computer vision

Intelligent Automated System for Parsing and Ranking Resumes

Resume parsing is a method used to extract key information from resumes, allowing for further actions such as candidate selection and ranking.  In traditional recruitment processes, companies often handle thousands of resumes manually or require applicants to follow a pre-defined template.  However, the evolving recruitment environment calls for more advanced technological solutions and efficient resume analysis methods.  Although various basic techniques can analyze structured documents, they are inadequate for processing unstructured formats such as PDF, DOC, and DOCX

Transformer-Based Network for Robust 3D Industrial Environment Understanding in Autonomous UAV Systems

Autonomous navigation of unmanned aerial vehicles (UAVs) in unstructured industrial environments remains challenging due to irregular geometry, dynamic obstacles and sensor uncertainty. Classical Simultaneous Localization and Mapping (SLAM) systems, though geometrically consistent, often fail under poor initialization, textureless areas or reflective surfaces. To overcome these issues, this work proposes a hybrid transformer-geometric framework that fuses learned scene priors with keyframe-based SLAM.

Overview of Computer Vision Technologies for Product Labeling

In today’s world of globalized trade and e­commerce, product labeling is becoming increasingly important. It ensures product traceability throughout the supply chain, provides information and protection, and influences consumer confidence. Traditional methods of checking and reading labels are based on manual control or the use of simple barcode scanners, which often prove ineffective in conditions of increasing data processing volumes.

Enhancing Images in Poor Lighting Conditions Through Fusion of Optical and Thermal Camera Data

The goal of the article is to provide a methodology of improving images quality in low-light conditions trough fusion of data received from telecamera and thermal camera. Data from thermal camera uses for compensation of significant illumination reduction in poor lighting conditions and allow keep required level of information. Proposed method establishes dynamic regulation of fusion coefficients depending on brightness level to minimize artifacts, increase edge sharpness, and improve object detectability.

RESEARCH AND SOFTWARE IMPLEMENTATION OF HAND GESTURE RECOGNITION METHODS

The article presents the development of an interactive system for recognizing and classifying human hand gestures based on machine learning technologies. A new approach to gesture representation is proposed, combining spatial and temporal characteristics of the location of key points of the hand, which ensures high accuracy, noise resistance, and adaptability of the system to various conditions of use.

HYBRID APPROACH TO TRAFFIC SIGN RECOGNITION BASED ON COLOR SEGMENTATION AND CONVOLUTIONAL NEURAL NETWORKS

This paper presents a hybrid approach to traffic sign recognition that combines classical preprocessing techniques (color segmentation, contour detection, Haar Cascade, and HOG) with a lightweight Convolutional Neural Network (CNN) for classification. The proposed method reduces the amount of processed image data by a factor of 10–20, as only preselected regions of interest are passed to the neural network.

Development of a deep learning-based system in Python 3.9 with YOLOv5: A case study on real-time fish counting based on classification

This study developed a real-time fish classification and counting system for six types of fish using the YOLOv5 machine learning model with high accuracy.  The system achieved an F1-score of 0.87 and a precision confidence curve with an all-classes value of 1.00 at a confidence level of 0.920, demonstrating the model's reliability in object detection and classification.  Real-time testing showed that the system could operate quickly and accurately under various environmental conditions with an average inference speed of 30 FPS.  However, several challenges remain, such

ENSEMBLE IMAGE SUPER-RESOLUTION FOR UAV GEO-LOCALIZATION

In this paper, we address the challenge of visual geo-localization from low-quality UAV imagery captured in real world environments. We propose a two-stage architecture, which includes Super-Resolution and visual geo-localization. We introduced novel, non-learnable Ensemble Super-Resolution (ESR) module, which first refines upscaled aerial frames, then seamlessly feeds the enhanced imagery into a visual geo-localization pipeline.

Efficiency and accuracy: comparison of PIR, OpenCV with a webcam, and Raspberry Pi

This paper is dedicated to developing and evaluating the facial recognition system, focusing on its effectiveness and operational reliability under real-world conditions. The choice of the Raspberry Pi hardware platform for implementing the system has been justified by its capability to process video streams in real time, as well as its compatibility with the high-quality Raspberry Pi Camera V2, which enables the acquisition of images with sufficient resolution for the proper functioning of computer vision algorithms.

SYSTEMIZATION OF REQUIREMENTS FOR OPERATIONAL QUALITY CONTROL SYSTEMS OF MEAT PRODUCTS

This paper presents a study on organizing requirements for automated meat quality control systems. It identifies key quality indicators–color, texture, marbling, and gloss–and analyzes the technical and functional parameters essential for practical assessment. The research highlights integrating computer vision, image processing, and machine learning algorithms to enhance objectivity, accuracy, and evaluation speed. The proposed approach aims to reduce human influence, enable real-time monitoring, and offer scalable solutions suitable for large-scale producers and small enterprises.