Comparative analysis of image classification algorithms based on traditional machine learning and deep learning

• Published in: Pattern recognition letters Vol. 141; pp. 61 - 67
• Main Authors: Wang, Pin, Fan, En, Wang, Peng
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.01.2021; Elsevier Science Ltd
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classification; Comparative analysis; Convolution; Convolutional neural networks; Datasets; Deep learning; Image classification; Image processing; Learning algorithms; Machine learning; Neural networks; Support vector machines; Traditional machine learning; Deep learning; Support vector machines; Traditional machine learning; Convolutional neural networks
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2020.07.042

•Representative SVM and CNN algorithms in traditional machine learning and deep learning for research.•Under other conditions being the same, the data sets are different. The impact of the results varies.•This article compares and analyzes the accuracy and running time. Image classification is a hot research topic in today's society and an important direction in the field of image processing research. SVM is a very powerful classification model in machine learning. CNN is a type of feedforward neural network that includes convolution calculation and has a deep structure. It is one of the representative algorithms of deep learning. Taking SVM and CNN as examples, this paper compares and analyzes the traditional machine learning and deep learning image classification algorithms. This study found that when using a large sample mnist dataset, the accuracy of SVM is 0.88 and the accuracy of CNN is 0.98; when using a small sample COREL1000 dataset, the accuracy of SVM is 0.86 and the accuracy of CNN is 0.83. The experimental results in this paper show that traditional machine learning has a better solution effect on small sample data sets, and deep learning framework has higher recognition accuracy on large sample data sets.