The invention discloses an automatic comparison and identification method for an explosive circuit board debris image, and belongs to the technical field of pattern recognition and image processing. The method comprises the following steps that: firstly, carrying out object segmentation on the debris image on the basis of an image segmentation algorithm of a probability graph model, then, adopting a color model based on probability sampling to carry out the object fine positioning of a component, extracting and filtering feature points, comparing and identifying the filtered feature points with circuit board feature points in a retrieval library, and determining a source circuit board to which a debris belongs. The invention puts forward and realizes a method for automatically identifying the primitive plate which has the same type with a printed circuit board according to the explosive circuit board debris image. By use of the comparison and identification method, the component and a character area in the circuit board can be accurately segmented, noise interference can be inhibited, and similarity between feature point description and a space geometry relationship is considered while comparison is carried out. By use of the method, TOP1 accuracy in the automatic identification of the circuit board debris image is higher than 99%.