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.
Microscope examination of Gram stained clinical specimens is used for aiding the diagnosis of patients with infectious diseases. In high volume pathology laboratories, this manual microscopy examination is considered time consuming and labour intensive. Unfortunately, despite the great benefits offered from the application of Computer Aided Diagnosis (CAD) systems, to our knowledge, the highest automation...
In this paper, we propose an optimization scheme aiming at optimal nonlinear data projection, in terms of Fisher ratio maximization. To this end, we formulate an iterative optimization scheme consisting of two processing steps: optimal data projection calculation and optimal class representation determination. Compared to the standard approach employing the class mean vectors for class representation,...
Moving object tracking is a tricky job in computer vision problems. In this approach, the object tracking system relies on the deterministic search of target, whose color content matches a reference histogram model. A simple RGB histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by...
This paper describes a method of cross-domain object categorization, using the concept of domain adaptation. Here, a classifier is trained using samples from the source/auxiliary domain and performance is observed on a set of test samples taken from a different domain, termed as the target domain. To overcome the difference between the two domains, we aim to find a sequence of optimally weighted sub-spaces,...
An efficient algorithm for shadow and highlight removal in nonparametric moving object detection strategies is proposed. By the nonparametric modeling of the variations of the brightness and the chromaticity along the sequences, shadows and highlights are identified. In this way, the quality of the detections is significantly improved.
In traffic video surveillance system, target-level tracking and feature-level tracking are two important areas for research. Therefore, the combination between them is an interesting question. Mean-shift is a traditional target-level tracking algorithm with no adaptation to vehicle scale and orientation change. In order to solve the problem, algorithm combine SURF (speed-up robust feature) feature...
Hashing function is an efficient way for nearest neighbor search in massive dataset because of low storage cost and low computational cost. However, it is NP hard problem to transform data points from the original space into a new hypercube space directly. Typically, the most of hashing methods choose a two-stage strategy. In the first stage, dimension reduction methods are used to project original...
Feature extraction is the most important and essential part in any image matching algorithm. Features are obtained by quantifying the characteristics of an image like illumination, corner, orientation and view angle etc. Image matching techniques consist of features extraction and their matching with other features. The inherent mathematical steps involved in calculation of these features make the...
We present a hardware architecture for the extraction of image feature descriptors, based on a model inspired on the Human Retina. This model comes from an analysis of a recent descriptor extractor, the FREAK (Fast Retina Keypoint) method, which has shown good performance results for different Computer Vision applications. From such analysis we decide the approximations that may be made to the original...
A novel image recognition method based on the improved BDBN (Bilinear Deep Belief Network) model is presented, optimized with a MKL (Multiple Kernel Learning) strategy. All kernel functions in MKL are replaced by hierarchical feature representations, and the number of kernels is set to the number of layers of BDBN. The method is performed on the standard Caltech101 image dataset. The experiments show...
In recent years, the design of classification algorithms, with the aid of information combination methods, has received a considerable attention. In machine vision, in order to overcome the high inter-class variations between the classes of image, various feature descriptors have been designed to be robust to these inter-class variations. However, no single feature can be robust to these variations...
The camera motion during image capturing results in poor and spoiled images. The conventional available methods to remove the camera shake assumes uniform spatial blur on the image, which in most of the cases is not a true assumption. Most of the available methods model the blur image as a convolution of sharp image and a blurring kernel, these results in more number of unknown parameters than known...
Linear discriminant analysis that takes spatial smoothness into account has been developed and widely used in image processing society. However, two questions remain unanswered. First, which is the best way to incorporate the smoothness property of images with linear discriminant analysis? Second, which is the best representation for the smoothness property of images? To answer the first question,...
In this paper we bring forth a novel stroke-based method which is simple and effective to detect texts in natural scenes. We first introduce a general mathematical model to describe character strokes from the perspective of the scale space along with difference of Gaussian filters. Then we detail a text line aggregation approach utilizing the inherent text layout. Afterwards, we set up the whole scheme...
This paper presents a Convolutional Neural Network (CNN) for document image classification. In particular, document image classes are defined by the structural similarity. Previous approaches rely on hand-crafted features for capturing structural information. In contrast, we propose to learn features from raw image pixels using CNN. The use of CNN is motivated by the the hierarchical nature of document...
Classifier fusion methods are usually used to combine multiple classification decisions and generate better classification results than any single classifier. In order to improve object classification accuracy, it is a common method to assign weights to classifiers based on their importance in a multiple decision system. In this paper we put forward a method to weight different classifiers in classifier...
A novel method for anomaly detection in crowded scenes is presented. In our method, a new feature which named Mixture of Kernel Dynamic Texture was used for video representation. The MKDT method jointly models the appearance and dynamics of the scene. Based on this method, the abnormal detection includes temporal detection and spatial detection. The model for normal crowd behavior is based on MKDTs...
The goal of this article is to review the state-of-the-art object tracking techniques developed using mean shift approach and identify the domain in which it can be improved upon. Object tracking, in general, is a challenging problem, which can be achieved in many ways. Of the various possible directions, mean shift is most popular because of its simplicity and applicability to many states of affairs...
We propose an efficient algorithm for motion deblurring with kernel estimation using consecutive images. First we estimate motion vectors between consecutive images using optical flow and RANSAC. Then we calculate the weights of motion vectors. The proposed method is similar to Ben-Ezra's method. The main difference is that we use a single camera for estimating a blur kernel and capturing a blurred...
Spatio-temporal oriented energy features have been proved to be an efficient feature for action recognition. It has satisfied performance on most of public databases. However, the oriented energy features were used as holistic action features for template matching in many literatures. In the paper, we proposed an action representation based on local spatio-temporal oriented energy features, and multiple...
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.