Optical flow algorithms offer a way to estimate motion from a sequence of images. The computation of optical flow plays a key-role in several computer vision applications, including motion detection and segmentation, frame interpolation, three-dimensional scene reconstruction, robot navigation and video compression. In the case of gradient based optical flow implementation, the pre-filtering step plays a vital role, not only for accurate computation of optical flow, but also for the improvement of performance. Generally, in optical flow computation, filtering is used at the initial level on original input images and afterwards, the images are resized. In this paper, we propose an image filtering approach as a pre-processing step for the Lucas-Kanade pyramidal optical flow algorithm. Based on a study of different types of filtering methods and applied on the Iterative Refined Lucas-Kanade, we have concluded on the best filtering practice. As the Gaussian smoothing filter was selected, an empirical approach for the Gaussian variance estimation was introduced. Tested on the Middlebury image sequences, a correlation between the image intensity value and the standard deviation value of the Gaussian function was established. Finally, we have found that our selection method offers a better performance for the Lucas-Kanade optical flow algorithm.

Our research is focused on the development of robust machine vision algorithms for pattern recognition. We want to provide robotic systems the ability to understand more on the external real world. In this paper, we describe a method for detecting ellipses in real world images using the randomized Hough transform with result clustering. A preprocessing phase is used in which real world images are transformed - noise reduction, greyscale transform, edge detection and final binarization - in order to be processed by the actual ellipse detector. The ellipse detector filters out false ellipses that may interfere with the final results. Due to the fact that usually more "virtual" ellipses are detected for one "real" ellipse, a data clustering scheme is used, the clustering method, classifies all detected "virtual" ellipses into their corresponding "real" ellipses. The post processing phase is VQ similar and it also finds the actual number of classes unknown a priori

In recent years, significant advancements in the field of machine learning have influenced the domain of image restoration. While these technological advancements present prospects for improving the quality of images, they also present difficulties, particularly the proliferation of manipulated or counterfeit multimedia information on the internet. The objective of this paper is to provide a comprehensive review of existing inpainting algorithms and forgery detections, with a specific emphasis on techniques that are designed for the purpose of removing objects from digital images. In this study, we will examine various techniques encompassing conventional texture synthesis methods as well as those based on neural networks. Furthermore, we will present the artifacts frequently introduced by the inpainting procedure and assess the state-of-the-art technology for detecting such modifications. Lastly, we shall look at the available datasets and how the methods compare with each other. Having covered all the above, the outcome of this study is to provide a comprehensive perspective on the abilities and constraints of detecting object removal via the inpainting procedure in images.

Neonatal brain injury or neonatal encephalopathy (NE) is a significant morbidity and mortality factor in preterm and full-term newborns. NE has an incidence in the range of 2.5 to 3.5 per 1000 live births carrying a considerable burden for neurological outcomes such as epilepsy, cerebral palsy, cognitive impairments, and hydrocephaly. Many scoring systems based on different risk factor combinations in regression models have been proposed to predict abnormal outcomes. Birthweight, gestational age, Apgar scores, pH, ultrasound and MRI biomarkers, seizures onset, EEG pattern, and seizure duration were the most referred predictors in the literature. Our study proposes a decision-tree approach based on clinical risk factors for abnormal outcomes in newborns with the neurological syndrome to assist in neonatal encephalopathy prognosis as a complementary tool to the acknowledged scoring systems. We retrospectively studied 188 newborns with associated encephalopathy and seizures in the perinatal period. Etiology and abnormal outcomes were assessed through correlations with the risk factors. We computed mean, median, odds ratios values for birth weight, gestational age, 1-min Apgar Score, 5-min Apgar score, seizures onset, and seizures duration monitoring, applying standard statistical methods first. Subsequently, CART (classification and regression trees) and cluster analysis were employed, further adjusting the medians. Out of 188 cases, 84 were associated to abnormal outcomes. The hierarchy on etiology frequencies was dominated by cerebrovascular impairments, metabolic anomalies, and infections. Both preterms and full-terms at risk were bundled in specific categories defined as high-risk 75–100%, intermediate risk 52.9%, and low risk 0–25% after CART algorithm implementation. Cluster analysis illustrated the median values, profiling at a glance the preterm model in high-risk groups and a full-term model in the inter-mediate-risk category. Our study illustrates that, in addition to standard statistics methodologies, decision-tree approaches could provide a first-step tool for the prognosis of the abnormal outcome in newborns with encephalopathy.

Sound is the result of mechanical vibrations that set air molecules in motion, causing variations in air pressure that propagate as pressure waves. Represented as waveforms, these visual snapshots of sound reveal some of its characteristics. While waveform analysis offers limited insights, audio features provide a quantitative and structured way to describe sound, enabling data-driven analysis and interpretation. Different audio features capture various aspects of sound, facilitating a comprehensive understanding of the audio data. By leveraging audio features, machine learning models can be trained to recognize patterns, classify sounds, or make predictions, enabling the development of intelligent audio systems. Time-domain features, e.g., amplitude envelope, capture events from raw audio waveforms. Frequency domain features, like band energy ratio and spectral centroid, focus on frequency components, providing distinct information. In this paper, we will describe three time-domain and three frequency-domain features that we consider crucial and widely used. We will illustrate the suitability of each feature for specific tasks and draw general conclusions regarding the significance of sound features in the context of machine learning.

The main scope of the presented research was the development of an innovative product for the management of city parking lots. Our application will ensure the implementation of the Smart City concept by using computer vision and communication platforms, which enable the development of new integrated digital services. The use of video cameras could simplify and lower the costs of parking lot controls. In the aim of parking space detection, an aggregated decision was proposed, employing various metrics, computed over a sliding window interval provided by the camera. The history created over 20 images provides an adaptive method for background and accurate detection. The system has shown high robustness in two benchmarks, achieving a recognition rate higher than 93%.