基于SSA-CatBoost 的颜色校正模型仿真  

Simulation of Color Correction Model Based on SSA-CatBoost

作　　者：沈楠翔 顾文娟[1] 李志文 王洪成 SHEN Nan-xiang;GU Wen-juan;LI Zhi-wen;WANG Hong-cheng(College of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming Yunnan 650504,China)

机构地区：[1]昆明理工大学机电工程学院,云南昆明650504

出　　处：《计算机仿真》2024年第4期219-223,228,共6页Computer Simulation

基　　金：基于烤烟基础样品的人工智能分级模型的建立及应用(2021530000241012)。

摘　　要：针对图像采集设备在采集过程中出现的颜色失真以及传统方法存在校正效果不佳的问题,提出了一种结合SSA算法的CatBoost颜色校正模型。首先,建立三个CatBoost模型,并使用SSA算法分别搜索三个模型的最佳参数;然后将所得到的最优参数赋值给三个CatBoost模型,并分别对三通道的测量值与真实值进行拟合;最后,与传统多项式回归方法进行对比,校验此模型校正效果。模型仿真结果表明,上述模型可将色差值ΔE控制在3以内,证实了SSA-CatBoost模型具有更好的颜色校正。In order to solve the problem of color distortion in the process of image acquisition equipment and the traditional method has poor correction effect,a CatBoost color correction model combined with SSA algorithm is proposed.Firstly,three CatBoost models were established,and the SSA algorithm was used to search the best parameters of the three models.Then the obtained optimal parameters were assigned to three CatBoost models,and the measured values of the three channels were fitted with the real values respectively.Finally,compared with the traditional polynomial regression method,the correction effect of this model was verified.The model simulation results show that shows that the model makes the color difference value(ΔE)is controlled within 3,which proves that the SSA-CatBoost model has better color correction.

关 键 词：颜色失真 麻雀搜索算法 对称决策树 颜色校正 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]