实验表明该算法获得的图像匹配结果较传统算法在颜色相似度和细节保持方面均有明显的提高。
Experiments show that the proposed algorithm has obvious advantage over traditional ones, especially in color difference and image details.
介绍了基于内容图像检索中多种颜色的特征提取和匹配算法,以及加权欧几里得距离、中心距的加权距离、直方图交集算法等。
Introduces color feature extraction and matching algorithms in content-based image retrieval, such as weighted Euclidean-distance, weighted centre distance, histogram intersection algorithm, etc.
在复杂背景的图像中,用直方图作为目标的特征模板,依据颜色分布进行匹配,具有较好的稳定性。
Histogram as the characteristic template of target and matched based on color distribution has good stability in the complex background image.
应用推荐