Work

Using Convolutional Neural Networks to Analyze and Detect Key Points of Objects in Image

Year: 2024

Type: article

Abstract: The article discusses the use of Convolutional Neural Networks (CNNs) for analysis and detection of key points of objects in images, in particular hands. The mathematical representation of the principles of CNNs work explains the keypoint detection process, and the conducted experiments show the significant influence of lighting conditions and frame rate (frame per second - FPS) on detection accuracy and processing delay. The results confirm that increasing illumination up to 500 lux and frame rates up to 60 FPS improve accuracy and reduce latency, although detection accuracy decreases in low light. The findings highlight the importance of lighting and frame rate optimization to achieve high real-time performance.

Source: Multidisciplinary Journal of Science and Technology

DOI: 10.5281/zenodo.13692434

Authors: Dmytro Gurin, Vladyslav Yevsieiev, Svitlana Maksymova, Ahmad Alkhalaileh

Institutions: Kharkiv National University of Radio Electronics, V. N. Karazin Kharkiv National University

Language: English

Topic: Hand Gesture Recognition Systems

Subfield: Human-Computer Interaction

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W6911790784

FWCI:

Cites:

Cited by:

Related to: