A method of detecting a printed mark, a storage medium and related apparatus

Abstract

The present application relates to the technical field of printing equipment, and discloses a detection method of printed marks, a storage medium and related devices. The method comprises: collecting images of printed marks of different quality and interference factors under different paper, different light environments as sample images; preprocessing and indexing the sample images to obtain a printed mark training sample set; training a printed mark detection model based on a neural network using the printed mark training sample set; collecting real-time images of printed paper in real time, and preprocessing the collected real-time images of printed paper; inputting the preprocessed real-time images into the printed mark detection model to obtain printed mark detection results of the real-time images; and controlling the printing equipment to perform a printing action according to the printed mark detection results. The method can improve the robustness of printed mark detection, thereby ensuring the stability of the printing effect under different environments, avoiding the need to frequently adjust detection parameters in an industrial scenario, and reducing maintenance costs.

Images