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 address the problem of natural flower classification. It is a challenging task due to the non-rigid deformation, illumination changes, and inter-class similarity. We build a large dataset of flower images in the wide with 79 categories and propose a novel framework based on convolutional neural network (CNN) to solve this problem. Unlike other methods using hand-crafted visual features,...
Feature enhancement in an image is to reinforce some exacted features so that it can be used for object classification and detection. As the thermal image is lack of texture and colorful information, the techniques for visual image feature enhancement is insufficient to apply to thermal images. In this paper, we propose a new gradient-based approach for feature enhancement in thermal image. We use...
In this paper, we present a direct application of Support Vector Machine with Augmented Features (AFSVM) for video concept detection. For each visual concept, we learn an adapted classifier by leveraging the pre-learnt SVM classifiers of other concepts. The solution of AFSVM is to re-train the SVM classifier using augmented feature, which concatenates the original feature vector with the decision...
Aim of this paper is to propose a solution to the correspondence problem in multi-camera systems. In these systems, two or more cameras are used to record the same scene from different view points. In this way it is possible to face the problem of occlusions in crowding scenes. In this work an object level motion detection algorithm is used and it is applied to the videos sampled by two cameras. The...
Based on MILES algorithm, we propose a novel multiple instance learning approach which regards visual word dictionary as feature space, and combines segmentation for object detection and extraction in the process of instance classification. This approach uses "Bag of Words" model. The whole image is considered as a multiple instance bag. The visual words that represent the image are regarded...
Recently, in the fields of internet and social networking, the classification and filtering of naked images has been receiving a significant amount of attention. In this paper, we propose a novel naked image classification which can make effective use of semantic features of a naked image. In addition, a novel measurement, termed accumulated distance ratio (ADR), is proposed in order to systematically...
This article shows the improvement of automatic cartoon classification. Two new visual features - color component and color kind based on region segmentation - are proposed. Compared to traditional HSV color histogram and texture, experiment using the two new features can achieve better result, with less dimensions and higher mining efficiency.
Since the challenging visual object categorization has attracted more and more attention in recent years, we present in this paper a novel approach called statistical measures based image modeling for this problem, thus avoiding the major difficulty of the popular “bag-of-visual words” approach which needs to fix a visual vocabulary size. We use a series of statistical measures over our proper region...
Recently, bag of words (BoW) model has led to many significant results in visual object classification. However, due to the limited descriptive and discriminative ability of visual words, the resulting performance of visual object classification is still incomparable to its analogy in text domain, i.e. document categorization. Furthermore, for weakly labeled image data, where we only know whether...
A new visual approach to the surface shape analysis and classification of 3D facial images is presented. It aims to allow the users to visually explore the natural patterns and geometric features of 3D facial scans to provide decision-making information for face classification which can be used for the diagnosis of diseases that exhibit facial characteristics. Using surface feature analysis under...
In this paper, we propose a novel approach to automatically generating, instead of manually designing, discriminative visual features for face detection. The features are composed by multiple local features (e.g., Haar features), and such features can capture not only the local texture information but also their spatial configurations. Therefore, the proposed feature contains rich semantic information...
In order to decrease negative effects brought by the particularity and complexity of imaging environment, and satisfy the real-time need of the underwater task, combined invariant moments are extracted as recognition features. Furthermore, an underwater target recognition system based on neural network which improved by Artificial Fish Swarm Algorithm (AFSA) is proposed. AFSA is of capable of attaining...
Although primates can facilely maintain long-duration tracking of an object without infection of occlusion or other near similar distracters, it remains a challenge for computer vision system. Studies in psychology suggest that the ability of primates to focus selective attention on the spatial properties of an object is necessary to observe object quickly and efficiently while focus selective attention...
This paper proposes an efficient approach for object classification. This method bases on bag-of-features classification framework and extends the limits of it. It applies modified spatial PACT as local feature descriptor, which can efficiently catch image patch's characteristic. In order to address the speed bottleneck of codebook creation, extremely randomized clustering forest is used to create...
Many object detection systems rely on linear classifiers embedded in a sliding-window scheme. Such exhaustive search involves massive computation. Efficient Subwindow Search (ESS) avoids this by means of branch and bound. However, ESS makes an unfavourable memory tradeoff. Memory usage scales with both image size and overall object model size. This risks becoming prohibitive in a multiclass system...
A new challenge in the spam email detection is the emergence of image spam, which consists in embedding the advertising messages into attached images to defeat the conventional text-based anti-spam technologies. New techniques are needed to filter these spam messages. In this paper, we proposed a prototype system to automatically classify an image directly as being spam or ham. The proposed method...
Visual target classification is one of the most important issues addressed in wireless multimedia sensor network (WMSN). This paper proposes a hybrid Gaussian process based classification method to implement binary visual classification (human/nonhuman) in WMSN. Because the computation ability of sensor node in WMSN is strictly limited, target classification is achieved by Gaussian process classifier...
In this paper an implementation of an algorithm for fast visual tracking and localization of mobile agents has been described. Based on an extremely rapid method for visual detection of an object, described localization strategy provides a real time solution suitable for the design of multi-agent control schemes. The agents tracking and localization is carried out through five differently trained...
The purpose of the current investigation was dedicated to the development of an automatic side-scan sonar imagery analysis program for the detection and identification of stationary targets, such as meter-sized concrete artificial reefs, on the sea floor. The major components of the program include: image acquisition; feature extraction; feature classification; target identification; and target properties...
In this paper, we address the problem of detecting and localizing cars in still images. The proposed car detection system is based on a hierarchical feature detector in which the processing units are shunting inhibitory neurons. To reduce the training time and complexity of the network, the shunting inhibitory neurons in the first layer are implemented as directional nonlinear filters, whereas the...
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.