With the development of computer technology, digital image processing, pattern recognition and machine vision have become an important research field. Text classification is a process of extracting text based on content analysis. In this paper, RGB is used as the feature vector for character segmentation, and the string is converted into simple Chinese characters (i.e. binary). SVM is used to establish the vector relationship matrix between characters to obtain the corresponding pixel value of each word, and then combined with the threshold comparison function to generate a single word set, so as to realize the recognition of attribute parameters such as the Chinese and English abstract representing human information and background in the image, so as to meet the requirements of semantic connection between different classified texts. The test results show that the recognition accuracy of the intelligent machine learning automatic character recognition system based on text classification technology is more than 90%, and it can accurately recognize characters.

Jiwei Zhang. Automatic Text Recognition Based on Intelligent Machine Learning Technology. Machine Learning Theory and Practice (2022), Vol. 3, Issue 3: 18-26. https://doi.org/10.38007/ML.2022.030303.

[1] Jihed Elouni, Hamdi Ellouzi, Hela Ltifi, Mounir Ben Ayed:Intelligent health monitoring system modeling based on machine learning and agent technology. Multiagent Grid Syst. 16(2): 207-226 (2020). https://doi.org/10.3233/MGS-200329

[2] Salvador Lima-López, Eulàlia Farré-Maduell, Antonio Miranda-Escalada, Vicent Brivá-Iglesias, Martin Krallinger:NLP applied to occupational health: MEDDOPROF shared task at IberLEF 2021 on automatic recognition, classification and normalization of professions and occupations from medical texts. Proces. del Leng. Natural 67: 243-256 (2021).

[3] Asghar Ali Chandio, Md. Asikuzzaman, Mark R. Pickering, Mehjabeen Leghari:Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network. IEEE Access 10: 10062-10078 (2022). https://doi.org/10.1109/ACCESS.2022.3144844

[4] Sangwon Hwang, Jisun Lee, Seungwoo Kang:Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality. IEEE Access 10: 98769-98782 (2022). https://doi.org/10.1109/ACCESS.2022.3205344

[5] Prabu Selvam, Joseph Abraham Sundar Koilraj, Carlos Andrés Tavera Romero, Meshal Alharbi, Abolfazl Mehbodniya, Julian L. Webber, Sudhakar Sengan:A Transformer-Based Framework for Scene Text Recognition. IEEE Access 10: 100895-100910 (2022). https://doi.org/10.1109/ACCESS.2022.3207469

[6] Neeraj Gupta, Anand Singh Jalal:Traditional to transfer learning progression on scene text detection and recognition: a survey. Artif. Intell. Rev. 55(4): 3457-3502 (2022). https://doi.org/10.1007/s10462-021-10091-3

[7] Wondimu Dikubab, Dingkang Liang, Minghui Liao, Xiang Bai:Comprehensive benchmark datasets for Amharic scene text detection and recognition. Sci. China Inf. Sci. 65(6): 1-2 (2022). https://doi.org/10.1007/s11432-021-3447-9

[8] T. Mithila, R. Arunprakash, A. Ramachandran:CNN and Fuzzy Rules Based Text Detection and Recognition from Natural Scenes. Comput. Syst. Sci. Eng. 42(3): 1165-1179 (2022). https://doi.org/10.32604/csse.2022.023308

[9] Chebah Ouafa, Laskri Mohamed Tayeb:Facial Expression Recognition Using Convolution Neural Network Fusion and Texture Descriptors Representation. Int. J. Comput. Intell. Appl. 21(1): 2250002:1-2250002:29 (2022). https://doi.org/10.1142/S146902682250002X

[10] Mohanad Abukmeil, Gian Luca Marcialis:Experimental results on palmvein-based personal recognition by multi-snapshot fusion of textural features. Int. J. Biom. 14(1): 20-45 (2022). https://doi.org/10.1504/IJBM.2022.119547

[11] Silvia Cascianelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara:Boosting modern and historical handwritten text recognition with deformable convolutions. Int. J. Document Anal. Recognit. 25(3): 207-217 (2022). https://doi.org/10.1007/s10032-022-00401-y

[12] Germán Lescano, Rosanna Costaguta, Analía Amandi:Emotions recognition in synchronic textual CSCL situations. Int. J. Data Min. Model. Manag. 14(2): 183-202 (2022). https://doi.org/10.1504/IJDMMM.2022.123359

[13] Veronica Naosekpam, Nilkanta Sahu:Text detection, recognition, and script identification in natural scene images: a Review. Int. J. Multim. Inf. Retr. 11(3): 291-314 (2022). https://doi.org/10.1007/s13735-022-00243-8

[14] Samia Abd El-Moneim, Eman Abd El-Mordy, Mohamed Abd-Elsalam Nassar, Moawad I. Dessouky, Nabil A. Ismail, Adel S. El-Fishawy, Sami Abdelmeneem Eldolil, Ibrahim M. El-Dokany, Fathi E. Abd El-Samie:Performance enhancement of text-independent speaker recognition in noisy and reverberation conditions using Radon transform with deep learning. Int. J. Speech Technol. 25(3): 679-687 (2022). https://doi.org/10.1007/s10772-021-09880-6

[15] Leena Mary Francis, N. Sreenath:Robust scene text recognition: Using manifold regularized Twin-Support Vector Machine. J. King Saud Univ. Comput. Inf. Sci. 34(3): 589-604 (2022). https://doi.org/10.1016/j.jksuci.2019.01.013

[16] Nadeesha Perera, Thi Thuy Linh Nguyen, Matthias Dehmer, Frank Emmert-Streib:Comparison of Text Mining Models for Food and Dietary Constituent Named-Entity Recognition. Mach. Learn. Knowl. Extr. 4(1): 254-275 (2022). https://doi.org/10.3390/make4010012

[17] Pawan Dubey, Tirupathiraju Kanumuri, Ritesh Vyas:Optimal directional texture codes using multiscale bit crossover count planes for palmprint recognition. Multim. Tools Appl. 81(14): 20291-20310 (2022). https://doi.org/10.1007/s11042-022-12580-1

[18] Husam Ahmed Al Hamad, Laith Abualigah, Mohammad Shehab, Khalil H. A. Al-Shqeerat, Mohammed Otair:Improved linear density technique for segmentation in Arabic handwritten text recognition. Multim. Tools Appl. 81(20): 28531-28558 (2022). https://doi.org/10.1007/s11042-022-12717-2