粒子群优化结合相关反馈的花卉图像检索

Particle swarm optimization combined with relevance feedback for flower image retrieval

针对花卉图像特性,为平衡花卉图像检索系统的检索精度与速度,提出一种将粒子群优化结合于花卉检索相关反馈的算法.算法以2RGB为花卉图像的颜色模型,选取计算量较小的图像低层特征描述,按用户的满意度对检索结果进行评价,指导反馈过程中粒子的最优运动方向.实验结果表明,该算法能有效提高系统的检索效率.

Aiming at flower image characteristics and balancing retrieval accuracy and speed of flower image retrieval system, this paper proposes an algorithm for flower image retrieval relevance feedback combined with particle swarm optimization. The algorithm uses 2RGB color model for flower images, selects some less computational low -level image features, evaluates user satisfaction with the retrieval results to guide the optimal direction of particles motion in feedback process. Experiments show that the algorithm can improve the retrieval efficiency.