The cable joints is complex in internal structure and the composition of the material properties are different. In order to use X-ray to realize a clear presentation of all the internal structure of cable joints

a condition judgement method of cable joints based on multi-energy X-ray image fusion is proposed. The guided filtering is used to decompose the X-ray inspection image of cable joints into multi-scale and the multi-energy X-ray image is divided into both detail layer and base layer. The multi-scale gradient function is used to generate the significant mapping of the detail layer

and the fusion weight map of the detail layer is obtained after normalization

the fusion weights of different base layers are assigned based on the degree of deviation from the exposure degree

and the weighted fusion is performed on the base and detail layers to get the reconstructed fusion image. Moreover

the fused image to be examined is differentiated from the standard image to judge the location of defects. The test results show that the fusion image obtained by the method of decomposition and then fusion has better advantages in variance

information entropy

average gradient and spatial frequency. The multi-energy X-ray fusion image

compared with the single detection image

can present the different internal structures of the cable joints in a clearer and more complete image

which is conducive to the accurate identification and localization of the defects in the cable joints.