The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper we present a system for mobile augmented reality (AR) based on visual recognition. We split the tasks of recognizing an object and tracking it on the user's screen into a server-side and a client-side task, respectively. The capabilities of this hybrid client-server approach are demonstrated with a prototype application on the Android platform, which is able to augment both stationary...
Content based retrieval and recognition of objects represented in images is a challenging problem making it an active research topic. Shape analysis is one of the main approaches to the problem. In this paper we propose the use of a reduced set of features to describe 2D shapes in images. The design of the proposed technique aims to result in a short and simple to extract shape description. We conducted...
With the development of content-based multimedia systems, there is a need for automatic extraction of central object from natural color images. A new method for automatic extraction of central object is presented in this paper. First, a criterion of homogeneity based on both the global and the local information for HSV color images is proposed, and is used to get the "E-image". The high...
Many state-of-the-art object recognition systems rely on identifying the location of objects in images, in order to better learn its visual attributes. In this paper, we propose four simple yet powerful hybrid ROI detection methods (combining both local and global features), based on frequently occurring keypoints. We show that our methods demonstrate competitive performance in two different types...
SIFT (scale invariant feature transform) used in fruits recognition presents a characteristics matching algorithm according to fruits images. The algorithm uses SIFT characteristics as matching feature, then introduces Euclidean distance as the similarity metrics of image matching, and uses a method of setting a threshold value to delete the false matching points. The experimental results prove that...
Interest points have been used as local features with success in many computer vision applications such as image/video retrieval and object recognition. However, a major issue when using this approach is a large number of interest points detected from each image and created a dense feature space. This influences the processing speed in any runtime application. Selecting the most important features...
Edition of natural images usually asks for considerable user involvement, being segmentation one of the main challenges. This paper describes an unified graph-based framework for fast, precise and accurate interactive image segmentation. The method divides segmentation into object recognition, enhancement and extraction. Recognition is done by the user when markers are selected inside and outside...
Appearance information is essential for applications such as tracking and people recognition. One of the main problems of using appearance-based discriminative models is the ambiguities among classes when the number of persons being considered increases. To reduce the amount of ambiguity, we propose the use of a rich set of feature descriptors based on color, textures and edges. Another issue regarding...
Due to the advents of multi-core CPU and GPU, various parallel processing techniques have been widely applied to many application fields including computer vision. This paper presents a parallel processing technique for realtime feature extraction in object recognition by autonomous mobile robots, which utilizes both CPU and GPU by combining OpenMP, SSE (Streaming SIMD Extension) and CUDA programming...
Efficiency image matching technology is very important to assembly product line based on machine vision. SIFT (scale invariant feature transform) descriptor is commonly used in image matching because of the good invariance of scale, rotation, illumination. But its algorithm is complicated and computation time is long. To improve SIFT algorithm real-time quality, the method of reducing similar measure...
It can improve the recognition rate and segmentation accuracy of moving objects in strong wind and no buildings to extract the features of trees. In this paper, the similarity criterion about the pore texture feature matching of tree crown is proposed by analyzing the pore texture feature and experimenting. The feature difference matrix of 5times5 pixels is chosen as the basic operator of tree features...
This paper present a new method to extract shapes in drop caps and particularly the most important shape: letter itself. This method relies on a combination of a Aujol and Chambolle algorithm first, and a segmentation using a Zipf law in a second step. This method can be enhanced as a three-step process: 1) decomposition in layers 2) segmentation using a Zipf law 3) selection of connected components...
Edge structures which are boundaries of object surfaces are essential image characteristic in computer vision and image processing. As a result, edge detection becomes part of the core feature extraction in many object recognition and digital image applications. This paper presents a new hybrid edge detector that combines the advantages of Prewitt, Sobel and optimized Canny edge detectors to perform...
A new multiscale approach to motion based segmentation of objects in video sequences is presented. While image features extracted at multiple scales are commonly used within the pattern recognition community, they have seldom been employed for background modelling and subtraction. The paper describes a methodology for maintaining an explicit background model at multiple scales. Biological inspiration...
This paper presents a road signs detection, recognition and tracking system based on multi-cues hybrid. In detection stage, the color and gradient cues are used to segment the interesting regions, and the corner and geometrical cues are used to detect the signs. A pseudo RGB-HSI conversion method without the need of nonlinear transformation is presented for color extraction. In recognition stage,...
In this paper we present a method for learning class-specific features for recognition. Recently a greedy layer-wise procedure was proposed to initialize weights of deep belief networks, by viewing each layer as a separate restricted Boltzmann machine (RBM). We develop the convolutional RBM (C-RBM), a variant of the RBM model in which weights are shared to respect the spatial structure of images....
Several recently-proposed architectures for high-performance object recognition are composed of two main stages: a feature extraction stage that extracts locally-invariant feature vectors from regularly spaced image patches, and a somewhat generic supervised classifier. The first stage is often composed of three main modules: (1) a bank of filters (often oriented edge detectors); (2) a non-linear...
This work adds the concept of object to an existent low-level attention system of the humanoid robot iCub. The objects are defined as clusters of SIFT visual features. When the robot first encounters an unknown object, found to be within a certain (small) distance from its eyes, it stores a cluster of the features present within an interval about that distance, using depth perception. Whenever a previously...
This paper presents a new approach to detect points of interest in an image. It uses swarm intelligence to detect centers of objects which are considered as points of high interest because many of psychological works state that the symmetry attracts the attention of human visual system. This fact led to the choice of symmetric objects' centers as points having a high visual interest and then used...
Bridge is an important artificial target in the field of remote sensing analysis. A method for automatic recognition of bridges over water in high-resolution remote sensing images is presented. Firstly, we establish bridge knowledge models. Based on top-down knowledge-driven, the flow is composed of two steps: hypothesis and testing. Hypothesis is rough positioning including such techniques: waters...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.