Abstract
Recently, image feature extraction has been an essential topic in computer research. In response to the problem that the accuracy and efficiency of extracting image texture features are still insufficient to meet the practical requirements in applications, this study presents a new transformation invariant low rank texture feature extraction and restoration algorithm. Firstly, the basic contents of image texture features and sparse representation are introduced. Then a new transformation invariant low rank texture feature extraction and restoration algorithm is proposed in view of this. From the results, the research algorithm had a higher peak signal-to-noise ratio of 36.02 dB. The high fidelity criterion value of the research algorithm was 7.04. The structural similarity index of the research algorithm was relatively high, with a value of 0.9146. The average relative error of the research algorithm is 2.327%, the mean square error is 1.327%, the mean absolute error is 7.265%, the root mean square deviation was 0.1123, and the coefficient of determination was 0.9998. The experimental results show that the proposed algorithm has good performance in extracting image texture features and has certain application value in pattern extraction of architectural decoration surfaces. Research can provide theoretical basis and data support for image feature extraction, which is not only of great significance in improving the realism and aesthetics of architectural decoration, but also has a broad application prospect in the field of ancient building restoration, which helps to protect and inherit cultural heritage.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03626-y/MediaObjects/11760_2024_3626_Fig16_HTML.png)
Similar content being viewed by others
Data availability
No datasets were generated or analysed during the current study.
References
Sajwan, V., Ranjan, R., Swapnil, S.: Color texture description with diagonal local binary patterns using a new distance metric for impressive image retrieval. Indian J. Comput. Sci. Eng. 12(4), 1112–1124 (2021). https://doi.org/10.21817/indjcse/2021/v12i4/211204213
Li, W., Huang, Q., Srivastava, G.: Contour feature extraction of medical image based on multi-threshold optimization. Mobile Netw. Appl. 26(1), 381–389 (2021). https://doi.org/10.1007/s11036-020-01674-5
Nie, Q., Zou, Y.B., Lin, C.W.: Feature extraction for medical CT images of sports tear injury. Mob. Netw. Appl. 26(1), 404–414 (2021). https://doi.org/10.1007/S11036-020-01675-4
Zhang, B., Gao, Y., Wu, J., Wang, N., Wang, Q., Ren, J.: Approach to predict software vulnerability based on multiple-levelN-gram feature extraction and heterogeneous ensemble learning. Int. J. Softw. Eng. Knowl. 32(10), 1559–1582 (2022). https://doi.org/10.1142/S0218194022500620
Chen, H., Gao, J., Jiang, X., Gao, Z., Zhang, W.: Optimization-inspired deep learning high-resolution inversion for seismic data. Geophys. 86(3), 1–15 (2021). https://doi.org/10.1190/geo2020-0034.1
Huang, J., Zhang, F., Wang, J., Wang, H., Liu, X., Jia, J.: An analysis of noise folding for low-rank matrix recovery. Anal. Appl. 21(2), 429–451 (2023). https://doi.org/10.1142/S0219530522500154
Xu, J., Wang, F., Peng, Q., You, X., Wang, S., Jing, X.Y., Philip Chen, C.L.: Modal-regression-based structured low-rank matrix recovery for multiview learning. IEEE Trans. Neural Netw. Learn. Syst. 32(3), 1204–1216 (2021). https://doi.org/10.1109/tnnls.2020.2980960
Lai, M.J., Liu, Y., Li, S., Wang, H.: On the schatten p-quasi-norm minimization for low-rank matrix recovery. Appl. Comput. Harmonic Anal. 51(2), 157–170 (2021). https://doi.org/10.1016/j.acha.2020.11.001
Quézia, C., Porsani, M.J.: Low-rank seismic data reconstruction and denoising by CUR matrix decompositions. Geophys. Prospect. 70(2), 362–376 (2022). https://doi.org/10.1111/1365-2478.13163
Wang, Z.Y., Abhadiomhen, S.E., Liu, Z.F., Shen, X.J., Gao, W.Y., Li, S.Y.: Multi-view intrinsic low-rank representation for robust face recognition and clustering. IET Image Process. 15(14), 3573–3584 (2022). https://doi.org/10.1049/ipr2.12232
Ge, Y., Du, B., Tang, H., Zhong, P.: Rock joint detection from borehole imaging logs based on gray-level co-occurrence matrix and Canny edge detector. Q. J. Eng. Geol. Hydrogeol. 55(1), 1–11 (2022). https://doi.org/10.1144/qjegh2021-016
