese herbal medicine contains rich cultural symbols and cultural connotations. With the advent of the era of cultural big data, Chinese herbal medicine data also has rich digital resources, integrating technology and culture to explore the culture contained in Chinese herbal medicine. The content is a topic that has been widely mentioned. Using the method of labeling to analyze the categories and functions of Chinese herbal medicine is a scientific and technological method that can realize cultural identification, cultural interpretation, and cultural inheritance. [0003] Traditional Chinese medicine is mainly composed of plant medicine, animal medicine and mineral medicine. Because botanicals accoun...

AI Technical Summary

Problems solved by technology

In the general labeling algorithm, due to the large difference between the two modalities and the weak correlation, they should be treated as different classification labeling tasks, but in this way, both modalities have the same label attribute (semantic consistency). ) and have a certain connection in some special categories (for example, the similarity between the two forms of honeycomb or tortoise shell data is high), in this case, if we use the two forms of image data separately, it will lead to the algorithm model The problem of information loss in the system will lead to problems such as decreased accuracy rate and inaccurate object recognition; at the same time, if we confuse the two modalities for recognition, there will be more serious recognition accuracy problems. It can be seen that both methods are feasible to a certain extent. , but there are also some problems in certain situations

Images