基于多尺度信息处理和Gabor初始化的图像显著性对象检测  

Image salient object detection based on multi-scale information processing and Gabor initialization

作　　者：闯跃龙[1] 张石清[1] 赵小明[1] CHUANG Yue-long;ZHANG Shi-qing;ZHAO Xiao-ming(Institute of Image Processing and Pattern Recognition,Taizhou University,318000)

机构地区：[1]台州学院图像处理与模式识别研究所,浙江台州318000

出　　处：《光电子．激光》2020年第8期834-841,共8页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金项目(61976149);浙江省自然科学基金项目(LZ20F020002);台州市科技计划项目(1901gy20)资助项目。

摘　　要：基于全卷积网络的图像显著性检测获得了广泛的关注,并取得了令人瞩目的检测性能。然而,该类型神经网络依然存在许多问题,如高复杂网络导致难以训练、显著性对象边缘结果不准确等。针对这些问题,本文提出基于Gabor初始化的卷积神经网络。该网络主要特点包括:1)利用Gabor特征初始化卷积神经网络,提高神经网络训练效率;2)构建多尺度桥接模块,有效衔接编码和解码阶段,进而提高显著性检测结果;3)提出加权交叉熵损失函数,提高训练效果。实验结果表明,本文提出的神经网络在三个不同的数据集上均显示出优异的显著性对象检测性能。FCN based image saliency detection met hods have become very popular in the past few years because of outstanding performance.However,problems still exist in the methods,such as difficult training process,inaccurate edge detect ion.To solve the problems,a convolutional neural network based on Gabor initia lization is proposed,and the features of the network include:1)making use of Gabor feature improving the efficiency of training process;2)constructing brid ge module for the purpose connecting coding and decoding processes;3)proposing weighted cross entropy loss function to facilitate training effect.The experim ent shows that the proposed network represent brilliant performance in three pub lic datasets.

关 键 词：多尺度信息 GABOR 显著性对象检测 卷积神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]