Image processing technique by multi scale retinex algorithm to flame characteristics investigation

Abstract EN

Image processing algorithms was more effected in modern processes to evaluate the flame characteristics such as height, length and thickness by taking digital image for flame by high speed camera for three different fuel types diesel, biodiesel and biofuel of jet flame by depend upon more variables effect such as mass flow rate, diameter of nozzle and compressed pressure.

We will be applying two different mathematical methods in order to measuring some characteristics of diffusion flame.

Where one depend upon Wiens distribution of a black body with MSR math-lab processing and another depend upon the intensity of the flame.

These operations target to enhancing the exactitude of image segmentation and resolution.

Secondly, feature extractions of the visible and infrared line images are performed, and the recognition of the target image is further completed.

Finally, image fusion is performed by weighted averaging of the targets detected by visible light and infrared images The image properties are investigating by increase the knowledge of the color and resolution of digital image and enhancement the origin image by applying the concern algorithm and less the noise.

The results show that the algorithm of retinex is suitable to analysis the digital image and not distortions on it .