Infrared image enhancement model based on gravitational force and lateral inhibition networks
| Autor: | Ferzan Katırcıoğlu, Yusuf Çay, Zafer Cingiz |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
media_common.quotation_subject Condenser (optics) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Edge (geometry) 01 natural sciences Edge detection 010309 optics Dimension (vector space) Lateral inhibition 0103 physical sciences Median filter Contrast (vision) Computer vision media_common business.industry Refrigeration system 021001 nanoscience & nanotechnology Condensed Matter Physics Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials Noise Computer Science::Computer Vision and Pattern Recognition Image enhancement Gravitational force Lateral inhibition network Artificial intelligence 0210 nano-technology business |
| Zdroj: | Infrared Physics & Technology. 100:15-27 |
| ISSN: | 1350-4495 0004-8585 |
| DOI: | 10.1016/j.infrared.2019.05.004 |
| Popis: | WOS: 000485855500003 Problems such as low contrast, noise, and edge blur are often encountered in color infrared images produced by infrared cameras. To solve these problems, we propose a new image enhancement algorithm based on the gravitational force and lateral inhibition network. First, information on total gravitational force for each dimension of the color infrared image was obtained. These two-dimensional three gray level images obtained using three-dimensional color properties help to define noise, edge and region within each dimension. Secondly, these three gray level images were subjected to a dual threshold value. A mean filter was used to reduce noise, while the lateral inhibition network was used for resolution and edge detection, and the regional gravity factor was used for contrast control. Finally, each dimension was combined again and a color enhanced image was produced. This study sets out to develop a method of enhancement images for infrared image analysis in cooling systems. The images used in the study are made up of a compressor, a condenser, and an evaporator belonging to the cooling system. The implementation of our method is simple and easy to understand and yields more accurate results. The experimental results show that the proposed method can eliminate noise, blur, and low contrast, and can also improve the details of infrared images better than other methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect