Artificial ice crystal identification and statistics method based on YOLOv3 algorithm

• Main Authors: FANG CHUNGANG, LI JUNXIA, CHE YUNFEI, ZHOU SHUXUE, SU ZHENGJUN, LIU XIJING, DANG JUAN
• Format: Patent
• Language: Chinese; English
• Published: 15.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses an artificial ice crystal identification and statistics method based on a YOLOv3 algorithm, and the method carries out the model training through constructing a glass slide ice crystal picture data set, builds an artificial ice crystal detection network, and can carry out the detection and statistics of an artificial ice crystal small target in a microscope glass slide ice crystal picture. According to the method, automatic ice crystal counting and ice crystal shape recognition can be carried out, and the execution efficiency and the recognition accuracy are remarkably improved. 本发明公开了一种基于YOLOv3算法的人工冰晶识别与统计方法，该方法通过构建载玻片冰晶图片数据集来进行模型训练，建立人工冰晶检测网络，能够针对显微镜载玻片冰晶图片中人工冰晶小目标进行检测与统计。该方法能够进行自动冰晶计数和冰晶形状识别，并在执行效率和识别准确率上有显著提升。