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 method for the retrieval of document images with chosen layout characteristics. The proposed method is based on statistics of patch-codewords over different regions of image. We begin with a set of wanted and a random set of unwanted images representative of a large heterogeneous collection. We then use raw-image patches extracted from the unlabeled images to learn a codebook...
In this paper, we address the problem of representing objects using contours for the purpose of recognition. We propose a novel segmentation method for integrating a new contour matching energy into level set based segmentation schemes. The contour matching energy is represented by major components of Elliptic Fourier shape descriptors and serves as a shape prior to guide the curve evolution. The...
According to the latest Internet usage statistics, more than 4.5 million photos are being uploaded to Flickr every day. An automated system that can provide feedback about aesthetic value or quality based on learned rules could be a very useful support in picture searching, sorting and editing. This is a challenging problem as it requires semantic understanding of images, which is beyond the state-of-the-art...
Texture analysis and classification is a well researched topic in computer vision. Since textures are captured at arbitrary angles, the derivation of rotation-invariant texture descriptors has received much attention. A group of high performing texture algorithms are based on the concept of local binary patterns (LBP). These algorithms are very efficient as they typically rely solely on local comparison...
Affine transformation detection can be used in many computer vision and other applications. This paper presents a new method for affine transformation detection. The state-of-the-art methods are mainly divided into two classes. One class is based on complicated descriptors. But this kind of methods need a lot of time to establish and matching the complicated descriptors. The second class is based...
A new soft relevance technique for scene categorization is proposed in this paper. A popular approach for scene categorization is the Bag-of-Words (BoW) framework, where a histogram is calculated for each image as the image signature. However, in most of the existing BoW based image classification methods, all the image signatures are regarded equally, so the outlier images may be harmful to the classification...
In this paper, we propose a Bayesian nonparametric approach for modeling and selection based on the mixture of Dirichlet processes with Dirichlet distributions, which can also be considered as an infinite Dirichlet mixture model. The proposed model adopts a stick-breaking representation of the Dirichlet process and is learned through a variational inference method. In our approach, the determination...
In this paper we examine the causes of one of the major shortcomings of current natural feature registration approaches, failure to register when the camera's view approaches parallel to the marker. The methods used by current registration algorithms in the attempt to overcome this problem are reviewed, and a novel tracking based approach called the Optical-flow Perspective Invariant Registration...
Efficient location of fruits in the trees is the most important criterion of an automatic robotic harvesting system. The main challenges faced in the development of the robotic harvesting arm are accurate identification of the fruits in dense foliages and detection of the occluded fruits. This paper proposes a statistical technique that accurately detects and tracks pomegranates in trees. A k-means...
The usual method for classification processes of brazil-nut is manual and present some drawbacks like slowness, subjectivity, and inconsistency. In this paper, the main objective is to automate the classification process by analysing digital images with multiple brazil-nuts. These images have been segmented using the Level Set method without reinitialization with a new stopping criteria based on the...
Recent work shows interest-point-based representation is greatly popular in action recognition, due to their simple implementation and good reliability. The neighborhood information of local descriptors usually improves the recognition accuracy. Taking inspiration from this observation, we propose a novel hierarchical neighborhood descriptor for action recognition. At low level, we propose the compound...
We present a novel feature, named Spatio-Temporal Interest Points Chain (STIPC), for activity representation and recognition. This new feature consists of a set of trackable spatio-temporal interest points, which correspond to a series of discontinuous motion among a long-term motion of an object or its part. By this chain feature, we can not only capture the discriminative motion information which...
The challenge addressed in this paper is the classification of visual objects by robots. Visual classification is an active field within Computer Vision, with excellent results achieved recently.
Tensor based dimensionality reduction has recently attracted attention from computer vision and pattern recognition communities for both feature extraction and data compression. As an unsupervised method, High-Order Singular Value Decomposition (HOSVD) searches for low-rank subspaces such that the low-rank approximation error is minimized. In this paper, we propose a new unsupervised high-order tensor...
It attracts many researchers' attention to find a stereo matching algorithm both accurate and fast. Yoon and Kweon's Adaptive Support-Weight(ASW) method is supposed to be a very successful algorithm in both accuracy and speed. However, it is very time consuming for ASW to take a large number of pixels into consideration for computing a disparity. In this paper, we present a stereo matching algorithm...
The recently proposed two-phase test sample sparse representation (TPTSR) method makes a great contribution to the field of face recognition. Though TPTSR uses a computationally very efficient algorithm, it can obtain a better performance than the well-known sparse representation method. In the first phase of TPTSR, the determined M nearest neighbors for the test sample seem not to be optimal in terms...
A growing number of projects are solving complex computational and scientific tasks by soliciting human feedback through games. Many games with a purpose focus on generating textual tags for images. In contrast, we introduce a new game, Odd Leaf Out, which provides players with an enjoyable and educational game that serves the purpose of identifying misclassification errors in a large database of...
This paper presents a method for recognizing scene categories based on multiple channels of Pyramid Histogram Of Words (PHOW). The main difference among different channels lies in what kind of feature detector/descriptor pair is employed in the framework of Bag-of-Words (BoW) models. This technique works by obtaining the confidence scores of a test image belonging to each possible category based on...
The discretization of a HT space results in the ρ value detection error of a line. This paper addresses the ρ-direction precision improvement by compensating for this error. The mage are vertically or horizontally shifted, and a series peak positions are obtained by applying the standard HT (SHT) on these shifted images. The change of ρ value of a line due to these shifts is studied. On one hand this...
In this paper we propose the integration of computer vision with accelerometry in order to provide a precise localization solution. In terms of accelerometry, our approach makes use of a single off-the-shelf accelerometer on the waist to precisely obtain the velocity of the user. This allows us to calculate the kinetic energy of the person being tracked, and link the accelerometry data with the computer...
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.