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
针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发...针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发一种交互式资源管理系统,对实验影像资源内容进行多元信息标注并分配权重,应用ADO.NET(Microsoft ActiveX Data Objects.Net)技术实现影像资源多元信息的编辑和存储,基于多元信息权重创建推荐查询方法,联合浏览选择,实现影像资源的获取与应用。测试结果表明本系统可根据影像资源多元信息进行添加、删除、修改和查询,当输入字段与本地数据库无法精确匹配时可智能推荐数据,实现了对影像资源多元信息的有效管理。多元信息能够唯一准确标识影像资源并作为资源管理的依据,基于多元信息权重设计的推荐方法能够有效解决用户输入字段与本地数据表不完全匹配的问题。展开更多
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
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.
文摘针对免耕播种装备产品数据管理(Product data management,PDM)系统的实验影像资源在存储和查询过程中内容甄别困难、用户获取相关资源需求难以保证的问题,在VS(Microsoft Visual Studio)环境下应用VB.NET语言搭载SQL Server数据库开发一种交互式资源管理系统,对实验影像资源内容进行多元信息标注并分配权重,应用ADO.NET(Microsoft ActiveX Data Objects.Net)技术实现影像资源多元信息的编辑和存储,基于多元信息权重创建推荐查询方法,联合浏览选择,实现影像资源的获取与应用。测试结果表明本系统可根据影像资源多元信息进行添加、删除、修改和查询,当输入字段与本地数据库无法精确匹配时可智能推荐数据,实现了对影像资源多元信息的有效管理。多元信息能够唯一准确标识影像资源并作为资源管理的依据,基于多元信息权重设计的推荐方法能够有效解决用户输入字段与本地数据表不完全匹配的问题。
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.
