一种权值可发育的视觉选择性注意模型研究
2018-05-15李福进杜建任红格史涛
李福进 杜建 任红格 史涛



摘 要: 针对Itti视觉选择性注意模型不具有子特征图显著图归一化过程中权值随任务改变而改变的问题,借鉴自主发育在视觉选择性注意学习的研究成果,提出一种权值可发育视觉选择性注意模型作为图像特征提取的学习机制。该算法采用三层自组织神经网络和Itti视觉选择性注意模型相结合的决策进行寻优,通过对模型的训练学习获取最优权值更新。这样既可以保证在初期特征提取内容的完整性,又降低了系统对不同任务条件的约束性,提高了模型特征提取能力。利用权值可发育视觉选择性注意模型对图像进行感兴趣区域特征提取实验,结果表明,该方法能够提高特征提取准确性、减少运算时间,获得了良好的动态性能。
关键词: Itti视觉选择性注意模型; 权值可发育; 自主发育; 特征提取; 显著图; 模型训练
中图分类号: TN911.73?34; TP391.4 文献标识码: A 文章编号: 1004?373X(2018)10?0183?04
Abstract: In the Itti visual selective attention model, the weight does not change as the task changes during the saliency map normalization of child feature map. Therefore, a visual selective attention model with weight development is proposed to be the learning mechanism of image feature extraction by learning from the research achievements of autonomous development in visual selective attention learning. In the algorithm, the strategy of combining three?layer self?organized neural network with Itti visual selective attention model is used for optimization. The optimal weight update is obtained by training and learning of the model, which can not only guarantee the completeness of the initial feature extraction content, but also reduce the constraint of the system on different task conditions, and improve the feature extraction capability of the model. An interested?area feature extraction experiment was carried out for images by using the visual selective attention model with weight development. The results show that the proposed method can improve the accuracy of feature extraction, reduce the computation time, and obtain a good dynamic performance.
Keywords: Itti visual selective attention model; weight development; autonomous development; feature extraction; saliency map; model training
0 引 言
视觉选择性注意(Visual Selective Attention)机制[1]是一种视觉感知机能,它是灵长目类动物长期进化的结果。研究表明,人类在感知外界信息信号过程中大约有75%的信息来源于视觉,在面对海量的感知信息时,为确保大脑处理信息的效率,视觉系统会选择感知信息中的一个子集做优先处理。在认知心理学中,这种选择有限信息进行优先处理的机制称为视觉选择性注意机制。基于此,研究者们根据心理学、生理学、认知科学的相关实验结果,模拟出一系列视觉选择性注意模……
