Search
Filters
total: 520
Search results for: image segmentation, computer vision, deep learning
-
Patryk Ziółkowski dr inż.
PeoplePatryk Ziolkowski is a graduate of the Faculty of Civil and Environmental Engineering at the Gdansk University of Technology, specializing in Building and Engineering Structures. He works as an Assistant Professor at the Department of Engineering Structures. He participated in international projects, including projects for the Ministry of Transportation of the State of Alabama (2015), he is also the winner of a grant from the Kosciuszko...
-
Efkleidis Katsaros
PeopleEfklidis Katsaros received the B.Sc. degree in mathematics from the Aristotle University of Thessaloniki, Greece, in 2016, and the M.Sc. degree (cum laude) in data science: statistical science from Leiden University, The Netherlands, in 2019. He is currently pursuing the Ph.D. degree in deep video multi-task learning with the Department of Biomedical Engineering, Gdańsk University of Technology, Poland. Since 2020, he has been...
-
Human Feedback and Knowledge Discovery: Towards Cognitive Systems Optimization
PublicationCurrent computer vision systems, especially those using machine learning techniques are data-hungry and frequently only perform well when dealing with patterns they have seen before. As an alternative, cognitive systems have become a focus of attention for applications that involve complex visual scenes, and in which conditions may vary. In theory, cognitive applications uses current machine learning algorithms, such as deep learning,...
-
Human-Computer Interface Based on Visual Lip Movement and Gesture Recognition
PublicationThe multimodal human-computer interface (HCI) called LipMouse is presented, allowing a user to work on a computer using movements and gestures made with his/her mouth only. Algorithms for lip movement tracking and lip gesture recognition are presented in details. User face images are captured with a standard webcam. Face detection is based on a cascade of boosted classifiers using Haar-like features. A mouth region is located in...
-
Grzegorz Szwoch dr hab. inż.
PeopleGrzegorz Szwoch was born in 1972 in Gdansk. In 1991-1996 he studied at the Technical University of Gdansk. In 1996 he graduated as a student from the Sound Engineering Department. His thesis was related to physical modeling of musical instruments. Since that time he has been a member of the research staff at the Multimedia Systems Department as a PhD student (1996-2001), Assistant (2001-2004), Assistant professor (2004-2020) and...
-
MEAN SHIFT BASED SEGMENTATION FOR BLEEDING REGIONS IN ENDOSCOPIC VIDEOS
PublicationWith a set of 38 manually marked bleeding regions form endoscopic videos, the authors attempted to find an optimal image segmentation method for reproducing doctor’s markup. Mean shift segmentation combined with HSV histogram segmentation were used as a segmentation method, which was then optimized by tuning the parameters of the method using global optimization algorithm. A target function for measuring the quality of segmentation was...
-
Reinforcement Learning Algorithm and FDTD-based Simulation Applied to Schroeder Diffuser Design Optimization
PublicationThe aim of this paper is to propose a novel approach to the algorithmic design of Schroeder acoustic diffusers employing a deep learning optimization algorithm and a fitness function based on a computer simulation of the propagation of acoustic waves. The deep learning method employed for the research is a deep policy gradient algorithm. It is used as a tool for carrying out a sequential optimization process the goal of which is...
-
Designing acoustic scattering elements using machine learning methods
PublicationIn the process of the design and correction of room acoustic properties, it is often necessary to select the appropriate type of acoustic treatment devices and make decisions regarding their size, geometry, and location of the devices inside the room under the treatment process. The goal of this doctoral dissertation is to develop and validate a mathematical model that allows predicting the effects of the application of the scattering...
-
Deep neural networks for data analysis
e-Learning CoursesThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Ensembling noisy segmentation masks of blurred sperm images
PublicationBackground: Sperm tail morphology and motility have been demonstrated to be important factors in determining sperm quality for in vitro fertilization. However, many existing computer-aided sperm analysis systems leave the sperm tail out of the analysis, as detecting a few tail pixels is challenging. Moreover, some publicly available datasets for classifying morphological defects contain images limited only to the sperm head. This...
