Jozef Goga

Bio: Jozef Goga is an academic researcher from Slovak University of Technology in Bratislava. The author has contributed to research in topics: Convolutional neural network & Artificial intelligence. The author has an hindex of 3, co-authored 7 publications receiving 18 citations.

A survey of iris datasets

Abstract: Research on human eye image processing and iris recognition has grown steadily over the last few decades. It is important for researchers interested in this discipline to know the relevant datasets in this area to (i) be able to compare their results and (ii) speed up their research using existing datasets rather than creating custom datasets. In this paper, we provide a comprehensive overview of the existing publicly available datasets and their popularity in the research community using a bibliometric approach. We reviewed 158 different iris datasets referenced from the 689 most relevant research articles indexed by the Web of Science online library. We categorized the datasets and described the properties important for performing relevant research. We provide an overview of the databases per category to help investigators conducting research in the domain of iris recognition to identify relevant datasets.

Detection of Diabetic Retinopathy Using Pretrained Deep Neural Networks

Abstract: This paper is focused on automatic detection and classification of diabetic retinopathy symptoms using a pretrained convolutional neural network (CNN). We obtained a dataset of retinal images from EyePacs Diabetic Retinopathy Database, which was divided into five categories based on grade of retinal damage [1]. Images from this database were preprocessed and used as training and testing data. We compared the classification accuracy of three different pretrained neural networks and selected the most successful one.

Hand gesture recognition using 3D sensors

Abstract: The aim of this work is to investigate the problem of static hand gesture recognition using Kinect v2 depth sensor. We have dealt not only with the theory of recognition itself, but also with the use of depth sensors and the latest approaches in this field. We have successfully applied different convolutional neural network architectures to this classification problem and evaluated the impact of kernel size on the recognition score. By creating our own static gesture database, we have gained an objective way of comparing each test method.

Support vector machine and deep-learning object detection for localisation of hard exudates.

Abstract: Hard exudates are one of the main clinical findings in the retinal images of patients with diabetic retinopathy. Detecting them early significantly impacts the treatment of underlying diseases; therefore, there is a need for automated systems with high reliability. We propose a novel method for identifying and localising hard exudates in retinal images. To achieve fast image pre-scanning, a support vector machine (SVM) classifier was combined with a faster region-based convolutional neural network (faster R-CNN) object detector for the localisation of exudates. Rapid pre-scanning filtered out exudate-free samples using a feature vector extracted from the pre-trained ResNet-50 network. Subsequently, the remaining samples were processed using a faster R-CNN detector for detailed analysis. When evaluating all the exudates as individual objects, the SVM classifier reduced the false positive rate by 29.7% and marginally increased the false negative rate by 16.2%. When evaluating all the images, we recorded a 50% reduction in the false positive rate, without any decrease in the number of false negatives. The interim results suggested that pre-scanning the samples using the SVM prior to implementing the deep-network object detector could simultaneously improve and speed up the current hard exudates detection method, especially when there is paucity of training data.

Comparison of Algorithms for Dynamic Hand Gesture Recognition

Abstract: The aim of this work is to compare different algorithms for dynamic hand gesture recognition using the Kinect v2 sensor. We have developed an application that has implemented algorithms such as dynamic time warping algorithm, hidden Markov models, long short-term memory network and convolutional neural networks. To test and compare the mentioned algorithms, a simple database was created. Using our own database we have gained an objective way of comparing these algorithms.

A systematic review on hand gesture recognition techniques, challenges and applications.

Abstract: Background With the development of today's technology, and as humans tend to naturally use hand gestures in their communication process to clarify their intentions, hand gesture recognition is considered to be an important part of Human Computer Interaction (HCI), which gives computers the ability of capturing and interpreting hand gestures, and executing commands afterwards. The aim of this study is to perform a systematic literature review for identifying the most prominent techniques, applications and challenges in hand gesture recognition. Methodology To conduct this systematic review, we have screened 560 papers retrieved from IEEE Explore published from the year 2016 to 2018, in the searching process keywords such as "hand gesture recognition" and "hand gesture techniques" have been used. However, to focus the scope of the study 465 papers have been excluded. Only the most relevant hand gesture recognition works to the research questions, and the well-organized papers have been studied. Results The results of this paper can be summarized as the following; the surface electromyography (sEMG) sensors with wearable hand gesture devices were the most acquisition tool used in the work studied, also Artificial Neural Network (ANN) was the most applied classifier, the most popular application was using hand gestures for sign language, the dominant environmental surrounding factor that affected the accuracy was the background color, and finally the problem of overfitting in the datasets was highly experienced. Conclusions The paper will discuss the gesture acquisition methods, the feature extraction process, the classification of hand gestures, the applications that were recently proposed, the challenges that face researchers in the hand gesture recognition process, and the future of hand gesture recognition. We shall also introduce the most recent research from the year 2016 to the year 2018 in the field of hand gesture recognition for the first time.

ResNet Based Deep Features and Random Forest Classifier for Diabetic Retinopathy Detection.

Abstract: Diabetic retinopathy, an eye disease commonly afflicting diabetic patients, can result in loss of vision if prompt detection and treatment are not done in the early stages. Once the symptoms are identified, the severity level of the disease needs to be classified for prescribing the right medicine. This study proposes a deep learning-based approach, for the classification and grading of diabetic retinopathy images. The proposed approach uses the feature map of ResNet-50 and passes it to Random Forest for classification. The proposed approach is compared with five state-of-the-art approaches using two category Messidor-2 and five category EyePACS datasets. These two categories on the Messidor-2 dataset include ’No Referable Diabetic Macular Edema Grade (DME)’ and ’Referable DME’ while five categories consist of ‘Proliferative diabetic retinopathy’, ‘Severe’, ‘Moderate’, ‘Mild’, and ‘No diabetic retinopathy’. The results show that the proposed approach outperforms compared approaches and achieves an accuracy of 96% and 75.09% for these datasets, respectively. The proposed approach outperforms six existing state-of-the-art architectures, namely ResNet-50, VGG-19, Inception-v3, MobileNet, Xception, and VGG16.

Iris Recognition Development Techniques: A Comprehensive Review

Abstract: Recently, iris recognition techniques have achieved great performance in identification. Among authentication techniques, iris recognition systems have received attention very much due to their rich iris texture which gives robust standards for identifying individuals. Notwithstanding this, there are several challenges in unrestricted recognition environments. In this article, the researchers present the techniques used in different phases of the recognition system of the iris image. The researchers also reviewed the methods associated with each phase. The recognition system is divided into seven phases, namely, the acquisition phase in which the iris images are acquired, the preprocessing phase in which the quality of the iris image is improved, the segmentation phase in which the iris region is separated from the background of the image, the normalization phase in which the segmented iris region is shaped into a rectangle, the feature extraction phase in which the features of the iris region are extracted, the feature selection phase in which the unique features of the iris are selected using feature selection techniques, and finally the classification phase in which the iris images are classified. This article also explains the two approaches of iris recognition which are the traditional approach and the deep learning approach. In addition, the researchers discuss the advantages and disadvantages of previous techniques as well as the limitations and benefits of both the traditional and deep learning approaches of iris recognition. This study can be considered as an initial step towards a large-scale study about iris recognition.

Ocular recognition databases and competitions: a survey

Abstract: The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufficient to extract iris information. In addition to providing information about an individual’s identity, features extracted from these traits can also be explored to obtain other information such as the individual’s gender, the influence of drug use, the use of contact lenses, spoofing, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specific problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics.