Aleksej Avramovic

Aleksej Avramovic
University of Banja Luka · Faculty of Electrical Engineering

PhD

About

26
Publications
12,048
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
388
Citations
Introduction
Aleksej Avramovic currently works at the Faculty of Electrical Engineering, University of Banja Luka, as an assistant professor. Aleksej does research in Computer Engineering, Biomedical Engineering and Electrical Engineering. Their most recent publication is 'Multispectral scene recognition based on dual convolutional neural networks'.
Additional affiliations
March 2017 - present
University of Banja Luka
Position
  • Professor (Assistant)
Description
  • Lectures on: Elements of electrical engineering, Electrical Measurement, Computer Graphics, etc.
September 2007 - March 2017
University of Banja Luka
Position
  • Research Assistant
Description
  • Lab and audio exercises on: Elements of Electrical Engineering, Electrical Measurements, Circuit Theory, Computer Graphics, etc.
Education
October 2008 - August 2016
University of Belgrade, School of Electrical Engineering
Field of study
  • Image and Signal Processing
September 2002 - July 2007
University of Banja Luka, Faculty of Electrical Engineering
Field of study
  • Electrical Engineering

Publications

Publications (26)
Chapter
Full-text available
Free-flying honeybees can electrostatically collect particles from air in the flying and foraging areas, which in conjunction with organic-based explosive vapor sensing films, placed at the entrance to the beehive, can be used as a passive explosive sensing mechanism. Moreover, bees can be trained to actively search for a smell of explosive. Using...
Article
Full-text available
Recent trends in the development of autonomous vehicles focus on real-time processing of vast amounts of data from various sensors. The data can be acquired using multiple cameras, lidars, ultrasonic sensors, and radars to collect useful information about the state of the traffic and the surroundings. Significant computational power is required to...
Conference Paper
Full-text available
The utilization of honeybees for automatic explosive detection has been tested during the last few decades. Many biological and technical aspects have been considered, in order to understand all the possibilities for honeybee utilization for explosive detection. The scope of this research is an overview of the honey bees tracking capabilities durin...
Conference Paper
Full-text available
In case when higher-order statistic is used for local feature aggregation, final descriptor can have very high dimensionality. In this paper different methods for descriptor dimensionality reduction are evaluated for land-use classification. Concretely, aerial image classification accuracy is compared for the cases when dimensionality reduction is...
Article
Full-text available
We are witnessing daily acquisition of large amounts of aerial and satellite imagery. Analysis of such large quantities of data can be helpful for many practical applications. In this letter, we present an automatic content-based analysis of aerial imagery in order to detect and mark arbitrary objects or regions in high-resolution images. For that...
Article
Colon cancer is one of the deadliest diseases where early detection can prolong life and can increase the survival rates. The early stage disease is typically associated with polyps and mucosa inflammation. The often used diagnostic tools rely on high quality videos obtained from colonoscopy or capsule endoscope. The state-of-the-art image processi...
Conference Paper
Full-text available
The importance of texture for recognition of objects, scenes and events is well-known and used in various computer vision tasks. Until recently, best-performing texture classification algorithms relied on processing of low-level local features and statistical learning based adjustment of classifiers. Convolutional neural networks introduced higher...
Article
Full-text available
Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research...
Article
Full-text available
In this paper we compare different approaches for classification of aerial images based on descrip-tors computed using visible spectral bands as well as additional information obtained from the near infrared band. We also propose different methods for incorporating dimensionality reduction into descriptor extraction process for both global and loca...
Conference Paper
Full-text available
Analysis of colonoscopy, endoscopy and smart pill videos are often used during the diagnostic procedure, so automatic detection of colon polyps, tumors and internal bleeding can be helpful. Automatic video analysis can ease or improve diagnostic process in cases where physician needs to analyze long-duration videos in order to check if there are si...
Article
Full-text available
The squaring function is one of the frequently used arithmetic functions in DSP, so an approximation of the squaring function is acceptable as long as this approximation corrupts the bits that are already corrupted by noise, and does not degrade application׳s performance significantly. Approximation of the squaring function can lead to significant...
Conference Paper
Full-text available
Spatial partitioning is proven to be beneficial for the tasks of image classification, scene categorization and object recognition. The most popular method to capture rough spatial structure of the scene is spatial pyramid matching. However, spatial pyramid matching results in an image representation that is sensitive to rotations. In this research...
Conference Paper
Full-text available
During the last decade, storage of audio data without losses gained on its importance due to increased necessities for high-quality audio reproduction. The second reason can be found in implementation of systems such as speech recognition which can benefit from lossless data. This paper introduces lossless audio compression algorithm based on modul...
Conference Paper
Full-text available
During the years image classification gained important significance in practice, especially in the fields of digital radiology, remote sensing, image retrieval, etc. Typical algorithm for image classification contains descriptor extraction phase, learning phase and testing phase. Testing phase calculates accuracy of the classifier based on predeter...
Article
Many digital signal processing applications demand a huge number of multiplications, which are time, power and area consuming. But input data is often corrupted with noise, which means that a few least significant bits do not carry usable information and do not need to be processed. Therefore, approximate multiplication does not affect application...
Article
Full-text available
In this paper, a novel predictive-based lossless image compression algorithm is presented. Lossless compression must be applied when data acquisition is important and expensive, as in aerial, medical and space imaging. Besides requirements of high compression ratios as much as it is possible, lossless image coding algorithms must be fast. Proposed...
Conference Paper
Full-text available
There are many digital signal processing applications where a shorter time delay of algorithms and efficient implementations are more important than accuracy. Since squaring is one of the fundamental operations widely used in digital signal processing algorithms, approximate squaring is proposed. We present a simple way of approximate squaring that...
Conference Paper
Full-text available
It is often the case in image classification tasks that image descriptors are of high dimensionality. While adding new, independent, features generally improves performance of a classifier, it increases its cost and complexity. In this paper we investigate how descriptor dimensionality reduction techniques, namely principal component analysis and i...
Article
Full-text available
Digital signal processing algorithms often rely heavily on a large number of multiplications, which is both time and power consuming. However, there are many practical solutions to simplify multiplication, like truncated and logarithmic multipliers. These methods consume less time and power but introduce errors. Nevertheless, they can be used in si...
Article
Full-text available
Among the many categories of images that require lossless compression, medical images can be indicated as one of the most important category. Medical image compression with loss impairs of diagnostic value, therefore, there are often legal restrictions on the image compression with losses. Among the common approaches to medical image compression we...
Conference Paper
Full-text available
Digital signal processing algorithms often rely heavily on a large number of multiplications, which is both time and power consuming. However, there are many practical solutions to simplify multiplication, like truncated and logarithmic multipliers. These methods consume less time and power but introduce errors. Nevertheless, they can be used in si...
Article
Full-text available
There are many examples of digital image processing where lossless image compression is necessarily, due to the costs of data acquisition or legal issues, such as aerial and medical imaging. Need for lossless compression of large amounts of data requires speed and efficiency, so predictive methods are chosen before transform-based methods. Predicti...
Article
Full-text available
This paper presents a new multiplier with possibility to achieve an arbitrary accuracy. The multiplier is based upon the same idea of numbers representation as Mitchell's algorithm, but does not use logarithm approximation. The proposed iterative algorithm is simple and efficient, achieving an error percentage as small as required, until the exact...

Network

Cited By

Projects

Projects (3)
Project
The aim of this project is to introduce approximate arithmetic circuits that preserve the required accuracy and significantly reduces the power dissipation and the size of the system’s circuitry.