Artificial intelligence-based paintbook automatic classification system and method
Through an automated comic strip classification system based on artificial intelligence, using deep learning and natural language processing technology to automatically extract and blend the image and text features of comic strips, the problem of difficult to efficiently classify comic strips in the existing technology is solved, and more efficient and accurate classification management is achieved.
Patent Information
- Application Number
- CN202510168675.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-17
- Publication Date
- 2025-06-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
It is difficult for the existing technology to efficiently and accurately classify and manage massive comic strip data. Traditional manual classification is time-consuming and labor-intensive and the results are inconsistent. It is difficult for existing image recognition and text processing technologies to effectively extract the key features and information of comic strips.
Using an automated comic strip classification system based on artificial intelligence, including image acquisition, preprocessing, feature extraction, text extraction and feature fusion modules, we automatically extract and fuse images and text features through deep learning algorithms (such as convolutional neural networks) and natural language processing technologies (such as word vector models and text convolutional neural networks), we automatically extract and fuse images and text features to make classification decisions.
It greatly improves the efficiency and accuracy of comic strip classification, reduces manual intervention, can understand the content and theme of comic strips more accurately, achieve more reasonable classification, and has good expansion and adaptability.
Smart Images
Figure CN120220159A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a comic automatic classification system and method based on artificial intelligence. Background Art
[0002] With the continuous development of digital technology, a large number of comic resources have been digitally preserved. However, in the face of a vast amount of comic data, how to classify and manage it efficiently and accurately has become an urgent problem to be solved. The traditional manual classification method not only consumes a large amount of manpower and time, but also the classification criteria may vary from person to person, making it difficult to ensure the consistency and accuracy of the classification results.
[0003] Currently, although there are already some classification technologies based on image recognition and text processing, for the image data of comics with unique artistic styles and rich content, the existing classification methods have many deficiencies. For example, the images in comics often contain complex scenes, characters, and plots, and it is difficult for existing image recognition algorithms to accurately extract their key features; at the same time, the text descriptions in comics also have strong storytelling and literary qualities, and ordinary text classification methods are difficult to fully understand and utilize this information.
[0004] Therefore, we propose a comic automatic classification system and method based on artificial intelligence. Summary of the Invention
[0005] The present invention mainly solves the technical problems existing in the above-mentioned prior art, and provides a comic automatic classification system and method based on artificial intelligence.
[0006] To achieve the above object, the present invention adopts the following technical solutions. The comic automatic classification system based on artificial intelligence includes an image acquisition module, an image preprocessing module, an image feature extraction module, a text extraction module, a text feature extraction module, a classification decision module, a database module, and a user interaction module. The image acquisition module is used to obtain the image data of comics, and can convert paper comics into digital images through a scanning device, or directly read the image data from an existing digital comic resource library.
[0007] Preferably, the image preprocessing module preprocesses the acquired images, including operations such as image denoising, grayscale conversion, binarization, and image enhancement, to improve the quality of the images and facilitate subsequent feature extraction and analysis.
[0008] Preferably, the image feature extraction module uses the deep learning algorithm convolutional neural network (CNN) to extract features from the preprocessed images, and automatically learns the key features in the images, such as character images, scene layouts, and line styles, by constructing multiple convolutional layers and pooling layers.
[0009] Preferably, the text extraction module uses optical character recognition (OCR) technology to extract text information from the comic strip images, and performs preprocessing such as correction, word segmentation, and part-of-speech tagging on the extracted text for subsequent text analysis.
[0010] Preferably, the text feature extraction module uses natural language processing technology to extract features from the preprocessed text, maps each word in the text to a low-dimensional vector, and then extracts the semantic features of the text through convolution operations.
[0011] Preferably, the natural language processing technology is specifically a word vector model (Word2Vec) or a text convolutional neural network (TextCNN).
[0012] Preferably, the classification decision module fuses the image features and text features, and uses a classification algorithm such as a support vector machine (SVM) or a random forest (RF) to make a classification decision on the comic strip. According to the pre-set classification criteria, the comic strip is divided into different categories, such as historical story categories, mythological legend categories, science fiction categories, and children's education categories.
[0013] Preferably, the database module is used to store the original image data of the comic strip, the preprocessed image data, the extracted image features and text features, and the information of the classification results.
[0014] Preferably, the database module uses a relational database or a non-relational database.
[0015] Preferably, the relational database is specifically MySQL, and the non-relational database is specifically MongoDB.
