Wyszukiwarka
Filtry
wszystkich: 329
wybranych: 133
Wyniki wyszukiwania dla: emotion recognition, dataset, video annotation
-
Investigating Feature Spaces for Isolated Word Recognition
PublikacjaMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
Detection of Face Position and Orientation Using Depth Data
PublikacjaIn this paper an original approach is presented for real-time detection of user's face position and orientation based only on depth channel from a Microsoft Kinect sensor which can be used in facial analysis on scenes with poor lighting conditions where traditional algorithms based on optical channel may have failed. Thus the proposed approach can support, or even replace, algorithms based on optical channel or based on skeleton...
-
Multi-Stage Video Analysis Framework
PublikacjaThe chapter is organized as follows. Section 2 presents the general structure of the proposed framework and a method of data exchange between system elements. Section 3 is describing the low-level analysis modules for detection and tracking of moving objects. In Section 4 we present the object classification module. Sections 5 and 6 describe specialized modules for detection and recognition of faces and license plates, respectively....
-
Parallelization of video stream algorithms in kaskada platform
PublikacjaThe purpose of this work is to present different techniques of video stream algorithms parallelization provided by the Kaskada platform - a novel system working in a supercomputer environment designated for multimedia streams processing. Considered parallelization methods include frame-level concurrency, multithreading and pipeline processing. Execution performance was measured on four time-consuming image recognition algorithms,...
-
An audio-visual corpus for multimodal automatic speech recognition
Publikacjareview of available audio-visual speech corpora and a description of a new multimodal corpus of English speech recordings is provided. The new corpus containing 31 hours of recordings was created specifically to assist audio-visual speech recognition systems (AVSR) development. The database related to the corpus includes high-resolution, high-framerate stereoscopic video streams from RGB cameras, depth imaging stream utilizing Time-of-Flight...
-
Neural Network Subgraphs Correlation with Trained Model Accuracy
PublikacjaNeural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence...
-
Automatic recognition of males and females among web browser users based on behavioural patterns of peripherals usage
PublikacjaPurpose The purpose of this paper is to answer the question whether it is possible to recognise the gender of a web browser user on the basis of keystroke dynamics and mouse movements. Design/methodology/approach An experiment was organised in order to track mouse and keyboard usage using a special web browser plug-in. After collecting the data, a number of parameters describing the users’ keystrokes, mouse movements and clicks...
-
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublikacjaIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Application of autoencoder to traffic noise analysis
PublikacjaThe aim of an autoencoder neural network is to transform the input data into a lower-dimensional code and then to reconstruct the output from this code representation. Applications of autoencoders to classifying sound events in the road traffic have not been found in the literature. The presented research aims to determine whether such an unsupervised learning method may be used for deploying classification algorithms applied to...
-
Noise profiling for speech enhancement employing machine learning models
PublikacjaThis paper aims to propose a noise profiling method that can be performed in near real-time based on machine learning (ML). To address challenges related to noise profiling effectively, we start with a critical review of the literature background. Then, we outline the experiment performed consisting of two parts. The first part concerns the noise recognition model built upon several baseline classifiers and noise signal features...
-
Driver’s Condition Detection System Using Multimodal Imaging and Machine Learning Algorithms
PublikacjaTo this day, driver fatigue remains one of the most significant causes of road accidents. In this paper, a novel way of detecting and monitoring a driver’s physical state has been proposed. The goal of the system was to make use of multimodal imaging from RGB and thermal cameras working simultaneously to monitor the driver’s current condition. A custom dataset was created consisting of thermal and RGB video samples. Acquired data...
-
Improving methods for detecting people in video recordings using shifting time-windows
PublikacjaWe propose a novel method for improving algorithms which detect the presence of people in video sequences. Our focus is on algorithms for applications which require reporting and analyzing all scenes with detected people in long recordings. Therefore one of the target qualities of the classification result is its stability, understood as a low number of invalid scene boundaries. Many existing methods process images in the recording...
-
Thermal Image Processing for Respiratory Estimation from Cubical Data with Expandable Depth
PublikacjaAs healthcare costs continue to rise, finding affordable and non-invasive ways to monitor vital signs is increasingly important. One of the key metrics for assessing overall health and identifying potential issues early on is respiratory rate (RR). Most of the existing methods require multiple steps that consist of image and signal processing. This might be difficult to deploy on edge devices that often do not have specialized...
-
A comparative study of English viseme recognition methods and algorithms
PublikacjaAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector construction...
-
A comparative study of English viseme recognition methods and algorithm
PublikacjaAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector...
-
Controlling computer by lip gestures employing neural network
PublikacjaResults 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....
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublikacjaThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...
-
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-Learned Features
PublikacjaNematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed...