-
WEB-CAM AS A MEANS OF INFORMATION ABOUT EMOTIONAL ATTEMPT OF STUDENTS IN THE PROCESS OF DISTANT LEARNING
PublicationNew methods in education become more popular nowadays. Distant learning is a good example when teacher and student meet in virtual environment. Because interaction in this virtual world might be complicated it seems necessary to assure as much methods of conforming that student is still engaged in the process of learning as it is possible. We would like to present assumption that by means of web-cam we will be able to track facial...
-
Vident-lab: a dataset for multi-task video processing of phantom dental scenes
Open Research DataWe introduce a new, asymmetrically annotated dataset of natural teeth in phantom scenes for multi-task video processing: restoration, teeth segmentation, and inter-frame homography estimation. Pairs of frames were acquired with a beam splitter. The dataset constitutes a low-quality frame, its high-quality counterpart, a teeth segmentation mask, and...
-
International Machine Vision and Image Processing Conference
Conferences -
Assessment of particular abdominal aorta section extraction from contrast-enhanced computed tomography angiography
PublicationThe aim of this work is to improve the accuracy of extraction of a particular abdominal aorta section and to reduce the distortion in three-dimensional Computed Tomography Angiography (CTA) images. Imaging modality and quality plays crucial role in the medical diagnostic process, thus ensuring high quality of images is essential at every stage of acquisition and processing.Noise is defined as a disturbance of the image quality...
-
THE ROLE OF INFERENCE IN MOBILE MEDICAL APPLICATION DESIGN
PublicationIn the early 21st century, artificial intelligence began to be used to process medical information. However, before this happened, predictive models used in healthcare could only consider a limited number of variables, and only in properly structured and organised medical data. Today, advanced tools based on machine learning techniques - which, using artificial neural networks, can explore extremely complex relationships - and...
-
The influence of image masks definition onsegmentation results of histopathological imagesusing convolutional neural network
PublicationAbstract—In the era of collecting large amounts of tissue materials, assisting the work of histopathologists with various electronic and information IT tools is an undeniable fact. The traditional interaction between a human pathologist and the glass slide is changing to interaction between an AI pathologist with a whole slide images. One of the important tasks is the segmentation of objects (e.g. cells) in such images. In this...
-
Semantic segmentation training using imperfect annotations and loss masking
PublicationOne of the most significant factors affecting supervised neural network training is the precision of the annotations. Also, in a case of expert group, the problem of inconsistent data annotations is an integral part of real-world supervised learning processes, well-known to researchers. One practical example is a weak ground truth delineation for medical image segmentation. In this paper, we have developed a new method of accurate...
-
DevEmo—Software Developers’ Facial Expression Dataset
PublicationThe COVID-19 pandemic has increased the relevance of remote activities and digital tools for education, work, and other aspects of daily life. This reality has highlighted the need for emotion recognition technology to better understand the emotions of computer users and provide support in remote environments. Emotion recognition can play a critical role in improving the remote experience and ensuring that individuals are able...
-
Smart Karyotyping Image Selection Based on Commonsense Knowledge Reasoning
PublicationKaryotyping requires chromosome instances to be segmented and classified from the metaphase images. One of the difficulties in chromosome segmentation is that the chromosomes are randomly positioned in the image, and there is a great chance for chromosomes to be touched or overlap with others. It is always much easier for operators and automatic programs to tackle images without overlapping chromosomes than ones with largely overlapped...
-
Impact of Visual Image Quality on Lymphocyte Detection Using YOLOv5 and RetinaNet Algorithms
PublicationLymphocytes, a type of leukocytes, play a vital role in the immune system. The precise quantification, spatial arrangement and phenotypic characterization of lymphocytes within haematological or histopathological images can serve as a diagnostic indicator of a particular lesion. Artificial neural networks, employed for the detection of lymphocytes, not only can provide support to the work of histopathologists but also enable better...
-
Assessing the attractiveness of human face based on machine learning
PublicationThe attractiveness of the face plays an important role in everyday life, especially in the modern world where social media and the Internet surround us. In this study, an attempt to assess the attractiveness of a face by machine learning is shown. Attractiveness is determined by three deep models whose sum of predictions is the final score. Two annotated datasets available in the literature are employed for training and testing...
