Artificial intelligence

Abstract: The paper substantiates the need to assess the harm of food for consumers with chronic diseases or allergies, which is important to prevent possible deterioration of the disease or eliminate acute allergic reactions of the human body to harmful ingredients present in the product. It is proved that currently there is no convenient intelligent system that could recognize the composition of products on the Ukrainian market, provide product characteristics and assess the harmfulness of the product. It is proposed to use food labels and packaging as primary sources of food information that is available to the consumer. It is shown that the printed information on the packages is presented in text-graphic form. The development of a mobile system as a software solution for the detection and analysis of textual and graphical information on the composition of products based on the use of artificial intelligence methods is proposed and substantiated. The block diagram of the intelligent mobile system for detection and analysis of food composition has been developed. The MSER algorithm is used to select text regions on the input image matrix in the presented algorithmic software. The solution to the problem of character recognition was based on the use of convolutional neural network MobileNet-V2, which is currently the best option in the classification of images by mobile applications that do not have a server part, and therefore large computing resources. Alignment of text on the image was carried out using the method of finding a rectangle with the smallest area Developed algorithms for grouping words. A decision support algorithm has been proposed to assess the harmfulness of products. The developed system allows personalized selection of food for each individual user, ie, the assessment of the composition of products is calculated taking into account the state of health of use, existing threats, diseases, restrictions or allergies.

Keywords: analyzing product composition; assessment of the harmfulness of food; decision-making algorithm; intellectual system; text detection.

References:

