Abstract. Todays, the range of applications of image processing in various fields such as medical, robotics, agriculture and meteorology spread. Several studies have been conducted in these areas, but little researches have been done regarding its application in weld inspection. To test the groove and complete joint penetrating high-strength welding defects (such as pressure vessels, heat boilers, etc.) used radiography testing method. In the case of defects that are similar but have different acceptance criteria, minimize or eliminate the errors in radiography films by optimizing images using image processing. In image processing, edge detection, improving image quality and accurate color diagnosis is possible and help to accurately identifying of defects and decreases errors in diagnosis of defects type. In this study, the method for detection of internal defects of weld in radiography films using image processing will be investigated that its results can be used to eliminate the need for human interpretation of film and fully automate it using a machine.so first the general and basic concepts related to image processing, as well as a variety of weld defects will be described, then, using the results of research and development, effective way to identify defects using image processing algorithms will be provided and implement procedures and methods of it, using MATLAB software will be explained.