Image sample expansion method and device and storage medium

The invention discloses an image sample expansion method and device and a storage medium, relates to the field of image processing, and is used for solving the problem of poor neural network model training effect when the number of samples in a sample set is limited. The method comprises the following steps: selecting at least two sample images with the same image type from a sample set for neuralnetwork training; and fusing pixels of the selected sample image by using a preset fusion coefficient to generate an extended image for neural network training. Thus, when the number of samples in the sample set is limited, a new image can be obtained by fusing the sample images in the sample set, so that the number of samples in the sample set is increased, and the training effect of the neuralnetwork model is improved. 本申请公开了一种图像样本扩充方法、装置及存储介质，涉及图像处理领域，用以解决在样本集中的样本数量有限时，使得神经网络模型训练的效果较差的问题。该方法包括：从用于神经网络训练的样本集合中选取图像类型相同的至少两张样本图像；以预设的融合系数对选取的样本图像的像素进行融合处理，生成用于神经网络训练的扩充图像。这样，在样本集中的样本数量有限时，通过将样本集中的样本图像进行融合处理，可以得到新的图像，从而