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.
Using spatio-temporal features is popular for action recognition. However, existing methods embed these local features into a global representation. Orders and correlations among local motions of each action are missing. This can make it difficult to distinguish closely related actions. This paper proposes a solution to address this challenge by encoding correlations of movements. Space-time interest...
Brain tumor segmentation from magnetic resonance images is a critical step for early tumor diagnosis and treatment. However, accurate and general segmentation of brain tumor is still a challenging task due to complicated characteristics of brain tumor in magnetic resonance images. To solve this problem, we proposed a novel method for brain tumor segmentation based on features of separated local square...
When pathologists analyze the cytopathological assessment process, they firstly find the optimum focused region by moving the microscope table along the Z axis. Auto-focusing provides a better and more effective imaging by reducing the personality dependence on the microscope system. Various studies have been carried out in the literature to determine the optimum auto-focus function. The aim of the...
Feature ranking from video-wide temporal evolution brings reliable information for complex action recognition. However, a video may contain similar features in the sequence of frames which deliver unnecessary information to the ranking function. This paper proposes a method to improve the rank-pooling strategy which captures the optimized latent structure of the video sequence data. The optimization...
The huge amount of multivariate temporal data that has been produced in several applications demands the creation of appropriate tools for the analysis and pattern characterization of change. This paper introduces a novel image-based representation, named Change Frequency Heatmap (CFH), to encode temporal changes of multivariate numerical data. The method computes histograms of change patterns observed...
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings. In this work, we show how to improve the robustness of embeddings by exploiting independence in ensembles. We divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each...
In the course of the scheduling of a project we always have to face uncertainties in the planned durations of the individual activities. The most frequently used method to handle this situation, is PERT. But PERT offers some detriments like the systematic underestimation of the real risk. Therefore a further development led to the “critical field” approach, which implies the use of Monte Carlo simulation...
AbstractłIn order to enhance the robustness of kernel correlation filters(KCF) in complex background environment, this paper proposes a mean shift method with adaptive local object tracking algorithm. KCF algorithm has speed advantage by using the single template, we introduce the confidence map in the process of the tracking to determine the result of the current frame. If the result of confidence...
Bangla is one of the most widely used languages worldwide. This paper presents an application of image retrieval techniques to automatically judge the aesthetic quality of handwritten Bangla isolated characters. Retrieval techniques are also adapted to give improvement suggestions, with a plan to incorporate the methods in applications which can assist in learning/teaching handwriting. The proposed...
Currently the number of applications where the data generation function is not known has been growing, making necessary the use of non-parametric estimation techniques to describe such model. Therefore, relevant questions emerge regarding the quality of the model that represents some dataset and how to quantify this quality. This article aims to evaluate some of the measurements presented in the literature...
In this paper, we propose an analysis method of drowsiness status of a driver from the opening and closing of eye. For this purpose, eyes, nose and mouth are detected to improve the area of interest using the spatial correlation in the existing Viola-Jones algorithm. Then, histogram equalization is performed for detection at night driving, and drowsiness status of the driver data with the accumulation...
Multi-object tracking is an important computer vision task with wide variety of real-life applications from surveillance and monitoring to biomedical video analysis. Multi-object tracking is a challenging problem due to complications such as partial or full occlusions, factors affecting object appearance, object interaction dynamics, etc. and computational cost. In this paper, we propose a detection-based...
Colorization is a coloring process in the image or video, which is done to provide detail and clarity to the image or video. This study used image gray scale to be colored by matching both color image pixel blocks and grayscale images based on GLCM texture feature (gray level co-occurance matrix) using a sum of absolute difference. Color image blocks are used as templates and grayscale image blocks...
Face recognition task has been used worldwide due to its effectiveness in different disciplines, but because of the complexity of the procedures it is a very difficult task to accurately recognize variations in face images. Large set of feature extraction of face is difficult to handle since the storage and the computation of such dense feature makes the process of recognition more complicated. The...
In the multi-temporal InSAR technique, a deformation map is obtained by arc integration. Therefore, the reliability of an arc solution directly influences the precision of the final result. Many methods have been proposed to estimate arc parameters, but few have evaluated the arc quality. In this study, the influence of phase ambiguity is analyzed and two indicators are defined to identify the arcs...
the task of full-focused digital images construction relates to computational photography and is a process of increasing the information capacity of images obtained via photo- and video-fixation devices with limited optical depth of field. Additional to this task is the question of automatic evaluation of the quality of the images. The most popular non-reference metrics for comparing the quality of...
Hand gesture is one of a powerful means of communication among human. Sign language is an essential and natural expressive mean of communication especially for the deaf people. The article proposes a technique for the recognition of Lao alphabet sign language. The technique of image processing, that is Histogram of Oriented Gradients (HOG), is applied in order to extract characteristics of the hand...
A fast image cryptosystem based on AES is verified in this paper. The plain image is divided into data blocks of size 128 bits. The first block of plain image is permutated by an initial vector. Then, AES in cipher block chaining mode is used to encrypt each block sequentially. The initial vector and cipher image are transmitted to the decryption party through the public information channel. The decryption...
Several situations require the reliability of hand grasp in different relative positions of the shoulder-elbow system, like handling control elements of working equipment, sporting devices for athletes or rehabilitation supports for temporary or permanently lower limbs impaired people. Therefore the paper presents an experimental method of determining the variation of both anatomical and physiological...
This paper presents a detailed modelling, analysis and experimental verification of the noise behaviour for two families of MEMS based inclinometers. These MEMS use two accelerometers in opposing directions to measure inclination. Large sample sizes have been used to ensure reliable statistical results. The results reveal a differential susceptibility of the two sensors to ambient vibrational noise...
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.