Title: Contrast enhancement method for product packaging colour images based on machine vision
Authors: Chenhan Huang; Jing Zhu
Addresses: School of Art, Anhui University of Finance and Economics, Bengbu, Anhui, China ' Faculty of Creative Industries, City University of Malaysia, Kuala Lumpur, Malaysia
Abstract: To overcome the problems of low-image signal-to-noise ratio, poor quality and long processing time associated with traditional methods, a contrast enhancement method for product packaging colour images based on machine vision is proposed. Correction is performed for camera radial distortion, eccentric distortion and thin prism distortion. The machine vision camera with parameter correction is used to capture the product packaging colour images. Histogram equalisation is applied as a pre-processing step to the captured images. Gamma correction is then used to enhance the contrast of the pre-processed images, resulting in improved contrast of the product packaging colour images. The experimental results show that the average signal-to-noise ratio of the enhanced product packaging colour images using the proposed method is 56.73 dB. The image details are clearer and more defined, with higher saturation and contrast, and the colours are more vivid. The average processing time for contrast enhancement is 68.11 ms.
Keywords: machine vision; product packaging; colour images; contrast enhancement; histogram equalisation; gamma correction.
International Journal of Product Development, 2024 Vol.28 No.3, pp.165 - 183
Received: 18 Sep 2023
Accepted: 27 Feb 2024
Published online: 25 Jul 2024 *