In in-sensor image preprocessing, the sensed image undergoes low level processing like denoising at the sensor end, similar to the retina of human eye. Optoelectronic synapse devices are potential contenders for this purpose, and subsequent applications in artificial neural networks (ANNs). The optoelectronic synapses can offer image pre-processing functionalities at the pixel itself—termed as in-pixel computing. Denoising is an important problem in image preprocessing and several approaches have been used to denoise the input images. While most of those approaches require external circuitry, others are efficient only when the noisy pixels have significantly lower intensity compared to the actual pattern pixels. In this work, we present the innate ability of an optoelectronic synapse array to perform denoising at the pixel itself once it is trained to memorize an image. The synapses consist of phototransistors with bilayer MoS₂ channel and p-Si/PtTe₂ buried gate electrode. Our 7 × 7 array shows excellent robustness to noise due to the interplay between long-term potentiation and short-term potentiation. This bio-inspired strategy enables denoising of noise with higher intensity than the memorized pattern, without the use of any external circuitry. Specifically, due to the ability of these synapses to respond distinctively to wavelengths from 300 nm in ultraviolet to 2 µm in infrared, the pixel array also denoises mixed-color interferences. The “self-denoising” capability of such an artificial visual array has the capacity to eliminate the need for raw data transmission and thus, reduce subsequent image processing steps for supervised learning.

在传感器内图像预处理中，感测到的图像在传感器端进行低级处理，例如去噪，类似于人眼的视网膜。光电突触器件是实现此目的以及随后在人工神经网络（ANN）中的应用的潜在竞争者。光电突触可以在像素本身提供图像预处理功能，称为像素内计算。去噪是图像预处理中的一个重要问题，已经使用了多种方法对输入图像进行去噪。虽然大多数这些方法需要外部电路，但其他方法仅当噪声像素的强度明显低于实际图案像素时才有效。在这项工作中，我们展示了光电突触阵列在被训练来记忆图像后对像素本身执行去噪的固有能力。突触由具有双层 MoS ₂通道和 p-Si/PtTe ₂埋置栅电极的光电晶体管组成。由于长期增强和短期增强之间的相互作用，我们的 7 × 7 阵列表现出出色的抗噪声鲁棒性。这种仿生策略能够以比记忆模式更高的强度对噪声进行降噪，而无需使用任何外部电路。具体来说，由于这些突触能够对从 300 nm 紫外线到 2 µm 红外线的波长做出独特的响应，因此像素阵列还可以消除混合颜色干扰。这种人工视觉阵列的“自降噪”能力能够消除原始数据传输的需要，从而减少监督学习的后续图像处理步骤。