摘要
This paper presents a method for correspondence. This technique works by two recognizing images with steps： reference keypoint flat objects based on global keypoint structure selection and structure projection. The using of global keypoint structure is an extension of an orderless bag-of-features image representation, which is utilized by the proposed matching technique for computation efficiency. Specifically, our proposed method excels in the dataset of images containing ＂flat objects＂ such as CD covers, books, newspaper. The efficiency and accuracy of our proposed method has been tested on a database of nature pictures with flat objects and other kind of objects. The result shows our method works well in both occasions.
This paper presents a method for correspondence. This technique works by two recognizing images with steps： reference keypoint flat objects based on global keypoint structure selection and structure projection. The using of global keypoint structure is an extension of an orderless bag-of-features image representation, which is utilized by the proposed matching technique for computation efficiency. Specifically, our proposed method excels in the dataset of images containing ＂flat objects＂ such as CD covers, books, newspaper. The efficiency and accuracy of our proposed method has been tested on a database of nature pictures with flat objects and other kind of objects. The result shows our method works well in both occasions.
基金
supported by the National Natural Science Foundation of China under Grant Nos.61133009,61073089
the Innovation Program of the Science and Technology Commission of Shanghai Municipality of China under Grant No.10511501200
the Open Project Program of the National Laboratory of Pattern Recognition of China
