摘要
视觉词语的产生是基于字袋模型的图像检索中的重要一环:根据已知的视觉词典,查询图像特征被映射到词典中相应的视觉词语。提出一种新的基于空间相关性的快速视觉词语产生算法。统计视觉词典中任意两个词语在数据库中的共生次数,构建视觉词语共生表。利用共生表,建立一种新的概率预测器来辅助预测已知词语的近邻词语。将预测器与快速近似最近邻查找算法结合,在标准图像检索数据库上进行实验测试,相比较传统的树形搜索算法或哈希算法,新算法在时间效率上获得明显提高。
Visual word generation is a key observation in obtaining the bag-of-visual-words (BOVW) representation fin. image retrieval: query image feaures are mapped to their' visual words according to the pre-elustered codebook. In this paper, we propose a novel generation approach based on the spatial correlation of visual words. A visual word cn-oeeurrence table is constructed in the first step. Given the known visual words, a new probabilistic predictor is then presented to acce-lerate the generation of their" neighboring visual words. We combine the co-occurrence table with the fast libral7 for apprnxi-mate nearest neighbors (FLANN) , and test it on the Oxford dataset. Comparisons with representative approaches suggest the efficiency and effectiveness of the new scheme.
出处
《中国图象图形学报》
CSCD
北大核心
2013年第6期706-710,共5页
Journal of Image and Graphics
基金
国家重点基础研究发展计划(973)基金项目(2011CB302400)
国家自然科学基金项目(60975014
61121002)
北京市自然科学基金项目(4102024)
深圳基础研究课题(JCYJ20120614152136201)
关键词
字袋模型
空间相关性
视觉词语共生表
概率预测器
bag-of-visual-words (BOVW)
spatial correlation
visual word co-occurrence table
probabilistic predictor