Aiming at the existing problems of tool wear detection,such as slow detection speed,large manual workload and low economic benefit,a tool wear detection algorithm based on single perspective image processing was proposed.The CCD camera was used to extract the images before and after wear from a single perspective.The panoramic deep tool images before and after wear were obtained through image fusion and transformation,and the panoramic deep images before and after wear were registered.After the wear area image was obtained,the pixel of the wear area image was converted into the actual length value,and the actual wear amount was calculated.The experimental results show that the proposed method has high detection speed,and the measurement error range meets the requirement of detection accuracy,so it can be applied to actual production.