Title: Fuzzy edge detection method of product packaging image based on Kalman filter

Authors: Ruifang Xing; Jingjing Feng; Yayun Fan

Addresses: Xi'an Peihua University, Xi'an, Shaanxi, China ' Xi'an Peihua University, Xi'an, Shaanxi, China ' Xi'an Peihua University, Xi'an, Shaanxi, China

Abstract: The existing fuzzy edge detection methods for product packaging images are vulnerable to noise, resulting in the quality and effect of detection results cannot meet the actual needs, and the detection time is long, which affects the work efficiency. Therefore, based on Kalman filter algorithm, this paper studies the fuzzy edge detection method of product packaging image. Firstly, singular value decomposition algorithm is used to remove the noise of product packaging image. Then, the Fourier spectrum of the product packaging image is obtained by FFT operation, and the image blur parameters are quickly identified. Finally, the image fuzzy edge is processed by Kalman filter to realise image fuzzy edge detection. The experimental results show that the detection signal-to-noise ratio of the proposed method is as high as 61.5 dB, the quality factor is as high as 0.97, and the detection time is short, only 19.7 s. It can be proved that the proposed method can effectively improve the quality and efficiency of fuzzy edge detection of product packaging image.

Keywords: Kalman filter; singular value decomposition; FFT; product packaging image; fuzzy edge detection.

DOI: 10.1504/IJPD.2024.137815

International Journal of Product Development, 2024 Vol.28 No.1/2, pp.47 - 59

Received: 22 Apr 2022
Accepted: 03 Oct 2022
Published online: 05 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article