Neuromorphic engineering is essentially the development of artificial systems, such as electronic analog circuits that employ information representations found in biological nervous systems. Despite being faster and more accurate than the human brain, computers lag behind in recognition capability. However, it is envisioned that the advancement in neuromorphics, pertaining to the fields of computer vision and image processing will provide a considerable improvement in the way computers can interpret and analyze information. In this paper, we explore the implementation of visual tasks such as image segmentation, visual attention and object recognition. Moreover, the concept of anisotropic diffusion has been examined followed by a novel approach employing memristors to execute image segmentation. Additionally, we have discussed the role of neuromorphic vision sensors in artificial visual systems and the protocol involved in order to enable asynchronous transmission of signals. Moreover, two widely accepted algorithms that are used to emulate the process of object recognition and visual attention have also been discussed. Throughout the span of this paper, we have emphasized on the employment of non-volatile memory devices such as memristors to realize artificial visual systems. Finally, we discuss about hardware accelerators and wish to represent a case in point for arguing that progress in computer vision may benefit directly from progress in non-volatile memory technology.
翻译:神经神经系统工程主要是开发人工系统,例如利用生物神经系统中发现的信息显示的电子模拟电路。尽管计算机比人类大脑更快、更准确,但是在识别能力方面却落后于计算机。然而,据设想,与计算机视觉和图像处理领域有关的神经形态学的进步将大大改进计算机解释和分析信息的方式。在本文件中,我们探索了图像分割、视觉关注和物体识别等视觉任务的执行情况。此外,在研究动脉学扩散概念之后,还采用了一种新颖的方法,即使用模拟器进行图像分割。此外,我们讨论了神经形态视觉传感器在人工视觉系统中的作用,以及有关的协议,以便能够不同步地传输信号。此外,还讨论了两种被广泛接受的算法,用来模仿物体识别和视觉关注的过程。在本文件的整个过程中,我们一直强调使用非挥发性记忆装置,例如用于实现人造视觉系统。最后,我们讨论了关于硬质感应传感器在人工视觉系统中的作用,希望直接代表计算机记忆技术的进展。