Conventional computer vision systems detect object after super-resolution (SR) or image reconstruction of the whole image, which is not an economical manner. By imitating the visual system of human beings, we proposed the bionic vision system (BVS), which is mainly composed by three parts: object detection by visual attention model, object-oriented SR reconstruction and object recognition by convolutional neural networks. The visual attention model contains both bottom-up and top-down cues. The bottom-up cues integrate low-level features by the feature integration theory. An Adaboost detector imitates the top-down cues. Sparse coding and compressed sensing reconstruction realize the object-oriented SR reconstruction. The BVS was validated on license plate recognition task. Both detection performance and SR reconstruction performance are tested. Besides of these, we also test the final recognition rate, all the experimental results are quite encouraging.

中文翻译：

---

仿生视觉系统及其在车牌识别中的应用

传统的计算机视觉系统是在超分辨率（SR）或整个图像的图像重建之后检测对象的，这不是经济的方式。通过模仿人类的视觉系统，我们提出了仿生视觉系统（B仿生视觉系统），它主要由三个部分组成：视觉注意模型的对象检测，面向对象的SR重建和卷积神经网络的对象识别。视觉注意模型包含自下而上和自上而下的提示。自下而上的线索通过特征整合理论整合了底层特征。Adaboost检测器模仿自上而下的提示。稀疏编码和压缩感知重建实现了面向对象的SR重建。BVS已通过车牌识别任务验证。测试了检测性能和SR重建性能。