-
The Hough transform in the classification process of inland ships
PublikacjaThis article presents an analysis of the possibilities of using image processing methods for feature extraction that allows kNN classification based on a ship’s image delivered from an on-water video surveillance system. The subject of the analysis is the Hough transform which enables the detection of straight lines in an image. The recognized straight lines and the information about them serve as features in the classification...
-
Real-Time Gastrointestinal Tract Video Analysis on a Cluster Supercomputer
PublikacjaThe article presents a novel approach to medical video data analysis and recognition. Emphasis has been put on adapting existing algorithms detecting le- sions and bleedings for real time usage in a medical doctor's office during an en- doscopic examination. A system for diagnosis recommendation and disease detec- tion has been designed taking into account the limited mobility of the endoscope and the doctor's requirements. The...
-
Real-Time Bleeding Detection in Gastrointestinal Tract Endoscopic Examinations Video
PublikacjaThe article presents a novel approach to medical video data analysis and recognition of bleedings. Emphasis has been put on adapting pre-existing algorithms dedicated to the detection of bleedings for real-time usage in a medical doctor’s office during an endoscopic examination. A real-time system for analyzing endoscopic videos has been designed according to the most significant requirements of medical doctors. The main goal of...
-
Concurrent Video Denoising and Deblurring for Dynamic Scenes
PublikacjaDynamic scene video deblurring is a challenging task due to the spatially variant blur inflicted by independently moving objects and camera shakes. Recent deep learning works bypass the ill-posedness of explicitly deriving the blur kernel by learning pixel-to-pixel mappings, which is commonly enhanced by larger region awareness. This is a difficult yet simplified scenario because noise is neglected when it is omnipresent in a wide...
-
Toward Robust Pedestrian Detection With Data Augmentation
PublikacjaIn 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...
-
Identification of Emotional States Using Phantom Miro M310 Camera
PublikacjaThe purpose of this paper is to present the possibilities associated with the use of remote sensing methods in identifying human emotional states, and to present the results of the research conducted by the authors in this field. The studies presented involved the use of advanced image analysis to identify areas on the human face that change their activity along with emotional expression. Most of the research carried out in laboratories...
-
Audio content analysis in the urban area telemonitoring system
PublikacjaArtykuł przedstawia możliwości rozwinięcie monitoringu miejskiego o automatyczną analizę dźwięku. Przedstawiono metody parametryzacji dźwięku, które możliwe są do zastosowania w takim systemie oraz omówiono aspekty techniczne implementacji. W kolejnej części przedstawiono system decyzyjny oparty na drzewach zastosowany w systemie. System ten rozpoznaje dźwięki niebezpieczne (strzał, rozbita szyba, krzyk) wśród dźwięków zarejestrowanych...
-
Speech Analytics Based on Machine Learning
PublikacjaIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Enabling Deeper Linguistic-based Text Analytics – Construct Development for the Criticality of Negative Service Experience
PublikacjaSignificant progress has been made in linguistic-based text analytics particularly with the increasing availability of data and deep learning computational models for more accurate opinion analysis and domain-specific entity recognition. In understanding customer service experience from texts, analysis of sentiments associated with different stages of the service lifecycle is a useful starting point. However, when richer insights...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublikacjaIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublikacjaIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
CNN-CLFFA: Support Mobile Edge Computing in Transportation Cyber Physical System
PublikacjaIn the present scenario, the transportation Cyber Physical System (CPS) improves the reliability and efficiency of the transportation systems by enhancing the interactions between the physical and cyber systems. With the provision of better storage ability and enhanced computing, cloud computing extends transportation CPS in Mobile Edge Computing (MEC). By inspecting the existing literatures, the cloud computing cannot fulfill...
-
Genetic programming extension to APF-based monocular human body pose estimation
PublikacjaNew method of the human body pose estimation based on a single camera 2D observation is presented, aimed at smart surveillance related video analysis and action recognition. It employs 3D model of the human body, and genetic algorithm combined with annealed particle filter for searching the global optimum of model state, best matching the object's 2D observation. Additionally, new motion cost metric is employed, considering current...
-
How do responsible universities perceive their social engagement? In search of signs of Creating Shared Value by the University
PublikacjaObjectives: University social responsibility still lacks legitimisation and is perceived as a burden that hinders academics from doing research and teaching. Creating Shared Value by the University may serve as a tool to motivate universities to engage in initiatives for society, as this is beneficial for both parties. Yet, some researchers perceive the creation of economic value as inappropriate for academia. Thus, it was interesting...
-
Detecting Apples in the Wild: Potential for Harvest Quantity Estimation
PublikacjaKnowing the exact number of fruits and trees helps farmers to make better decisions in their orchard production management. The current practice of crop estimation practice often involves manual counting of fruits (before harvesting), which is an extremely time-consuming and costly process. Additionally, this is not practicable for large orchards. Thanks to the changes that have taken place in recent years in the field of image...