Saved in:
Bibliographic Details
Main Authors: Shalmani, Mohammad Alijanpour, Boroujeni, Alale Rezvani, Amini, Ali, Yuan, Jiann Shiun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.24726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918519992483840
author Shalmani, Mohammad Alijanpour
Boroujeni, Alale Rezvani
Amini, Ali
Yuan, Jiann Shiun
author_facet Shalmani, Mohammad Alijanpour
Boroujeni, Alale Rezvani
Amini, Ali
Yuan, Jiann Shiun
contents High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs: micro-scale defects shrink to a few pixels and are missed. Tile-based inference preserves local detail but introduces boundary artefacts at tile edges, causing split detections and false negatives. We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets, PCB-Defect (230 images, 1704 annotations) and HRIPCB (693 images, 2 953 annotations), spanning six defect classes. We show that training-inference scale consistency is critical: a detector trained on full images collapses to mAP@50 = 0.01 under tile inference, while the same architecture trained on 640*640 tile crops achieves 0.72 and 0.94 on the two datasets respectively. We further exploited Topology-Aware Tile Merging (TA-TM), a training-free post-processing method that builds a tile-adjacency graph and adjusts boundary-sensitive detection scores using neighbour-tile agreement before global NMS. Across both datasets, adding 128 px tile overlap raises boundary-zone recall from ~26-63% to ~70-100%, TA-TM achieves the best mAP@50 on both benchmarks, and tile inference recovers 46-100% of small defects missed entirely by full-image methods. Results are consistent across datasets, confirming the generalizability of the proposed strategy. TA-TM requires no retraining and is architecture-agnostic, making it directly applicable to existing PCB inspection pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24726
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection
Shalmani, Mohammad Alijanpour
Boroujeni, Alale Rezvani
Amini, Ali
Yuan, Jiann Shiun
Computer Vision and Pattern Recognition
High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs: micro-scale defects shrink to a few pixels and are missed. Tile-based inference preserves local detail but introduces boundary artefacts at tile edges, causing split detections and false negatives. We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets, PCB-Defect (230 images, 1704 annotations) and HRIPCB (693 images, 2 953 annotations), spanning six defect classes. We show that training-inference scale consistency is critical: a detector trained on full images collapses to mAP@50 = 0.01 under tile inference, while the same architecture trained on 640*640 tile crops achieves 0.72 and 0.94 on the two datasets respectively. We further exploited Topology-Aware Tile Merging (TA-TM), a training-free post-processing method that builds a tile-adjacency graph and adjusts boundary-sensitive detection scores using neighbour-tile agreement before global NMS. Across both datasets, adding 128 px tile overlap raises boundary-zone recall from ~26-63% to ~70-100%, TA-TM achieves the best mAP@50 on both benchmarks, and tile inference recovers 46-100% of small defects missed entirely by full-image methods. Results are consistent across datasets, confirming the generalizability of the proposed strategy. TA-TM requires no retraining and is architecture-agnostic, making it directly applicable to existing PCB inspection pipelines.
title From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.24726