An experimental study on object recognition and enhancement in MWIR thermography

摘要

An infrared (IR) camera is one of the common tools for taking images for thermography analysis in the medical field. In this paper, object recognition using infrared images captured with a middle wave infrared (MWIR) camera is studied. By using the InSb detector, the MWIR system used in this study operates in the 3-5 μm waveband, and it is well-suited for high-end research and development applications. To enhance the applicability of MWIR thermography to medical-related problems, it is important to devise reliable recognition and enhancement techniques for MWIR images. In this work, an experimental study is conducted to identify the capability of MWIR thermography in distinguishing an object (a human hand) from its background with varying emissivity and temperature levels. It is observed that object recognition becomes difficult when the emissivity difference is within 0.01 under the temperature condition of within 1℃ for the object and the background. In addition, a histogram equalisation approach is utilised to enhance blurry images from the MWIR system. The results demonstrate the histogram equalisation method is able to expand the dynamic range expansion of image grey levels so that the output image becomes clear and visible for object recognition.