Rajappan, R.J., Kandaswamy, T.K.: A composite framework of deep multiple view human joints feature extraction and selection strategy with hybrid adaptive sunflower optimization-whale optimization algorithm for human action recognition in video sequences. Comput. Intell. 38(2), 366–396 (2022). https://doi.org/10.1111/coin.12499
Li, Z., Qian, Y., Wang, H., Zhou, X., Sheng, G., Jiang, X.: A novel image-orientation feature extraction method for partial discharges. IET Gen., Transm. Distrib. 16(6), 1139–1150 (2022). https://doi.org/10.1049/ipr2.12232
Wang, S., Ma, Z., Sun, X.: Feature extraction method of face image texture spectrum based on a deep learning algorithm. Int. J. Biometrics 13(2), 195–210 (2022). https://doi.org/10.1504/IJBM.2021.10036136
Yogeshwari, M., Thailambal, G.: Automatic feature extraction and detection of plant leaf disease using GLCM features and convolutional neural networks. Mater Today: Proc 81(3), 530–536 (2023). https://doi.org/10.1016/j.matpr.2021.03.700
Dhiman, G., Kumar, A.V., Nirmalan, R., Sujitha, S., Srihari, K., Yuvaraj, N., Arulprakash, P., Raja, R.A.: Multi-modal active learning with deep reinforcement learning for target feature extraction in multi-media image processing applications. Multimedia Tools Appl 82(4), 5343–5367 (2023). https://doi.org/10.1007/s11042-022-12178-7
Ranjbarzadeh, R., Tataei Sarshar, N., Jafarzadeh Ghoushchi, S., Saleh Esfahani, M., Parhizkar, M., Pourasad, Y., Anari, S., Bendechache, M.: MRFE-CNN: multi-route feature extraction model for breast tumor segmentation in Mammograms using a convolutional neural network. Ann. Oper. Res. 328(1), 1021–1042 (2023). https://doi.org/10.1007/s10479-022-04755-8
Wang, S., Ma, Z., Sun, X.: Feature extraction method of face image texture spectrum based on a deep learning algorithm. Int. J. Biometrics 13(2), 195–210 (2021). https://doi.org/10.1504/IJBM.2021.10036136
Benning, M., Celledoni, E., Ehrhardt, M.J., Owren, B., Schnlieb, C.B.: Deep learning as optimal control problems. IFAC-PapersOnLine 54(9), 620–623 (2021). https://doi.org/10.1016/j.ifacol.2021.06.124
Zhao, X., Xue, L., Xu, F.: Asphalt pavement paving segregation detection method using more efficiency and quality texture features extract algorithm. Constr. Build. Mater. 277(4), 12–32 (2021). https://doi.org/10.1016/j.conbuildmat.2021.122302
Darapureddy, N., Karatapu, N., Battula, T.K.: Comparative analysis of texture patterns on mammograms for classification. Traitement Du Signal 38(2), 379–386 (2021). https://doi.org/10.18280/ts.380215
Chen, F., Muhammad, K., Wang, S.H.: Three-dimensional reconstruction of CT image features based on multi-threaded deep learning calculation. Pattern Recognit. Lett. 136(8), 309–315 (2021). https://doi.org/10.1016/j.patrec.2020.04.033
Khojastehnazhand, M., Roostaei, M.: Classification of seven Iranian wheat varieties using texture features. Expert Syst. Appl. 199(8), 1–12 (2023). https://doi.org/10.1016/j.eswa.2022.117014
Saeed, U.: Facial micro-expressions as a soft biometric for person recognition. Pattern Recognit. Lett. 143(5), 95–103 (2021). https://doi.org/10.1016/j.patrec.2020.12.021
Yang, D., Ye, X., Guo, B.: Application of multitask joint sparse representation algorithm in Chinese painting image classification. Complexity 2021(2), 1–11 (2021). https://doi.org/10.1155/2021/5546338
Hedyehzadeh, M., Maghooli, K., Momengharibvand, M.: Glioma grade detection using grasshopper optimization algorithm, ptimized machine learning methods: the cancer imaging archive study. Int. J. Imaging Syst. Technol. 31(3), 1670–1677 (2021)
Funding
The research is supported by: The third scientific research project of the Yellow River Basin Industry-Education Alliance Project Title: Research on the High-quality Development Model of Vocational Education in the New Era from the Perspective of Industry-education Integration (No. HHLYYB53).
Author information
Authors and Affiliations
Contributions
L.X. wrote the main manuscript text and prepared all works.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xia, L. Transform invariant low rank texture feature extraction and restoration algorithms for architectural decoration surface patterns. SIViP 19, 101 (2025). https://doi.org/10.1007/s11760-024-03626-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11760-024-03626-y