This paper provides an analysis and comparison of the YOLOv5, YOLOv8 and YOLOv10 models for webpage CAPTCHAs detection using the datasets collected from the web and darknet as well as synthetized data of webpages. The study examines the nano (n), small (s), and medium (m) variants of YOLO architectures and use metrics such as Precision, Recall, F1 score, mAP@50 and inference speed to determine the real-life utility. Additionally, the possibility of tuning the trained model to detect new CAPTCHA patterns efficiently was examined as it is a crucial part of real-life applications. The image slicing method was proposed as a way to improve the metrics of detection on oversized input images which can be a common scenario in webpages analysis. Models in version nano achieved the best results in terms of speed, while more complexed architectures scored better in terms of other metrics.

翻译：本文对YOLOv5、YOLOv8和YOLOv10模型在网页验证码检测任务中的性能进行了分析与比较，所使用的数据集包括从网络和暗网收集的网页验证码以及合成的网页数据。研究考察了YOLO架构的nano（n）、small（s）和medium（m）变体，并采用精确率、召回率、F1分数、mAP@50和推理速度等指标来评估其实际应用价值。此外，本文还探讨了将训练好的模型高效调优以检测新型验证码模式的可能性，这在实际应用场景中至关重要。针对网页分析中常见的输入图像尺寸过大的问题，本研究提出了图像切片方法以提升检测指标。实验结果表明，nano版本模型在推理速度方面表现最佳，而更复杂的架构在其他评估指标上取得了更好的成绩。