-
Instance segmentation of stack composed of unknown objects
PublicationThe article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer,...
-
Controlling computer by lip gestures employing neural network
PublicationResults of experiments regarding lip gesture recognition with an artificial neural network are discussed. The neural network module forms the core element of a multimodal human-computer interface called LipMouse. This solution allows a user to work on a computer using lip movements and gestures. A user face is detected in a video stream from a standard web camera using a cascade of boosted classifiers working with Haar-like features....
-
Hazard Control in Industrial Environments: A Knowledge-Vision-Based Approach
PublicationThis paper proposes the integration of image processing techniques (such as image segmentation, feature extraction and selection) and a knowledge representation approach in a framework for the development of an automatic system able to identify, in real time, unsafe activities in industrial environments. In this framework, the visual information (feature extraction) acquired from video-camera images and other context based gathered...
-
Olgun Aydin Dr
PeopleOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Senior Data Scientist in PwC Poland, gives lectures in Gdansk University of Technology in Poland and member of WhyR? Foundation. Olgun is a very big fan of R and author of the book called “R Web Scraping Quick Start Guide” , two video courses are called “Deep Dive into Statistical Modelling using R” and “Applied Machine Learning and Deep...
-
Predicting emotion from color present in images and video excerpts by machine learning
PublicationThis work aims at predicting emotion based on the colors present in images and video excerpts using a machine-learning approach. The purpose of this paper is threefold: (a) to develop a machine-learning algorithm that classifies emotions based on the color present in an image, (b) to select the best-performing algorithm from the first phase and apply it to film excerpt emotion analysis based on colors, (c) to design an online survey...
-
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublicationWith the technology advancements in smart home sector, voice control and automation are key components that can make a real difference in people's lives. The voice recognition technology market continues to involve rapidly as almost all smart home devices are providing speaker recognition capability today. However, most of them provide cloud-based solutions or use very deep Neural Networks for speaker recognition task, which are...
-
European Conference on Computer Vision
Conferences -
Asian Conference on Computer Vision
Conferences -
Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
PublicationMy doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.
-
Vident-synth: a synthetic intra-oral video dataset for optical flow estimation
Open Research DataWe introduce Vident-synth, a large dataset of synthetic dental videos with corresponding ground truth forward and backward optical flows and occlusion masks. It can be used for:
-
Smart Knowledge Engineering for Cognitive Systems: A Brief Overview
PublicationCognition in computer sciences refers to the ability of a system to learn at scale, reason with purpose, and naturally interact with humans and other smart systems, such as humans do. To enhance intelligence, as well as to introduce cognitive functions into machines, recent studies have brought humans into the loop, turning the system into a human–AI hybrid. To effectively integrate and manipulate hybrid knowledge, suitable technologies...
-
Optymalizacja zasobów chmury obliczeniowej z wykorzystaniem inteligentnych agentów w zdalnym nauczaniu
PublicationRozprawa dotyczy optymalizacji zasobów chmury obliczeniowej, w której zastosowano inteligentne agenty w zdalnym nauczaniu. Zagadnienie jest istotne w edukacji, gdzie wykorzystuje się nowoczesne technologie, takie jak Internet Rzeczy, rozszerzoną i wirtualną rzeczywistość oraz deep learning w środowisku chmury obliczeniowej. Zagadnienie jest istotne również w sytuacji, gdy pandemia wymusza stosowanie zdalnego nauczania na dużą skalę...
-
imPlatelet classifier: image‐converted RNA biomarker profiles enable blood‐based cancer diagnostics
PublicationLiquid biopsies offer a minimally invasive sample collection, outperforming traditional biopsies employed for cancer evaluation. The widely used material is blood, which is the source of tumor-educated platelets. Here, we developed the imPlatelet classifier, which converts RNA-sequenced platelet data into images in which each pixel corresponds to the expression level of a certain gene. Biological knowledge from the Kyoto Encyclopedia...
-
Computer Supported Collaborative Learning
Conferences -
Vehicle detector training with minimal supervision
PublicationRecently many efficient object detectors based on convolutional neural networks (CNN) have been developed and they achieved impressive performance on many computer vision tasks. However, in order to achieve practical results, CNNs require really large annotated datasets for training. While many such databases are available, many of them can only be used for research purposes. Also some problems exist where such datasets are not...
