computer vision

DEVELOPMENT OF A PROGRAM FOR MODELING AND SIMULATING A COLLABORATIVE ROBOT WORKSPACE

The article presents the software development for modeling and simulating the workspace of a collaborative robot taking into account the presence of people. This is an important step in creating safe and efficient robotic systems within Industry 5.0 concept. The problem is posed by the need to ensure safety during the interaction of the robot with the operator, which is relevant for modern production processes with high human participation.

Advanced YOLO models for real-time detection of tomato leaf diseases

The increasing focus on smart agriculture in the last decade can be attributed to various factors, including the adverse effects of climate change, frequent extreme weather events, increasing population, the necessity for food security, and the scarcity of natural resources.  The government of Morocco adopts preventative measures to combat plant illnesses, specifically focusing on tomatoes.  Tomatoes are widely acknowledged as one of the most important vegetable crops, but they are highly vulnerable to several diseases that significantly decrease their productivity.  De

Implementation of presence detection with Haar cascade and local binary patterns histograms

School truancy is a significant problem that affects the educational environment and student achievement.  This article presents a project to develop an automated absence detection system for classrooms using Haar Cascade and Local Binary Patterns Histogram (LBHP) techniques.  The study begins by collecting a large dataset of classroom images, including various lighting scenarios and conditions.  Haar Cascade is used to detect human faces in images, followed by LBHP feature extraction for each detected face.  Experimental results demonstrate the effectiveness of the pro

Information System for Adapting Road Lane Segmentation Methods in Navigation Systems in Order to Increase the Accuracy of Road Signs Detection

In today’s world, where the speed of technological change is extremely impressive, the traffic industry is not left behind. The use of lane segmentation on the road is becoming a key element not only for safety, but also for improving navigation and traffic sign detection systems. This approach opens the door to a new level of efficiency and accuracy in traffic management, helping to improve the quality and safety of our movement. Let’s dive into the details of this exciting and promising area of road transport technology development.

Development of an Algorithm and Software System for Facing Panels Accounting on Production Lines

This paper aims to develop and implement an algorithm and an automated software system for the auto- matic accounting process of external facing panels during transportation on line conveyors. The method described in this paper is designed to simplify the process of production and accounting of wall-facing panels. This method can also serve as a model for implementing other manufacturers. The developed  algorithm consists of the following steps: obtaining a video stream in real-time or from a file and its targeted processing and determining the number of moving objects of interest.

Extraction of ideogram features for diagnosing chromosomal abnormalities

This paper proposes an approach to the detection and extraction of specific features in an ideogram image. Ideogram is a depiction of a healthy chromosome used in a karyotyping process - a procedure designed to diagnose chromosomal abnormalities.

Extraction of ideogram features is a part of a general algorithm for the detection of chromosomal abnormlities. According to the general algorithm, both chromosomes and ideograms have to be parsed and converted into a single data format for further comparison.

Development of a Video Surveillance System for Motion Detection and Object Recognition

This article explores the development of a video surveillance system that utilizes cuttingedge technology to analyze the video stream in real-time, identify motion, and recognize objects within the video stream. The functionality of this system enables it to provide a high level of accuracy in identifying objects, even in low-light conditions or with low-resolution cameras. The software system has been designed as a user-friendly desktop application with the latest technologies and features that will ensure its relevance and easy maintenance in the future.

COMPUTER VISUAL INSPECTION OF PEAR QUALITY

A brief description of the basic stages of image processing is given to pay attention to the segmentation stage as a
possible way to improve efficiency in decision-making. The main characteristics of the presented model are visual signs, such as
color, shape, the presence of a stem, and others. Due to the different approaches in image processing, a high level of truthfulness is
achieved, which is expressed in the percentage ratio of the accuracy of decision-making and varies in the range from 90 to 96%.

Comprehensive Analysis of Few-shot Image Classification Method Using Triplet Loss

Image classification task is a very  important problem of a computer vision area. The first approaches to image classification tasks belong to a classic straightforward algorithm. Despite the successful applications of such algorithms a lot of image classification tasks had not been solved until machine learning approaches were involved in a computer vision area. An early successful result of machine learning applications helps researchers with extracted features classification which was not available without machine learning models.