Building a 3D Form to Recognize Facial Images
DOI:
https://doi.org/10.37375/sjfssu.v2i1.130Keywords:
Image Recognition, Multilayer Neural Networks, ,3D Image, Pattern Recognition, Correlation, Model.Abstract
There are several problems with the ability to recognize facial images, so the image was built in a 3D format, which allows users to evaluate and form the necessary properties of the entire object, while it is impossible to do this in two-dimensional form. Reprinting an object in an image form enables most of the properties of the target image by using layer-based neural networks that learn sequentially with discrete mathematical structures. A two-dimensional image is taken, and then the 3D shape is used in the image to spatially renovate it while different noise levels and different lighting levels are considered. This paper aims to show that the model for reconstructing the three-dimensional image reveals the dilemma of defining the basic characteristics of the image as a whole in all cases of interference, even if the viewpoint of taking the image changes. The processing has several stages. First, input the data processing result obtained in the previous level into the next level input to get the final result. After training, the first level sequences are represented as graphs, and then the input image data is sent to the first layer of the recognition model to calculate h. Consistent activation of learning validity for each subsequent level of the proposed model of reprinting an object in an image completely solves the problem of identifying a person from the front image as a whole under interference and regardless of the change in the perspective image.
References
Hemalatha, G., & Sumathi, C. P. (2014). A study of techniques for facial detection and expression classification. International Journal of Computer Science and Engineering Survey, 5(2), 27.
Hasan, M. H. M., Jouhar, W. A. A., & Alwan, M. A. (2012). 3-d face recognition using improved 3d mixed transform. International Journal of Biometrics and Bioinformatics (IJBB), 6(1), 278.
Blanz, V., & Vetter, T. (2003). Face recognition based on fitting a 3d morphable model. IEEE Transactions on pattern analysis and machine intelligence, 25(9), 1063-1074.
Alexandre, G. R., Soares, J. M., & Thé, G. A. P. (2020). Systematic review of 3D facial expression recognition methods. Pattern Recognition, 100, 107108.
Albakri, G., & Alghowinem, S. (2019). The effectiveness of depth data in liveness face authentication using 3D sensor cameras. Sensors, 19(8), 1928.
Noyes, E., Hill, M. Q., & O’Toole, A. J. (2018). Face recognition ability does not predict person identification performance: Using individual data in the interpretation of group results. Cognitive research: principles and implications, 3(1), 1-13.
Huang, X., Zhao, G., & Pietikäinen, M. (2013). Emotion recognition from facial images with arbitrary views. In BMVC (pp. 76-1).
Hsieh, C. T., Huang, Y., Chen, T. W., & Chen, L. M. 3D (2015) FACE MODEL CONSTRUCTION BASED ON KINECT FOR FACE RECOGNITION.
Amor, B. B., Ouji, K., Ardabilian, M., & Chen, L. (2008). 3D Face recognition BY ICP-based shape matching,‖ LIRIS Lab. Lyon Research Center for Images and Intelligent Information Systems, UMR, 5205.
Tyagi, V. (2018). Understanding digital image processing. CRC Press.
Turk, I. (2019). Practical MATLAB. Apress.
Solomon, C., & Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons.
Kaushik, P., Kaushik, H., & Singh, H. (2018). Building a Face Recognition Technique for Encryption by MATLAB.
Cao, M., Liu, Z., Huang, X., & Shen, Z. (2021, March). Research for Face Image Super-Resolution Reconstruction Based on Wavelet Transform and SRGAN. In 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) (Vol. 5, pp. 448-451). IEEE.
Afzal, H. R., Luo, S., Afzal, M. K., Chaudhary, G., Khari, M., & Kumar, S. A. (2020). 3D face reconstruction from single 2D image using distinctive features. IEEE Access, 8, 180681-180689.