1. A. Hybrid Approach to Detectand Localize TextsinNatural Scene Images. Yi-Feng Pan; Xinwen Hou; Cheng-Lin Liu. IEEE Transactions on Image Processing vol: 20, no: 3, pp. 800–813 March 2011. doi:10.1109/TIP.2010.2070803
2. Beyond MSER: Maximally Stable Regionsusing Tree of Shapes. Petra Bosilj, Ewa Kijak, Sébastien Lefèvre, September 2015. doi:10.5244/C.29.169. [Online] – Available: https://www.researchgate.net/publication/281565129_Beyond_MSER_Maximally_Stable_Regions_using_Tree_of_Shapes
3. Chy shkidlyva palmova oliya. Отримано з https://moz.gov.ua/article/health/chi-shkidliva-palmova-olija
4. Classification of fused face images using multilayer perceptron neural network, Debotosh Bhattacharjee, Mrinal Kanti Bhowmik, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu. Отримано з https://arxiv.org/abs/1007.0633
5. Documents kewdetection using minimum-area bo undingrect angle. Reza Safabakhsh. Shahram Khadivi. February 2000. doi:10.1109/ITCC.2000.844226. [Online] – Available: https://www.researchgate.net/publication/3848296_Document_skew_detection_using_minimum-area_bounding_rectangle
6. Food label reading: Read before youeat. Goyal R, Deshmukh N. Отримано з https://www.researchgate.net/publication/324761439_Food_label_reading_Read_before_you_eat
7. Generalized Intersectionover Union: A Metricand A Loss for Bounding Box Regression. February 2019. Hamid Rezatofighi, Nathan Tsoi, Jun Young Gwak, Amir Sadeghian. Отримано з https://www.researchgate.net/publication/331371000_Generalized_Intersection_over_Union_A_Metric_and_A_Loss_for_Bounding_Box_Regression
8. Hand written Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) Jamshed Memon, Maira Sami, and Rizwan Ahmed Khan. July 2020 IEEE Access. doi:10.1109/ACCESS.2020.3012542. [Online] – Available: https://www.researchgate.net/publication/343273822_Handwritten_Optical_Character_Recognition_OCR_A_Comprehensive_Systematic_Literature_Review_SLR
9. Identification of for k points on the skelet on sofh and written Chine secharacters. K. Liu, Y. S. Huang, and C. Y. Suen, IEEE Trans. Pattern Anal. Mach. Intell., vol. 21, no. 10, pp. 1095–1100, Oct. 1999, doi:10.1109/34.799914
10. Informacionnaya zapiska INFOSAN No. 3/2006 – Pishchevye allergii. Vsemirnaya organizaciya zdravoohraneniya. Отримано з https://www.who.int/foodsafety/fs_management/No_03_allergy_June06_ru.pdf
11. Metod identyfikaciyi harchovyh dobavok (pidsolodzhuvachiv) z metoyu vyyavlennya falsyfikaciyi produkciyi / P. G. Stolyarchuk [tain.] // Visnyk Nacz. tehn. un-tu "HPI": zb. nauk. pr. Temat. vyp.: Novi rishennya v suchasnyh tehnologiyah. – Harkiv: NTU "XPI", 2010. – # 46. – S. 3-7.
12. Mobile Net V2: Inverted Residuals and Linear Bottlenecks Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov Liang-Chieh Chen. Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. doi:10.1109/CVPR.2018.00474. Отримано з https://ieeexplore.ieee.org/document/8578572
13. Natural Scene Text Detection with Multi-channel Connected Component Segmentation. Xiaobing Wang; Yonghong Song; Yuanlin Zhang. 12th International Conference on Document Analysis and Recognition, 2013. doi:10.1109/ICDAR.2013.278
14. On the Minimum-Area Rectangular and Square Annulus Problem. Sang Won Bae. Отримано з https://arxiv.org/abs/1904.06832
15. Optimizing intersection-overunionin deep neural networks for images egmentation. Md Atiqur Rahman and Yang Wang. Отримано з http://cs.umanitoba.ca/~ywang/papers/isvc16.pdf
16. Pediatric Age Palm Oil Consumption. Lorenza Di Genova, Laura Cerquiglini, Laura Penta, Anna Biscarini, and Susanna Esposito. Отримано з https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5923693/
17. Real-Time and Accurate Drone Detection in a Video with a Static Background. Ulzhalgas Seidaliyeva, Daryn Akhmetov, Lyazzat Ilipbayeva, Eric T. Matson. doi:10.3390/s20143856. Отримано з https://www.researchgate.net/publication/342856036_Real-Time_and_Accurate_Drone_Detection_in_a_Video_with_a_Static_Background
18. Recognition of Handwritten Chinese Characters Basedon Concept Learning. Liang Xu, Yuxi Wang, Xiuxi Li, Ming Pan. July 2019. IEEE Access PP(99):1-1. doi:10.1109/ACCESS.2019.2930799
19. Region graph based text extraction from outdoor images. Hiroki Takahashi. August 2005. doi:10.1109/ICITA.2005.235 [Online] – Available: https://www.researchgate.net/publication/4162652_Region_graph_based_text_extraction_from_outdoor_images
20. Robust wide-base line stereo from maximally stable extremal regions. J. Matas, O. Chum, M. Urban, and T. Pajdla. Отримано з https://cmp.felk.cvut.cz/~matas/papers/matas-bmvc02.pdf
21. Ship Detection from Ocean SAR Image Basedon Local Contrast Variance Weighted Information Entropy. Weibo Huo, Yulin Huang, Jifang Pei, Qian Zhang, Qin Guand Jianyu Yang. Отримано з https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948720/
22. Survey on Text Detection, Segmentation and Recognition from a Natural Scene Images. Uma Karanje, Rahul Dagade. International Journal of Computer Applications 108(13):39–43.December 2014. doi:10.5120/18974-0472. [Online] – Available: https://www.researchgate.net/publication/287689667_Survey_on_Text_Detection_Segmentation_and_Recognition_from_a_Natural_Scene_Images
23. Text Detection and Recognition in Images and Videos. Datong Chen, Jean-Marc Odobez, Herve Bourlard. January 2004. Отримано з https://www.researchgate.net/publication/37433214_Text_Detection_and_Recognition_in_Images_and_Videos
24. Text detection and recognition using enhanced MSER detection and a novel OCR technique. Md. Rabiul Islam; Chayan Mondal; Md. Kawsar Azam; Abu Syed Md. Jannatul Islam. 5th International Conference on Informatics, Electronics and Vision (ICIEV), 2016. doi:10.1109/ICIEV.2016.7760054.
25. Thinning methodologies – a comprehensive survey. L. Lam, S. W. Lee, and C. Y. Suen, IEEE Trans. Pattern Anal. Mach. Intell., vol. 14, no. 9, pp. 869–885, Sep. 1992, doi:10.1109/34.161346
26. Using Adaboost to Detect and Segment Characters from Natural Scenes. K. H. Zhu, F. H. Qi, R. J. Jiang, L. Xu, M. Kimachi, Y. Wu, and T.Aizawa. Отримано з http://www.imlab.jp/cbdar2005/proceedings/papers/O2-3.pdf