Train wheel tread image segmentation method based on chemical reaction optimization

• Main Authors: FU JUN, DONG HUI, WANG GAN, MEI JINGSONG, GUO QICHANG, JIANG YINNAN
• Format: Patent
• Language: Chinese; English
• Published: 03.04.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a train wheel tread image segmentation method based on chemical reaction optimization. Aiming at the defect that a traditional OTSU threshold segmentation method is greatly influenced by factors such as an image contrast and a signal-to-noise ratio, a two-dimensional OTSU method is adopted for improvement, the defect segmentation accuracy is improved, , the threshold segmentation speed is improved and the time consumption is reduced in combination with an optical response optimization search method. According to the method, random noise can be effectively eliminated, necessary defect information is reserved, the method has high segmentation speed and precision, and the real-time requirement is met. 本发明公开了一种基于化学反应优化的列车车轮踏面图像分割方法，针对传统的OTSU阈值分割方法受图像对比度、信噪比等因素影响较大的缺点，采用二维OTSU方法加以改进，提高缺陷分割的准确性，同时结合学反应优化搜索方法，提高阈值分割速度，减少耗时。本方法可以有效地消除随机噪声，保留必要的缺陷信息，同时该方法具有较高的分割速度和精度，满足实时性要求。