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.
Analysis of lace texture images is a challenging problem because the lace is a soft and extensible material and can be easily deformed. This paper investigates a whole system for lace classification. A first step, based on Otsu's segmentation method, allows to remove the background. Then the lace texture is characterized using local binary patterns (LBP). In order to be robust against rotation the...
In this paper, we introduce a new color texture operator for natural texture classification, the Dominant and Minor Sum and Difference Histograms (DM-SDH) descriptor. The proposed approach allows to incorporate both color and texture information in order to enhance the texture discrimination performance. For this purpose, a vectorial representation of the image is used for the descriptor extraction...
In this paper, we propose an improved face recognition approach based on the combination of Vector Quantization (VQ) and Markov Stationary Feature (MSF) which obtain the extended MSF-VQ features from facial sub-regions for face recognition. It can not only utilize the MSF framework to extend the VQ histogram based features with the spatial structure information but can also incorporate more location...
Microcalcifications are very tiny deposits of calcium allocated in the breast tissue. Their gray level is similar to the dense normal breast tissue so its very difficult to differentiate between them. Once detected, its very difficult to between malign end benign microcalcifications. In this paper, we apply a new method to extract features of microcalcifications in order to classify them into malign...
Image segmentation is a basic task in image analysis and understanding and feature extraction is important but difficult. In this paper, we propose an effective feature selection method for color image segmentation which selects a group of mixed color features or channels from some different color spaces according to the principle of the least entropy of pixels frequency histogram distribution. Actually,...
In this paper we propose a method for automatic collimation border rotation angle detection. Algorithm utilizes pooling of image gradients based on their orientations to form a histogram of oriented gradients (HOG) with the goal of determining the dominant gradient orientation in the image as collimation border rotation angle. To avoid accumulation of lower magnitude gradients only a percentage of...
There are several methods to detect arrhythmia by analysis of the heartbeat rate. In practice, doctors follow a specific procedure to interpret if a particular RR interval as a premature heartbeat by analyzing the complex morphology of the ECG signal. We have tested several algorithms to determine premature heartbeats analyzing two neighboring RR intervals using different threshold values with a goal...
The use of micro expressions as a means to understand ones state of mind has received major interest owing to the rapid increase in security threats. The subtle changes that occur on ones face reveals one's hidden intentions. Recognition of these subtle intentions by humans can be challenging as this needs well trained people and is always a time consuming task. Automatic recognition of micro expressions...
This paper proposes a new approach for image classification by combining pyramid match kernel(PMK) with spatial pyramid. Unlike the conventional spatial pyramid matching (SPM) approach which only uses a single-resolution feature vector to represent an image, we use a multi-resolution feature vector to represent an image for SPM. We then calculate the match scores at each resolution of SPM representation...
Given their widespread use for authentication, biometricsystems are a key target for Presentation Attacks (PAs). A presentation attack is an attempt to circumvent a biometricsystem by simulating the trait of an authorized person andpresenting it to the sensor. Social dimension of biometric authenticationnourishes the interest in spoofing attacks. Dependingon motivation and availability of resources,...
Handwriting has been known to be a very strong identifying characteristic of an individual and can be considered a behavioural biometric trait. This has made hand writer identification an important area of research. In this paper, a novel offline writer identification system is proposed using ensemble of multi-scale local ternary pattern histogram features. Features are extracted at multiple scales...
This paper addresses the problem of automatic target recognition (ATR) using inverse synthetic aperture radar (ISAR) images. In this context, we propose a novel approach for feature extraction to describe precisely an aircraft target from ISAR images. In our approach, a visual attention model is adopted to separate the salient regions from the background. After that, the scale invariant feature transform...
SIMPLE (Searching Images with MPEG-7 (& MPEG-7-like) Powered Localized dEscriptors) is a model that proposes the reuse of well-established global descriptors by localizing their description mechanism on image patches located by local features' detectors. Having displayed impressive retrieval results on two different databases, in this paper we extend the family by replacing the originally picked...
One of the challenges of PET/MR is replacing CT-measured attenuation map with a MR-based, especially in the absence of bone signal in MR images. Regular MRI cannot distinguish between different tissue types based on electron density, thus, Zero Echo Time (ZTE) has been used to segment bone, air and soft tissue. In this study, we have evaluated the relationship between bone density measured in CT and...
Segmentation of optic disk (OD) is a very important step in automatic Diabetic Retinopathy screening. In this paper, we presented a robust and novel template matching algorithm for automatic detection of OD in retinal images. The size of OD area depends on camera field of view and image resolution. Based on these criteria we formulated and presented OD size estimation algorithm and it is used to create...
The pattern recognition system for biometric identification, which was presented in this paper, used mathematical and statistical approaches such as Principal Component Analysis as a feature extraction method also Cross Validation and k-nearest neighbor with Euclidean metric distance for the classification method. The proposed recognition system used face and androgenic hair as biometric traits with...
The use of multi-parameter analysis of acoustic emission signals allows identifying destructive processes not only in prestressed concrete elements but also in classical concrete and reinforced concrete members. The analysis is not based on single descriptors but on destructive processes, which may be used to evaluate structural integrity of the elements. Therefore the key question is the minimum...
In this paper, we propose a scheme for identifying the authorship of off-line handwritten documents based on a histogram-based descriptor. The idea of our work is inspired from that of the Local Derivative Patterns (LDP), that has found much success in the application of face recognition. However, to the best of our knowledge, this work is the first of its kind that utilizes them for characterizing...
This competition is aimed at classification of writer demographics from offline handwritten documents using the QUWI database. QUWI is a bilingual database comprising writing samples of same individuals in Arabic and English. This allows evaluating the performance of different systems in a more challenging multi-script environment. This paper presents the details of the competition tasks, the datasets...
In this paper, we propose two novel textural-based features for writer identification: CoHinge and QuadHinge which are based on the spatial and attribute co-occurrence of the Hinge kernel. The CoHinge feature is the joint distribution of the Hinge kernel on two different pixels of writing contours and the QuadHinge feature is the joint distribution of angles and curvature information of contour fragments...
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.