[0016] Preferably, the user interaction module provides an interaction interface between the user and the system. The user can input relevant parameters of the comic strip classification task, such as classification criteria and data sources, through this interface. The system displays the classification results to the user and provides relevant query and management functions.
[0017] The method for automatic classification of comic strips based on artificial intelligence, including the above-mentioned automatic classification system for comic strips based on artificial intelligence, specifically includes the following steps:
[0018] The first step: Image acquisition and preprocessing: Obtain the image data of the comic strip through the image acquisition module, and use the image preprocessing module to perform operations such as denoising, grayscale conversion, binarization, and image enhancement on the image;
[0019] The second step: Image feature extraction: Input the preprocessed image into the image feature extraction module, and use a convolutional neural network to extract features to obtain the feature vector of the image;
[0020] Step 3: Text Extraction and Preprocessing: Use optical character recognition technology to extract text information from comic images, and perform preprocessing on the extracted text, including correction, word segmentation, and part-of-speech tagging.
[0021] Step 4: Text Feature Extraction: Input the preprocessed text into the text feature extraction module, and use the word vector model and text convolutional neural network to extract features, obtaining the feature vectors of the text.
[0022] Step 5: Feature Fusion and Classification Decision: Fusion the image feature vectors and text feature vectors, and use the classification algorithms of support vector machines and random forests for classification decision. According to the pre-set classification criteria, classify the comic books into different categories.
[0023] Step 6: Result Storage and Display: Store the classification results in the database module, and display the classification results to the user through the user interaction module, while providing relevant query and management functions.
[0024] The present invention provides an automated comic book classification system and method based on artificial intelligence, having the following
[0025] Beneficial effects:
[0026] 1. The automated comic book classification system and method based on artificial intelligence can automatically extract the image features and text features of comic books, perform fusion classification, greatly improve the classification efficiency and accuracy, and reduce manual intervention by adopting artificial intelligence technology.
[0027] 2. The automated comic book classification system and method based on artificial intelligence can make full use of various information in comic books through comprehensive analysis of images and texts, can more accurately understand the content and theme of comic books, and thus achieve more reasonable classification.
[0028] 3. The automated comic book classification system and method based on artificial intelligence. The system and method of the present invention have good scalability and adaptability, and can continuously update and optimize the classification criteria and algorithm models according to actual needs to adapt to different types and scales of comic book data classification tasks. Brief Description of the Drawings
[0029] Figure 1 is the system architecture diagram of the present invention;
[0030] Figure 2 is the method flow diagram of the present invention. Detailed Embodiments
[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, without creative efforts, other implementation drawings can also be obtained based on the provided drawings.
[0032] The structures, proportions, sizes, etc. illustrated in this specification are only used to cooperate with the content disclosed in the specification for those who are familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.
[0033] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.
[0034] In the description of the embodiments of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "inner", "outer", "side", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invention product is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation to the present invention. In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.
[0035] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, the terms "set", "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific situations.
[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.
[0037] Embodiment 1: An automated classification system for comic books based on artificial intelligence, as Figure 1 shown, includes an image acquisition module, an image preprocessing module, an image feature extraction module, a text extraction module, a text feature extraction module, a classification decision module, a database module, and a user interaction module. The image acquisition module is used to obtain the image data of comic books, and can convert paper comic books into digital images through a scanning device, or directly read the image data from an existing digital comic book resource library. The image preprocessing module preprocesses the acquired images, including operations such as image denoising, grayscale conversion, binarization, and image enhancement, to improve the quality of the images and facilitate subsequent feature extraction and analysis. The image feature extraction module uses the deep learning algorithm convolutional neural network (CNN) to extract features from the preprocessed images. By constructing multiple convolutional layers and pooling layers, it automatically learns the key features in the images, such as character images, scene layouts, and line styles. The text extraction module uses optical character recognition (OCR) technology to extract text information from comic book images, and preprocesses the extracted text, including correction, word segmentation, and part-of-speech tagging, for subsequent text analysis. The text feature extraction module uses natural language processing technology to extract features from the preprocessed text, maps each word in the text to a low-dimensional vector, and then extracts the semantic features of the text through convolutional operations. The natural language processing technology is specifically a word vector model (Word2Vec) or a text convolutional neural network (TextCNN). The classification decision module fuses the image features and text features, and uses a classification algorithm such as support vector machine (SVM) or random forest (RF) to make classification decisions on comic books. According to the pre-set classification criteria, comic books are divided into different categories, such as historical story categories, mythological legend categories, science fiction categories, and children's education categories. The database module is used to store the original image data of comic books, the preprocessed image data, the extracted image features and text features, and the information of classification results. The database module uses a relational database or a non-relational database. The relational database is specifically MySQL, and the non-relational database is specifically MongoDB. The user interaction module provides an interaction interface between the user and the system. The user can input relevant parameters of the comic book classification task, such as classification criteria and data sources, through this interface. The system displays the classification results to the user and provides relevant query and management functions. By adopting artificial intelligence technology, it can automatically extract the image features and text features of comic books, and perform fusion classification, greatly improving the efficiency and accuracy of classification and reducing manual intervention. Through the comprehensive analysis of images and texts, various information in comic books is fully utilized, and the content and theme of comic books can be understood more accurately, thus achieving more reasonable classification.
