MCHB-DETR: An Efficient and Lightweight Inspection Framework for Ink Jet Printing Defects in Semiconductor Packaging

TL;DR

This paper introduces MCHB-DETR, a lightweight and efficient inspection framework for detecting inkjet printing defects in semiconductor packaging.

Contribution

The novel MCHB-DETR framework improves defect detection with reduced computational cost and enhanced performance.

Findings

MCHB-DETR reduces parameters by 29.1% and FLOPs by 36.7% compared to existing methods.

It achieves 3.1% improvement in mAP@50 and 3.5% in mAP@50:95 on an inkjet printing dataset.

The framework maintains high detection performance while enabling efficient inference.

Abstract

In semiconductor packaging and microelectronic manufacturing, inkjet printing technology is widely employed in critical processes such as conductive line fabrication and encapsulant dot deposition. However, dynamic printing defects, such as missing droplets and splashing can severely compromise circuit continuity and device reliability. Traditional inspection methods struggle to detect such subtle and low-contrast defects. To address this challenge, we propose MCHB-DETR, a novel lightweight defect detection framework based on RT-DETR, aimed at improving product yield in inkjet printing for semiconductor packaging. MCHB-DETR features a lightweight backbone with enhanced multi-level feature extraction capabilities and a hybrid encoder designed to improve cross-scale and multi-frequency feature fusion. Experimental results on our inkjet dataset show a 29.1% reduction in parameters and a 36.7% reduction in FLOPs, along with improvements of 3.1% in mAP@50 and 3.5% in mAP@50:95. These results demonstrate its superior detection performance while maintaining efficient inference, highlighting its strong potential for enhancing yield in semiconductor packaging.

Figures