IEEE Trans Syst Man Cybern B Cybern. 2011 Dec;41(6):1668-80. doi: 10.1109/TSMCB.2011.2158418. Epub 2011 Jul 14.
The biologically inspired model (BIM) proposed by Serre presents a promising solution to object categorization. It emulates the process of object recognition in primates' visual cortex by constructing a set of scale- and position-tolerant features whose properties are similar to those of the cells along the ventral stream of visual cortex. However, BIM has potential to be further improved in two aspects: mismatch by dense input and randomly feature selection due to the feedforward framework. To solve or alleviate these limitations, we develop an enhanced BIM (EBIM) in terms of the following two aspects: 1) removing uninformative inputs by imposing sparsity constraints, 2) apply a feedback loop to middle level feature selection. Each aspect is motivated by relevant psychophysical research findings. To show the effectiveness of the EBIM, we apply it to object categorization and conduct empirical studies on four computer vision data sets. Experimental results demonstrate that the EBIM outperforms the BIM and is comparable to state-of-the-art approaches in terms of accuracy. Moreover, the new system is about 20 times faster than the BIM.
塞尔提出的生物启发模型（BIM）为物体分类提供了一个很有前景的解决方案。它通过构建一组尺度和位置容忍特征来模拟灵长类动物视觉皮层中的物体识别过程，这些特征的属性与视觉皮层腹侧流中细胞的属性相似。然而，BIM在两个方面有进一步改进的潜力：由于密集输入导致的不匹配以及前馈框架导致的随机特征选择。为了解决或减轻这些限制，我们从以下两个方面开发了一种增强型BIM（EBIM）：1）通过施加稀疏约束去除无信息输入，2）在中层特征选择中应用反馈回路。每个方面都受到相关心理物理学研究结果的启发。为了展示EBIM的有效性，我们将其应用于物体分类，并在四个计算机视觉数据集上进行实证研究。实验结果表明，EBIM在准确性方面优于BIM，并且与当前最先进的方法相当。此外，新系统比BIM快约20倍。