-
Book Review
PublicationActing over the last three decades as an Editor and Associate Editor for a number of international journals in the general area of cybernetics and AI, as well as a Chair and Co-Chair of numerous conferences in this field, I have had the exciting opportunity to closely witness and to be actively engaged in the stimulating research area of machine learning and its important augmentation with deep learning techniques and technologies. From...
-
Monitoring wizyjny w systemach zabezpieczenia transportu wodnego. Koncepcja implementacyjna
PublicationW artykule autorzy przedstawiają koncepcję zastosowania własnych badań nad pomiarem prędkości przepływu cieczy do zastosowań praktycznych w pomiarach przepływu wody w kanałach otwartych i rzekach. Jako narzędzie pomiarowe wykorzystują zestaw aparatów synchronicznych, które rejestrują indykatory przepływu znajdujące się na powierzchni analizowanej cieczy. Aparat matematyczny przedstawiony w rozwiązaniu sprowadza się do stosowania...
-
Pupil detection supported by Haar feature based cascade classifier for two-photon vision examinations
PublicationThe aim of this paper is to present a novel method, called Adaptive Edge Detection (AED), of extraction of precise pupil edge coordinates from eye image characterized by reflections of external illuminators and laser beams. The method is used for monitoring of pupil size and position during psychophysical tests of two-photon vision performed by dedicated optical set-up. Two-photon vision is a new phenomenon of perception of short-pulsed...
-
A PROPOSAL FOR ONE-IMAGE PHOTOGRAMMETRY SYSTEM FOR MEASURING THE CLEARANCE DISTANCE. CASE STUDY
PublicationMeasurement of the clearance distance (both in the context of the rail and road) is one of the current and increasingly discussed topics in the context of photogrammetric and image processing (computer vision) methods. The article presents a description of a simple and rapid method of measure the clearance distance between the obstacles by using one-image photogrammetry. The proposed method was tested for the railway, tram and...
-
Toward Robust Pedestrian Detection With Data Augmentation
PublicationIn this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
A VISION-BASED UNMANNED AERIAL VEHICLE NAVIGATION METHOD
PublicationThe satellite navigation systems are the main position sources for unmanned aerial vehicles (UAVs). This fact limits the area of UAVs operation to the places where radio signals is visible for a satellite navigation system receiver, mounted on the vehicle-outdoor navigation. Closed spaced are unavailable for vehicles which navigation is based on global satellite navigation systems (GNSS). Miniature UAV (MiniUAV) is able to operate...
-
Visual Content Representation for Cognitive Systems: Towards Augmented Intelligence
PublicationCognitive Vision Systems have gained significant attention from academia and industry during the past few decades. One of the main reasons behind this interest is the potential of such technologies to revolutionize human life since they intend to work robustly under complex visual scenes (which environmental conditions may vary), adapting to a comprehensive range of unforeseen changes, and exhibiting prospective behavior. The combination...
-
International Conference on Computer Vision Systems
Conferences -
International Conference on Computer Vision and Graphics
Conferences -
IEEE Workshop on Applications of Computer Vision
Conferences -
IEEE International Conference on Computer Vision
Conferences -
Evaluating Accuracy of Respiratory Rate Estimation from Super Resolved Thermal Imagery
PublicationNon-contact estimation of Respiratory Rate (RR) has revolutionized the process of establishing the measurement by surpassing some issues related to attaching sensors to a body, e.g. epidermal stripping, skin disruption and pain. In this study, we perform further experiments with image processing-based RR estimation by using various image enhancement algorithms. Specifically, we employ Super Resolution (SR) Deep Learning (DL) network...
-
Medical Image Dataset Annotation Service (MIDAS)
PublicationMIDAS (Medical Image Dataset Annotation Service) is a custom-tailored tool for creating and managing datasets either for deep learning, as well as machine learning or any form of statistical research. The aim of the project is to provide one-fit-all platform for creating medical image datasets that could easily blend in hospital's workflow. In our work, we focus on the importance of medical data anonimization, discussing the...