Abstract
Convolutional neural networks also encountered some problems in the development of image recognition. The most prominent problem is that it is costly and time-consuming to collect data sets and train models. Limited data sets will cause the trained models to overfit. This paper proposes two methods to reduce overfitting based on the residual neural network architecture. The first type of method proposes a method of cross-combining waivers, reducing the size of the convolution kernel, and reducing the number of convolution kernels. The fitting method uses cross-combination to make the accuracy of Kaggle cat and dog data on the validation data set reach 95.37% and 90.31% on 30 types of engineering practice verification data set. The second method is based on the finetune residual neural network. A method of recurrent finetune residual neural network is proposed to improve the accuracy of the model. The accuracy of the finetune residual neural network on the Kaggle cat and dog validation dataset is 99.37%, and the accuracy of the dataset is verified in 30 types of engineering practice. The accuracy is 99.30%. The residual neural network method achieves 99.68% accuracy in the Kaggle cat and dog validation dataset and 99.61% in the validation dataset for 30 types of engineering practice.
Similar content being viewed by others
References
Tkáč M, Verner R (2015) Artificial neural networks in business: two decades of research. Appl Soft Comput 38:788–804
Liu H, Guo RY (2018) Detection and identification of Sawh pipe weld defects based on X-ray image And CNN. Chin J Sci Instrum 39(4):247–256
Zhu F, Kong X, Fu H, Qi T (2017) A novel two-stream saliency image fusion CNN architecture for person re-identification. Multimed Syst 7:1–14
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2016) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected Crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Liu CQ, Chen BQ (2014) Method of image detection for ear of corn based on computer vision. Trans Chin Soc Agric Eng 30(6):131–138
Hu TH, Wan L, Liu TA, Wang MW, Chen T, Wang YH (2017) Advantages and application prospects of deep learning in image recognition and bone age assessment. J Forensic Med 6:629–634
Oliva D, Cuevas E, Pajares G, Zaldivar D (2014) Template matching using an improved electromagnetism-like algorithm. Appl Intell 41(3):791–807
Li SW, Xu Y, Sun WC, Yang ZK, Wang DQ (2014) Remote sensing image recognition for vehicles based on self-feedback template extraction. J South China Univ Technol 42(5):97–102
Wang G, Sun XL, Shang Y, Yu QF (2017) A robust template matching algorithm based on best-buddies similarity. Acta Opt Sin 37(3):0315003
Cambria E, White B (2014) Jumping NLP curves: a review of natural language processing research. Comput Intell Mag IEEE 9(2):48–57
Dighe P, Asaei A, Bourlard H (2015) Sparse modeling of neural network posterior probabilities for exemplar-based speech recognition. Speech Commun 76:230–244
Errattahi R, El Hannani A, Ouahmane H (2018) Automatic speech recognition errors detection and correction: a review. Procedia Comput Sci 128:32–37
Liu DW, Han L, Han XY (2016) High spatial resolution remote sensing image classification based on deep learning. Acta Opt Sin 36(4):0428001
Li Q, Zhao T, Zhang L, Sun W, Zhao X (2017) Ferrography wear particles image recognition based on extreme learning machine. J Electr Comput Eng 2017(2):1–6
Abdel-Rahman EM, Mutanga O, Adam E, Ismail R (2014) Detecting sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data, random forest and support vector machines classifiers. ISPRS J Photogramm Remote Sens 88:48–59
Huang HW, Li QT, Zhang DM (2018) Deep learning based image recognition for crack and leakage defects of metro shield tunnel. Tunn Undergr Space Technol 77:166–176
Chen X, Peng X, Duan R, Li J (2017) Deep kernel learning method for SAR image target recognition. Rev Sci Instrum 88(10):104706
Zhou T (2016) An image recognition model based on improved convolutional neural network. J Comput Theor Nanosci 13(7):4223–4229
Zhu B, Yang C, Yu C, An F (2018) Product image recognition based on deep learning. J Comput Aided Des Comput Graph 30(9):1778–1784
Shah SAA (2015) Iterative deep learning for image set based face and object recognition. Neurocomputing 174:866–874
Shah N, Chaudhari P, Varghese K (2018) Runtime programmable and memory bandwidth optimized FPGA-based coprocessor for deep convolutional neural network. IEEE Trans Neural Netw Learn Syst 99:1–13
Fei J, Rui T, Zhou Y, Fang H, Zhu H (2015) Multi-input convolutional neural network based on gradient. Opto-Electron Eng 42(3):33–38
Wang W, Chen G, Chen HB (2016) Deep learning at scale and at ease. ACM Trans Multimed Comput Commun Appl 12(4s):69
Liu R, Gillies DF (2015) Overfitting in linear feature extraction for classification of high-dimensional image data. Pattern Recognit 53(C):73–86
Jiu X, Gu ZH, Jason K (2018) Recent advances in convolutional neural networks. Pattern Recognit 21(C):35–48
Acknowledgements
This work was financially supported by the National Natural Science Youth Foundation of China (Grant Number 61805067).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that they have no conflicts of interest to this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, H., Geng, L., Zhao, H. et al. Image recognition algorithm based on artificial intelligence. Neural Comput & Applic 34, 6661–6672 (2022). https://doi.org/10.1007/s00521-021-06058-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06058-8