欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出了一种物体分类模型——潜在局部区域空间关系模型及实现算法．模型描述物体各部分间的潜在空间关系，将抗缩放和仿射变换的特征区域方法与模型相结合，采用变分期望值最大方法进行学习．与同类空间关系模型算法比较，该文模型算法具有以下优点：（1）为非监督式学习模型；（2）可抵抗几何变换；（3）模型为稠密模型；（4）模型描述的是一种潜在的空间关系，这种关系对物体具有更本质的描述．在标准测试图像库上的实验表明了该算法在抵抗平移、旋转、尺度缩放、仿射变换和部分遮挡等难点问题上具有优势．
英文摘要：
Latent Local Spatial Relations （LLSR） model is presented as a novel technique of learning spatial models for visual object classification. Combined the latent local spatial relations model with statistical visual words and variational expectation maximization, LLSR is developed as an implementation of object classification algorithm. LLSR uses an unsupervised process that can capture both spatial relations and visual words appearances simultaneously. In contrast to other methods which explicitly give some parameterized spatial models, the proposed algorithm uses a latent class model to reveal some certain latent spatial relations. The advantages of the proposed model include： （1） it uses an unsupervised learning paradigm which can avoid some manual controls; （2） it can resist some geometry transforms; （3） it is a dense model; （4） the spatial relations are latent which have more insight into describing the object structure. The experiments are demonstrated on some standard databases and show that LLSR is a promising model for solving object classification problems, especially for translation, rotation, scale, affine and part of occlusion.
同期刊论文项目
同项目期刊论文
期刊信息
位置：