卷积特征图融合与显著性检测的图像检索

针对基于深度学习的图像检索提取特征往往包含了复杂的背景噪声,导致图像检索的精确率并不高的问题,提出一种特征图融合与显著性检测的方法.首先,训练用于分类的深度卷积神经网络模型.然后,并将图像卷积之后的特征图谱进行融合,得到图像的显著性区域.最后,通过计算图像显著性特征的余弦距离来进行检索.实验结果证明:相比目前主流的方法,文中方法能够有效提高检测精度,且鲁棒性较高.

Image Retrieval Based on Convolution Feature Map Fusion and Saliency Detection

Based on an in-depth learning of image retrieval, the features extracted usually contained the complicated background noises, which resulted in a low level of accuracy in image retrieval. The methods of feature map fusion and saliency detection are proposed in this paper. The method firstly trained deep convolutional neural network model used in image classification, and then fused the features of maps after image convolution in order to obtain the salient region of retrieved images. Finally, the retrieved images are calculated using the cosine distance of the salient features. The experiment shows that the proposed methods are able to effectively improve the accuracy of retrieval and that the robustness is relatively high, compared to the current mainstream methods.