Research on Image Enhancement of Crisp-Ripe Stage Red Jujube Based on Particle Swarm Optimization Algorithm
Machine vision technology plays a crucial role in non-destructive detection and online monitoring of deep processing for red dates during the crisp-ripe stage. However, due to factors such as uneven illumination in the collection environment and illumination attenuation on the curved surface of quasi-spherical objects, the collected images of red dates during the crisp-ripe stage often suffer from issues such as low overall image quality, difficulty in recognizing epidermal fruit spots and fine textures, low contrast between fruit surface crack defects and normal fruit surfaces, and blurred fruit body edges, which increase the difficulty of accurately identifying fruit surface features. In response to the common problems of over-enhancement and loss of details in current image enhancement methods when processing images of red dates during the crisp-ripe stage, this paper combines the practical requirements of preserving details of the fruit body and crack edges, enhancing epidermal texture clarity, balancing contrast and noise, and constructs a multi-dimensional image enhancement fitness function. A method for enhancing images of red dates during the crisp-ripe stage based on the Particle Swarm Optimization (PSO) algorithm is proposed. Through comparative experiments on image enhancement of red dates during the crisp-ripe stage, the effectiveness and superiority of the proposed image enhancement method are verified from both subjective visual effects and objective evaluation indicators.
References
- Khan, A. H., Ahmed, S., Bera, S. K., Mirjalili, S., Oliva, D., & Sarkar, R. (2022). Enhancing the contrast of the grey-scale image based on meta-heuristic optimization algorithm. Soft Computing, 26(13), 6293–6315.
- Li, C., Li, Y. J., Li, X. Z., Yu, G. W., Liu, X., & Ma, B. X. (2022). Research progress on external quality detection technology of Chinese jujube based on machine vision. Science and Technology of Food Industry, 43(20), 447–453.
- Zhang, W., Yang, S., Li, M., et al. (2026). A hybrid multiobjective particle swarm optimization with Q-learning-driven local search for distributed heterogeneous hybrid flow-shop scheduling problem with worker-machine-environment collaboration. Journal of Manufacturing Systems, 85, 1–21.
- Du, N., Luo, Q., Du, Y., et al. (2022). Color image enhancement: A metaheuristic chimp optimization algorithm. Neural Processing Letters, 54(6), 4769–4808.
- Tubbs, J. D. (1997). A note on parametric image enhancement. Pattern Recognition, 30(4), 617–621.
- Fan, X., Sun, Z., Tian, E., et al. (2023). Medical image contrast enhancement based on improved sparrow search algorithm. International Journal of Imaging Systems and Technology, 33(1), 389–402. https://doi.org/10.1002/ima.22791
- Chen, J., Yu, W., Tian, J., Li, C., & Chen, L. (2018). Image contrast enhancement using an artificial bee colony algorithm. Swarm and Evolutionary Computation, 38, 287–294. https://doi.org/10.1016/j.swevo.2017.09.002
- Mukhopadhyay, S., Hossain, S., Malakar, S., et al. (2023). Image contrast improvement through a metaheuristic scheme. Soft Computing, 27(18), 13657–13676. https://doi.org/10.1007/s00500-023-07947-2