This paper investigates the application of image segmentation for automating planogram compliance in retail stores. The main objective of this study is to identify the best suitable segmentation model for accurately segmenting the inner and outer shelves in a planogram zone of the supermarket rack. To identify the optimal segmentation model architecture for our task, we trained and evaluated seven segmentation architectures, including U-Net, LinkNet, FPN (Feature Pyramid Network), PAN (Pyramid Attention Network), PSPn.et (Pyramid Scene Parsing Network), MAnet (Multi-Attention-Network) and DeeplapV3.