[0038] Embodiment 2: On the basis of Embodiment 1, as Figure 2As shown in the figure, the method for automatic classification of comic strips based on artificial intelligence includes the above-mentioned automatic classification system for comic strips based on artificial intelligence, and specifically includes the following steps: The first step: Image acquisition and preprocessing: Obtain the image data of the comic strip through the image acquisition module, and use the image preprocessing module to perform operations such as denoising, grayscale conversion, binarization, and image enhancement on the image; The second step: Image feature extraction: Input the preprocessed image into the image feature extraction module, and use a convolutional neural network for feature extraction to obtain the feature vector of the image; The third step: Text extraction and preprocessing: Use optical character recognition technology to extract text information from the comic strip image, and perform preprocessing such as correction, word segmentation, and part-of-speech tagging on the extracted text; The fourth step: Text feature extraction: Input the preprocessed text into the text feature extraction module, and use a word vector model and a text convolutional neural network for feature extraction to obtain the feature vector of the text; The fifth step: Feature fusion and classification decision: Fusion the image feature vector and the text feature vector, and use classification algorithms such as support vector machines and random forests for classification decision. According to the pre-set classification criteria, classify the comic strips into different categories; The sixth step: Result storage and display: Store the classification results in the database module, and display the classification results to the user through the user interaction module, and at the same time provide relevant query and management functions. The system and method of the present invention have good scalability and adaptability, and can continuously update and optimize the classification criteria and algorithm models according to actual needs to adapt to different types and scales of comic strip data classification tasks.
[0039] The working principle of the present invention:
[0040] One: System construction:
[0041] The first step: Hardware environment: Select a server with a relatively high configuration, equipped with high-performance CPU, GPU, memory, and storage devices to meet the computing resource requirements of deep learning algorithms;
[0042] The second step: Software environment: Install an operating system (such as Ubuntu), a deep learning framework (such as TensorFlow or PyTorch), an optical character recognition engine (such as Tesseract), and a database management system (such as MySQL or MongoDB);
[0043] The third step: Data preparation: Collect a large number of comic strip sample data, including comic strips of different types and different eras, label these data, and divide them into different categories according to the pre-set classification criteria as training data.
[0044] Two: Model training:
[0045] Step 1: Training of the image feature extraction model: Using the collected comic image data, a convolutional neural network model is constructed. Through multiple iterations of training, the parameters of the model are adjusted so that the model can accurately extract the key features in the image. During the training process, data augmentation techniques such as rotation, flipping, and scaling can be adopted to increase the diversity of the training data and improve the generalization ability of the model;
[0046] Step 2: Training of the text feature extraction model: After preprocessing the text data extracted from the comic images, a word vector model and a text convolutional neural network are used for training. By continuously adjusting the parameters of the model, the model can accurately extract the semantic features of the text;
[0047] Step 3: Training of the classification model: The image feature vector and the text feature vector are fused, and a classification algorithm such as a support vector machine or a random forest is used for training. Based on the labeled training data, the parameters of the classification model are adjusted so that it can accurately classify the comics.
