# Edge-Embedded Multi-Feature Fusion Network for Automatic Checkout

## TL;DR

This paper introduces E2MF2Net, a new network for automatic checkout that improves accuracy by handling occlusions and clutter in checkout images.

## Contribution

The novel E2MF2Net combines synthetic image generation and feature modeling with edge-embedded modules for better detection.

## Key findings

- E2MF2Net achieves checkout accuracy of 98.52% on the Easy mode of the RPC dataset.
- It improves by 3.63 percentage points in the heavily occluded Hard mode.
- The model shows strong robustness in incremental learning and domain generalization.

## Abstract

The Automatic Checkout (ACO) task aims to accurately generate complete shopping lists from checkout images. Severe product occlusions, numerous categories, and cluttered layouts impose high demands on detection models’ robustness and generalization. To address these challenges, we propose the Edge-Embedded Multi-Feature Fusion Network (E2MF2Net), which jointly optimizes synthetic image generation and feature modeling. We introduce the Hierarchical Mask-Guided Composition (HMGC) strategy to select natural product poses based on mask compactness, incorporating geometric priors and occlusion tolerance to produce photorealistic, structurally coherent synthetic images. Mask-structure supervision further enhances boundary and spatial awareness. Architecturally, the Edge-Embedded Enhancement Module (E3) embeds salient structural cues to explicitly capture boundary details and facilitate cross-layer edge propagation, while the Multi-Feature Fusion Module (MFF) integrates multi-scale semantic cues, improving feature discriminability. Experiments on the RPC dataset demonstrate that E2MF2Net outperforms state-of-the-art methods, achieving checkout accuracy (cAcc) of 98.52%, 97.95%, 96.52%, and 97.62% on Easy, Medium, Hard, and Average mode, respectively. Notably, it improves by 3.63 percentage points in the heavily occluded Hard mode and exhibits strong robustness and adaptability in incremental learning and domain generalization scenarios.