A method was developed to detect generic objects using a single query image. The query image could be a typical real image, a virtual image, or even a hand-drawn sketch of the object. Without a training process, the k...A method was developed to detect generic objects using a single query image. The query image could be a typical real image, a virtual image, or even a hand-drawn sketch of the object. Without a training process, the key problem is how to describe the object class from only one query image with no pre-segmentation or other pre-processing procedures. The method introduces densely computed Scale-lnvariant Feature Transform （SIFT） as the descriptor to extract ＂gradient distribution＂ features of the image. The descriptor emphasizes the edge parts and their distribution structures, which are very representative of the object class, so it is very robust and can deal with virtual images or hand-drawn sketches. Tests on car detection, face detection, and generic object detection demonstrate that the method is effective, robust, and widely applicable. The results using queries of real images compare well with other training-free methods and state-of-the-art training-based methods.展开更多
This paper proposes a novel method based on statistical tests of hypotheses, such as F-ratio and Welch’s t-tests. The input query image is examined whether it is a textured or structured. If it is structured, the sha...This paper proposes a novel method based on statistical tests of hypotheses, such as F-ratio and Welch’s t-tests. The input query image is examined whether it is a textured or structured. If it is structured, the shapes are segregated into various regions according to its nature;otherwise, it is treated as textured image and considered the entire image as it is for the experiment. The aforesaid tests are applied regions-wise. First, the F-ratio test is applied, if the images pass the test, then it is proceeded to test the spectrum of energy, i.e. means of the two images. If the images pass both tests, then it is concluded that the two images are the same or similar. Otherwise, they differ. Since the proposed system is distribution-based, it is invariant for rotation and scaling. Also, the system facilitates the user to fix the number of images to be retrieved, because the user can fix the level of significance according to their requirements. These are the main advantages of the proposed system.展开更多
Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial tr...Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial transactions. In this paper, we propose a human verification method depends on extraction a set of retinal features points. Each set of feature points is representing landmarks in the tree of retinal vessel. Extraction and matching of the pattern based on Gabor filters and SVM are described. The validity of the proposed method is verified with experimental results obtained on three different commonly available databases, namely STARE, DRIVE and VARIA. We note that the proposed retinal verification method gives 92.6%, 100% and 98.2% recognition rates for the previous databases, respectively. Furthermore, for the authentication task, the proposed method gives a moderate accuracy of retinal vessel images from these databases.展开更多
基金Supported by the National Key Basic Research and Development (973) Program of China (No.2007CB311004)
文摘A method was developed to detect generic objects using a single query image. The query image could be a typical real image, a virtual image, or even a hand-drawn sketch of the object. Without a training process, the key problem is how to describe the object class from only one query image with no pre-segmentation or other pre-processing procedures. The method introduces densely computed Scale-lnvariant Feature Transform （SIFT） as the descriptor to extract ＂gradient distribution＂ features of the image. The descriptor emphasizes the edge parts and their distribution structures, which are very representative of the object class, so it is very robust and can deal with virtual images or hand-drawn sketches. Tests on car detection, face detection, and generic object detection demonstrate that the method is effective, robust, and widely applicable. The results using queries of real images compare well with other training-free methods and state-of-the-art training-based methods.
文摘This paper proposes a novel method based on statistical tests of hypotheses, such as F-ratio and Welch’s t-tests. The input query image is examined whether it is a textured or structured. If it is structured, the shapes are segregated into various regions according to its nature;otherwise, it is treated as textured image and considered the entire image as it is for the experiment. The aforesaid tests are applied regions-wise. First, the F-ratio test is applied, if the images pass the test, then it is proceeded to test the spectrum of energy, i.e. means of the two images. If the images pass both tests, then it is concluded that the two images are the same or similar. Otherwise, they differ. Since the proposed system is distribution-based, it is invariant for rotation and scaling. Also, the system facilitates the user to fix the number of images to be retrieved, because the user can fix the level of significance according to their requirements. These are the main advantages of the proposed system.
文摘Authentication reliability of individuals is a demanding service and growing in many areas, not only in the military barracks or police services but also in applications of community and civilian, such as financial transactions. In this paper, we propose a human verification method depends on extraction a set of retinal features points. Each set of feature points is representing landmarks in the tree of retinal vessel. Extraction and matching of the pattern based on Gabor filters and SVM are described. The validity of the proposed method is verified with experimental results obtained on three different commonly available databases, namely STARE, DRIVE and VARIA. We note that the proposed retinal verification method gives 92.6%, 100% and 98.2% recognition rates for the previous databases, respectively. Furthermore, for the authentication task, the proposed method gives a moderate accuracy of retinal vessel images from these databases.
