一种图像检测方法及计算机可读存储介质

• Format: Patent
• Language: Chinese
• Published: 14.10.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

本发明公开了一种图像检测方法及计算机可读存储介质，其中，图像检测方法包括：基于图像检测模型的特征提取网络对获取的目标图像进行特征提取，得到所述目标图像的基础特征图；所述目标图像中包括目标对象；基于所述图像检测模型的显著性提取网络对所述基础特征图进行显著性区域提取，得到多个显著性特征图；对所述多个显著性特征图进行特征融合，得到显著性融合特征图；将所述显著性融合特征图输入至所述图像检测模型的检测网络中进行目标检测，得到所述目标对象的目标检测结果。本发明提高了显著性区域特征对目标检测结果的影响，使得到的目标检测结果更加准确，有利于提高对医学图像的判读的准确性和效率。 The invention discloses an image detection method and a computer readable storage medium. The image detection method comprises the steps: carrying out feature extraction of an obtained target image based on a feature extraction network of an image detection model, and obtaining a basic feature map of the target image, wherein the target image comprises a target object; based on a saliency extraction network of the image detection model, performing saliency region extraction on the basic feature map to obtain a plurality of saliency feature maps; performing feature fusion on the plurality of saliency feature maps to obtain a saliency fusion feature map; and inputting the saliency fusion feature map into a detection network of the i