# Merge-YOLO: An accurate detection model for book packaging defects in intelligent logistics scenarios

## TL;DR

This paper introduces Merge-YOLO, a new model for detecting book packaging defects in logistics, which improves accuracy for small and irregular defects.

## Contribution

The novel Merge-YOLO model introduces three key improvements for detecting small and irregular book packaging defects.

## Key findings

- Merge-YOLO achieves 95.8% precision, 93.6% recall, and 94.1% mAP@0.5 on the book packaging defect dataset.
- The model outperforms baseline YOLOv11 and traditional algorithms in all metrics.
- The model's improvements include better feature extraction for small objects and irregular shapes.

## Abstract

Driven by the knowledge economy and digitalization, the scale of book logistics continues to expand. However, the quality inspection process in this field currently uses generic target detection models and rarely considers defect characteristics. Therefore, this paper proposes the Merge-YOLO model to address the three prominent characteristics of book packaging defects: low contrast, small-sized defects, and irregular shapes. Three improvements are made to enhance detection performance: the WT-C3k2 module is designed to separate high- and low-frequency features using wavelet transforms, combined with multi-level convolutions and a bottleneck structure to enhance feature extraction capabilities for small objects and complex lighting conditions, while expanding the receptive field and reducing semantic detail loss; introducing the QA Transformer, which uses a learnable transformation matrix to generate adaptive quadrilateral windows, breaking through the limitations of traditional fixed windows and improving the ability to capture features of irregular defects; and adopting the DySample dynamic upscaler, which replaces nearest-neighbor interpolation by dynamically adjusting the scaling ratio through an adaptive scope factor, reducing computational overhead while preserving pixel-level details. Experiments show that the model achieves 95.8% precision, 93.6% recall, and 94.1%mAP@0.5 on the book packaging defect dataset, outperforming the baseline model YOLOv11 and traditional algorithms in all metrics. This provides an efficient and accurate detection model for quality control in book supply chain packaging.