TY - GEN
T1 - Research on Commodity Image Data Compression Based on SVD Algorithm
AU - Han, Xiaowei
AU - Hu, Wen
AU - Weng, Rui
AU - Yao, Guilin
AU - Zhang, Yuru
AU - Hua, Xiaojie
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/5/28
Y1 - 2021/5/28
N2 - In recent years, with the development of E-commerce economy, growth of multimedia information data is very rapid. The data without image compression processing will be limited in processing and storage, and it is not conducive to the use of machine learning for data mining. In this paper, SVD (Singular Value Decomposition) image compression algorithm is used to reduce the dimension of the images in the commodity image data set of Harbin University of Commerce, and preserve the image features. This study mainly uses the scikit-learn open source machine learning library written in Python language, combined with the function of the module, to write the target algorithm. The experimental results show that different commodity images in the dataset can achieve 0.7-0.9 compression ratio through the algorithm, while maintaining good image features. It is significant to improve the efficiency of image data transmission and the machine learning research for this dataset.
AB - In recent years, with the development of E-commerce economy, growth of multimedia information data is very rapid. The data without image compression processing will be limited in processing and storage, and it is not conducive to the use of machine learning for data mining. In this paper, SVD (Singular Value Decomposition) image compression algorithm is used to reduce the dimension of the images in the commodity image data set of Harbin University of Commerce, and preserve the image features. This study mainly uses the scikit-learn open source machine learning library written in Python language, combined with the function of the module, to write the target algorithm. The experimental results show that different commodity images in the dataset can achieve 0.7-0.9 compression ratio through the algorithm, while maintaining good image features. It is significant to improve the efficiency of image data transmission and the machine learning research for this dataset.
KW - Image compression
KW - SVD algorithm
KW - dimensionality reduction
KW - machine learning
UR - https://www.scopus.com/pages/publications/85113476129
U2 - 10.1145/3469213.3470700
DO - 10.1145/3469213.3470700
M3 - 会议稿件
AN - SCOPUS:85113476129
T3 - ACM International Conference Proceeding Series
BT - Proceedings of 2021 2nd International Conference on Artificial Intelligence and Information Systems, ICAIIS 2021
PB - Association for Computing Machinery
T2 - 2nd International Conference on Artificial Intelligence and Information Systems, ICAIIS 2021
Y2 - 28 May 2021 through 30 May 2021
ER -