In this paper, we explore the application of Recurrent Neural Network (RNN) for still images. Typically, Convolutional Neural Networks (CNNs) are the prevalent method applied for this type of data, and more recently, transformers have gained popularity, although they often require large models. Unlike these methods, RNNs are generally associated with processing sequences over time rather than single images. We argue that RNNs can effectively handle still images by interpreting the pixels as a sequence. This approach could be particularly advantageous for compact models designed for embedded systems, where resources are limited. Additionally, we introduce a novel RNN design tailored for two-dimensional inputs, such as images, and a custom version of BiDirectional RNN (BiRNN) that is more memory-efficient than traditional implementations. In our research, we have tested these layers in Convolutional Recurrent Neural Networks (CRNNs), predominantly composed of Conv2D layers, with RNN layers at or close to the end. Experiments on the COCO and CIFAR100 datasets show better results, particularly for small networks.

本研究解决了递归神经网络（RNN）在处理静态图像时的不典型应用，通常该任务由卷积神经网络（CNN）主导。论文提出将像素视为序列来处理图像，并设计了一种新的二维输入RNN结构，尤其适合嵌入式系统。实验结果表明，在COCO和CIFAR100数据集上，这一方法在小型网络中具有更好的性能。

针对静态图像的递归神经网络