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 order to meet the requirement of autonomous navigation in deep space exploration, this paper presents a novel visual navigation method. The visual navigation algorithm based on single feature matching is a common visual method to calculate the attitude and position of a lander. However, the algorithm based on feature line matching or crater matching is great limited due to the feature line extracted...
Aiming at the problem that traditional Meanshift tracking algorithm cannot track target accurately. When target is occluded or background interferences appear, a new tracking algorithm based on features matching and motion detection predicting is proposed. The new algorithm extracts features of target by the SIFT algorithm to realize the location. The original iteration position is estimated by the...
Active Learning Method (ALM) is a fuzzy learning method and is inspired by the approach of human's brain toward understanding complicated problems. In this algorithm, a Multi-Input Single-Output system is modeled by some Single-Input Single-Output sub-systems. Each sub-model tries to capture the input-output relationship of each sub-system on a plane called IDS plane. The output of the original system...
Grey Wolf Optimizer (GWO) is a new meta-heuristic optimization. It is inspired by the unique predator strategy and organization system of grey wolves. Since the GWO algorithm is easy to fall into local optimum especially when it is used in the high-dimensional data, an improved GWO algorithm combined with Cuckoo Search (CS) is proposed in this paper. By introducing the global-search ability of CS...
Aiming at the problem that the semantic explanation of the existing topic model is poor and the accuracy is not high, a semi-supervised topic learning and representation method based on association rules and metadata is proposed. First, we used the metadata as a priori knowledge to guide the topic learning, and got the probability distribution of the term in the document. Then, we got the frequent...
Fraudulent activities in financial institutes can break the economic system of the country. These activities can be identified using clustering and classification algorithms. Effectiveness of these algorithms depend on quality of the input data. Moreover, financial data comes from various sources and forms such as financial statements, stakeholders activities and others. This data from various sources...
With development of medical image processing, more and more cancers are diagnosed and treated with assistance of computer, especially lung cancer. Extracting lung from CT image series is usually the first step. Hundreds of CT images slow down the processing. As to clinical applications, the accuracy and efficiency is crucial. We proposed and realized an auto-segmentation of lung in CT image series...
Herlev dataset consists of 7 cervical cell classes, i.e. superficial squamous, intermediate squamous, columnar, mild dysplasia, moderate dysplasia, severe dysplasia, and carcinoma in situ is considered. The dataset will be tested to classify two classes, consisting of normal and abnormal cells. Seven different cell types will be classified to separate the cells into 7 classes which are 3 normal cell...
Accurate recognition of human actions is essential to many health-care, entertainment, and human-computer interface applications. However, the achievable accuracy depends on a variety of parameters for the various stages of recognition, including sensing, feature extraction, and classification. In this paper, we quantitatively evaluate the classification accuracy for varying sensing rates, sensor...
Recognition of human actions by using wearable sensors has become an important research field. Segmentation to sensor data is a vital issue in reconstructing and understanding human daily actions, and strongly affects the accuracy of human actions recognition. Traditional online segmentation approaches are mostly designed for one-dimensional sensor data, which greatly limits these approaches to multi-dimensional...
Image steganalysis is to discriminate innocent images and those suspected images with hidden messages. In this paper, we propose a unified Convolutional Neural Network (CNN) model for this task. In order to reliably detect modern steganographic algorithms, we design the proposed model from two aspects. For the first, different from existing CNN based steganalytic algorithms that use a predefined highpass...
An increasing number of people are using dating websites to search for their life partners. This leads to the curiosity of how attractive a specific person is to the opposite gender on an average level. We propose a novel algorithm to evaluate people's objective attractiveness based on their interactions with other users on the dating websites and implement machine learning algorithms to predict their...
To extract key topics from news articles, this paper researches into a new method to discover an efficient way to construct text vectors and improve the efficiency and accuracy of document clustering based on Word2Vec model. This paper proposes a novel algorithm, which combines Jaccard similarity coefficient and inverse dimension frequency to calculate the importance degree between each dimension...
Stereo correspondence is one of the most important steps in binocular stereovision. It consists feature point extraction and image matching. In order to solve the problems of bad anti-noise performance and low accuracy of image matching in Scale Invariant Feature Transform (SIFT) algorithm, an optimized matching method based on local feature algorithm with Speeded-up Robust Feature (SURF) is proposed...
Millions of comments are available on forums, Facebook, Tweeter, YouTube etc. Proper analysis of these huge comments can lead to solve many social, economic, political, business related questions which otherwise are difficult to understand and analyse. Proposed system explores the statistical approach for sentiment analysis of product reviews using expectation maximization algorithm. Systematic mathematical...
Inspired by the importance of self-representation and structure-preserving ability of features, in this paper, we propose a novel unsupervised feature selection algorithm named structure-preserving non-negative feature self-representation (SPNFSR). In this algorithm, each feature in high-dimensional data can be represented by the linear combination of other features. Then, to exploit the structure-preserving...
In order to meet the requirement of high-compact and hard-real-time outdoor navigation system, to solve the problem of invalid satellite navigation during GPS-denied period, a multi-sensors integrated navigation system is designed in this study. The system is fused with accelerometer, gyroscope, satellite receiver, binocular vision camera and barometer. The Kalman Filter, which is designed for model...
Object clustering is a very challenging unsupervised learning problem in machine learning and pattern recognition. In this paper, we will study visual object pattern clustering problem by combining the k-means clustering algorithm and the binary sketch templates, which quantify each image by a vector of indicators showing that a sketch at certain location, scale, and orientation exist or not. This...
Image Registration has investigated in many researches in recent years. It is an important preprocessing step in a variety of applications such as medical images, super resolution and remote sensing. Generally, dense image registration requires several transformations and deformations such as contrast changing, scaling, rotation and displacement. However, in most recent proposed methods, only some...
In the traditional abandoned object detection(AOD for short) researches, the monitoring equipment is stationary which is limited in practice. In this paper, a novel abandoned object detection based on tachograph is proposed. Firstly, we use the Harris-SIFT features and particle filter to achieve object tracking. After that, the VIBE algorithm is applied to detect the abandoned object with background...
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.