Tasking on Natural Statistics of Infrared Images

ABSTRACT:

Natural scene statistics (NSSs) provide powerful, perceptually relevant tools that have been successfully used for image quality analysis of visible light images. Since NSS capture statistical regularities that arise from the physical world, they are relevant to long wave infrared (LWIR) images, which differ from visible light images mainly by the wavelengths captured at the imaging sensors. We show that NSS models of bandpass LWIR images are similar to those of visible light images, but with different parameterizations. Using this difference, we exploit the power of NSS to successfully distinguish between LWIR images and visible light images. In addition, we study distortions unique to LWIR and find directional models useful for detecting the halo effect, simple bandpass models useful for detecting hotspots, and combinations of these models useful for measuring the degree of non-uniformity present in many LWIR images. For local distortion identification and measurement, we also describe a method for generating distortion maps using NSS features. To facilitate our evaluation, we analyze the NSS of LWIR images under pristine and distorted conditions, using four databases, each captured with a different IR camera. Predicting human performance for assessing distortion and quality in LWIR images is critical for task efficacy. We find that NSS features improve human targeting task performance prediction. Furthermore, we conducted a human study on the perceptual quality of noise and blur-distorted LWIR images and create a new blind image quality predictor for IR images.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

• Although NSS have proven to be highly successful tools in applications on visible light images, the development and use of similar models has not been nearly as widespread on LWIR images.

• Morris et al. compared LWIR image statistics with natural visible light image statistics, and found that the spectral power of LWIR images is more “heavy-tailed” and that LWIR wavelet histograms are generally peakier, likely due to the characteristic spatial smoothness of infrared images.

• Kaser and Goodall and Bovik modeled the fit of the BRISQUE and NIQE image quality models to LWIR images showing that these visible

DISADVANTAGES OF EXISTING SYSTEM:

• The statistics of visible-light and LWIR are predictably different.

• The “Halo effect” is another distortion, which occurs mostly in thermal cameras equipped with ferro-electric sensors. This effect causes the region surrounding a bright object to grow darker and it causes the region around dark objects to grow lighter

PROPOSED SYSTEM:

• A broad theme of this paper is the development and practical application of Natural Scene Statistic (NSS) models of LWIR images. NSS models describe statistical regularities that are observed on images taken of the natural world.

• LWIR images are certainly ’natural’ in the sense that we use the term, and understanding and modeling the NSS of LWIR images has the potential to drive the development of new applications.

• These applications include identifying distortions present in any given LWIR image, enhancing images to reduce the degree of distortion, and for producing more accurate and reproducible comparisons of the performance of thermal imagers. Since the final receiver of LWIR images is often the human observer, human tasks can be improved by incorporating NSS that capture the response of the human visual system.

• Important distortions that we study here include nonuniformity (NU) noise, ferro-electric “Halo effects,” sensor noise, JPEG artifacts, blurring, and hotspots.

ADVANTAGES OF PROPOSED SYSTEM:

• Provides accurate global distortion level estimate.

• Correlate well with human task performance and human subjective test results.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System            : Pentium Dual Core.

• Hard Disk       : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB

• Tool                      : MATLAB R2013A

REFERENCE:

Todd Richard Goodall, Alan Conrad Bovik, Fellow, IEEE, and Nicholas G. Paulter Jr., Fellow, IEEE , “Tasking on Natural Statistics of Infrared Images”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 1, JANUARY 2016.