Tobacco shred width detection method and device based on residual network, equipment and medium

The invention discloses a tobacco shred width detection method and device based on a residual network, equipment and a medium. The method comprises the steps that firstly, an obtained first tobacco shred image is preprocessed, and a second tobacco shred image is obtained; wherein the second tobacco shred image is an image with a white background part and a black tobacco shred part; extracting a plurality of target tobacco shred image blocks from the second tobacco shred image; and finally, inputting the plurality of target tobacco shred image blocks into the trained residual network detection model to obtain the tobacco shred width in the first tobacco shred image. According to the invention, real-time detection of the tobacco shred width can be effectively realized under the condition that the detection accuracy is ensured. 本发明公开了一种基于残差网络的烟丝宽度检测方法、装置、设备和介质。该方法包括：首先对获取的第一烟丝图像进行预处理，获得第二烟丝图像；其中，第二烟丝图像是背景部分为白色、烟丝部分为黑色的图像；然后从该第二烟丝图像中提取出多个目标烟丝图像块；最后将多个目标烟丝图像块输入训练后的残差网络检测模型中，获得第一烟丝图像中的烟丝宽度。本发明能够在保证检测精确度的情况下有效实现烟丝宽度