摘要
分析了基于自底向上的视觉注意计算模型的感兴趣区域检测方法;它分别提取颜色、灰度、纹理三个特征图像,然后进行线性融合得到综合显著图。而显著目标通常自身灰度相近,但与背景灰度不同,根据这个特性结合灰度概率统计方法对视觉注意计算模型进行改进。实验结果验证了,该模型能够更好的模拟视觉注意的过程,而且计算复杂度较低。
A visual attention mechanism based on approach of regions of interest detection is analyzed. Colors, intensity, and orientations of image features, are combined into a single topographical saliency map. To improve the attention mechanism,it adds a intensity distribution method. The proposed method is based on searching image regions whose intensity values are more accurately described by the intensity distribution of the object compared to the distribution of the surrounding area. The experimental results show that the model corresponds with the procedure of visual attention.Besides,it has low complexity and high utility value.
出处
《电子设计工程》
2013年第5期54-56,60,共4页
Electronic Design Engineering