[0048] III. System operation:
[0049] Step 1: Image acquisition and preprocessing: The user scans the paper comic into a digital image through the image acquisition module or imports the image data from an existing digital resource library. The image preprocessing module performs operations such as denoising, grayscale conversion, binarization, and image enhancement on the acquired image to improve the image quality;
[0050] Step 2: Image feature extraction: The preprocessed image is input into the image feature extraction module, and the convolutional neural network model automatically extracts the feature vector of the image;
[0051] Step 3: Text extraction and preprocessing: Optical character recognition technology is used to extract the text information from the image, and the extracted text is preprocessed such as correction, word segmentation, and part-of-speech tagging;
[0052] Step 4: Text feature extraction: The preprocessed text data is input into the text feature extraction module, and the word vector model and the text convolutional neural network extract the feature vector of the text;
[0053] Step 5: Feature fusion and classification decision: After the image feature vector and the text feature vector are fused, they are input into the classification decision module. The classification algorithm makes a classification decision on the comic according to the pre-trained model to determine its category;
[0054] Step 6: Result storage and display: The classification result is stored in the database module, and the user can query and manage the classification result through the user interaction module. The system displays the classification result to the user in an intuitive way.
[0055] IV. System optimization:
[0056] Step 1: Regularly update the training data by adding new comic samples so that the model can adapt to the changing comic content and styles.
[0057] Step 2: Optimize the model, such as adjusting the structure and parameters of the neural network, and adopting more advanced algorithms to improve the performance and accuracy of the model.
[0058] Step 3: Reasonably configure and optimize the hardware resources of the system to improve the operating efficiency of the system.
[0059] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.
Claims
1. An automatic comic book classification system based on artificial intelligence, characterized in that: It includes an image acquisition module, an image preprocessing module, an image feature extraction module, a text extraction module, a text feature extraction module, a classification decision module, a database module and a user interaction module. The image acquisition module converts paper comic books into digital images through a scanning device, or directly reads image data from an existing digital comic book resource library.
2. The artificial intelligence-based comic strip automatic classification system according to claim 1, characterized in that: The image preprocessing module preprocesses the collected image, including operations of image denoising, grayscale conversion, binarization and image enhancement.
3. The comic strip automatic classification system based on artificial intelligence according to claim 1 is characterized in that: The image feature extraction module uses a deep learning algorithm, a convolutional neural network (CNN), to extract features from the preprocessed image, and automatically learns key features in the image, such as character image, scene layout, and line style, by constructing multiple layers of convolutional layers and pooling layers.
4. The comic strip automatic classification system based on artificial intelligence according to claim 1 is characterized in that: The text extraction module uses optical character recognition (OCR) technology to extract text information from the comic strip image, and performs pre-processing of correction, word segmentation and part-of-speech tagging on the extracted text.
5. The artificial intelligence-based comic strip automatic classification system according to claim 1, characterized in that: The text feature extraction module adopts natural language processing technology, and the natural language processing technology is specifically a word vector model (Word2Vec) or a text convolutional neural network (TextCNN).
6. The artificial intelligence-based comic strip automatic classification system according to claim 1 is characterized by: The classification decision module uses a support vector machine (SVM) or random forest (RF) classification algorithm to make classification decisions on the comic strips.
7. The comic strip automatic classification system based on artificial intelligence according to claim 1 is characterized in that: The database module adopts a relational database or a non-relational database, the relational database is specifically MySQL, and the non-relational database is specifically MongoDB.
8. The comic strip automatic classification system based on artificial intelligence according to claim 1 is characterized by: The user interaction module provides an interactive interface between the user and the system, through which the user can input relevant parameters of the comic book classification task, such as classification standards and data sources. The system will display the classification results to the user and provide relevant query and management functions.
9. A method for automatic classification of comic strips based on artificial intelligence, characterized in that: The artificial intelligence-based comic strip automatic classification system according to any one of claims 1 to 8 specifically comprises the following steps: Step 1: Image acquisition and preprocessing: The image data of the comic strip is obtained through the image acquisition module, and the image preprocessing module is used to perform denoising, grayscale, binarization and image enhancement operations on the image; Step 2: Image feature extraction: The preprocessed image is input into the image feature extraction module, and a convolutional neural network is used to extract features to obtain the feature vector of the image; Step 3: Text extraction and preprocessing: Use optical character recognition technology to extract text information from comic strip images, and perform preprocessing of correction, word segmentation and part-of-speech tagging on the extracted text; Step 4: Text feature extraction: Input the preprocessed text into the text feature extraction module, use the word vector model and text convolutional neural network to extract features, and obtain the feature vector of the text; Step 5: Feature fusion and classification decision: The image feature vector and the text feature vector are fused, and the support vector machine and random forest classification algorithms are used to make classification decisions. The comic strips are divided into different categories according to the pre-set classification criteria. Step 6: Result storage and display: The classification results are stored in the database module, and the classification results are displayed to the user through the user interaction module, while providing related query and management functions.