eduzhai > Applied Sciences > Engineering >

Detection and Removal of Infrared (IR) Image Noise Patterns: An Experimental Case Study of Knee Thermograms

  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: It was observed in the relevant literature that thermal infrared imaging techniques serve as a potential tool in the diagnosis of inflammatory diseases at an early stage compared to existing imaging modalities such as Radiography. The skin surface temperature measured from knee region of thermograms was highly correlated to Erythrocyte Sedimentation Rate (ESR). It was observed in the relevant literature that thermal infrared imaging techniques serve as a potential tool in the diagnosis of inflammatory diseases at an early stage compared to existing imaging modalities such as Radiography. The skin surface temperature measured from knee region of thermograms was highly correlated to Erythrocyte Sedimentation Rate (ESR).It is very difficult to avoid the interference from external factors like bad atmospheric conditions that degrades the Infrared (IR) signal radiated from objects, affecting its quality and hindering its deployment in the field of medical image processing which can present a variety thermal noise. So detection and removal of distinct noise patterns from noisy knee thermograms is a very crucial task. The novelty of our work lies in the fact that we are trying to detect and analyze the presence of noise pattern in knee thermal images unlike bulk of existing literature that are focused only on framing different algorithms and methods for thermal noise reduction. One of our prime objectives is to detect the type of noise efficiently so that the reduction algorithms can work well for filtering the rightly detected thermal noise. In this paper, an experimental case study is presented relating to noise patterns of the knee thermograms and analysis based on their detection and removal is also done. Corresponding histogram output of the noisy and the filtered images along with their through Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) values are also analyzed to ascertain how well the filtering algorithm works for rightly detected noise removal.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×