Region-Aware Multi-View Inspection Using Deep Learning and Domain-Informed Decision Fusion

Srivishnu Ethirajulu Krishnaraj; Rishikesh R. Chopade

cs.CVOct 21, 2026

Region-Aware Multi-View Inspection Using Deep Learning and Domain-Informed Decision Fusion

Authors: Srivishnu Ethirajulu Krishnaraj, Rishikesh R. Chopade

Organizations: Bosch Limited, India

Abstract

Automated optical inspection of precision components with tiny surface defects remains challenging when different regions of the same component exhibit different defect characteristics and, therefore, different acceptance criteria. This paper presents a region-aware, dual-model inspection framework that combines instance segmentation of localized seat-region defects with image-level classification of global shaft-region anomalies. Rather than treating these two model detections as sufficient evidence for component rejection, a deterministic decision fusion layer that formalizes industrial Standard Operating Procedures is applied to the model outputs to make the final component level decision. A PLC-synchronized imaging system acquires 18 seat and 18 shaft images over a full 360-degree rotation to provide multi-view circumferential coverage. The framework was evaluated on 380 automotive fuel injector needles, covering representative operational defect types, using identical model predictions in all configurations. Direct model-output aggregation via simple union logic (where any single-view detection flags a rejection) identified all 104 non-conforming components but produced a component level false rejection rate of 57.6%. Inclusion of a complete decision layer maintained the observed non-conforming (NOK) recall of 100% while reducing the false rejection rate to 10.9%, corresponding to an 81.1% reduction in false-positive component decisions. The results demonstrate that formalized manufacturing acceptance criteria can complement sensitive visual models by translating frame-level detections into practical and traceable component-level decisions.

Figures & tables

Panel of Figure 1 — Fig. 1: Overall system architecture of the proposed PLC-synchronized, region-aware dual-model inspection pipeline (two camera views).

Fig. 2: Region-wise decomposition of the inspected component, including the upper one-third tip region, lower two-thirds seat region, and critical-line/edge region.

Parameter	Configuration
Views per rotation	18 views at 20 ∘ angular intervals
Seat camera	Basler ace U acA1300-200uc with Computar MLM-3XMP Lens
Shaft camera	Basler ace U acA1300-200uc with Fujifilm Fujinon HF35HA-1B lens
Lighting	$420\times 20$ mm LED bar light
Rotary fixture	Servo-driven
Seat-region resolution	$1280\times 1024$ pixels

TABLE I: Multi-view acquisition and inspection system configuration.

Fig. 3: Camera alignment and close-up view of the rotating component during inspection.

Category	Number of Images
Delamination	1,099
Grinding Marks	172
Droplet	671
Tip Damage	222
Grinding at Neck	27
Grinding Not Done	74

TABLE II: Class-wise image distribution of the seat-region dataset.

Subset	Number of Images	Approximate Percentage
Training	2,099	80%
Validation	261	10%
Test	261	10%
Total	2,621	100%

TABLE III: Partition of the seat-region dataset.

Parameter	Configuration
Architecture	Mask R-CNN ResNet-50-FPN V2
Framework	PyTorch and Torchvision
Initialization	COCO-pretrained Mask R-CNN V2 weights
Evaluated defect categories	Eight defect categories
Explicit preprocessing	None
Data augmentation	None

TABLE IV: Model and training configuration for Model I.

Class	Images	Approximate Percentage
Rotation OK	7,479	94.3%
Rotation Bad	454	5.7%
Total	7,933	100%

TABLE V: Class distribution of the shaft-region dataset.

Subset	Rotation OK	Rotation Bad	Total
Training	5,983	363	6,346
Validation	747	45	792
Test	749	46	795
Total	7,479	454	7,933

TABLE VI: Partition of the shaft-region dataset.

Parameter	Configuration
Model	EfficientNetV2-S
Framework	PyTorch and Torchvision
Initialization	ImageNet-pretrained weights
Input resolution	$224\times 224$ pixels
Input preprocessing	RGB conversion, resizing, and ImageNet normalization
Training augmentation	Brightness and contrast adjustment using ColorJitter

TABLE VII: Model and training configuration for Model II.

Fig. 4: Examples of seat- and shaft-region model outputs.

Component Status	Number of Components
Conforming/OK	276
Non-conforming/NOK	104
Total	380

TABLE VIII: Component-level distribution of the evaluation dataset.

Model	Metric	Result
Model I	Instance-level F1-score	43.79%
Model I	Instance-level recall	37.19%
Model I	Mean bounding-box IoU a	0.7069
Model II	Image-level accuracy	99.62%
Model II	Macro F1-score	98.32%
Model II	Rotation Bad recall	100% $(46/46)$

TABLE IX: Held-out test performance of the two inspection models.

Metric	MO	G-I	G-II	G-III	CDL
TP	104	104	104	104	104
FN	0	0	0	0	0
FP	159	120	40	114	30
TN	117	156	236	162	246
NOK recall (%)	100.0	100.0	100.0	100.0	100.0
FRR (%)	57.6	43.5	14.5	41.3	10.9

TABLE X: Component-level functional rule-group ablation results.

Industrial Inspection

Industrial inspection uses sensing, computer vision, and robotics to detect, measure, and explain defects and verify product or infrastructure quality.

See all 119 papers

Jul 6, 2026

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation when deployed in unseen production scenarios, and (2) most benchmarks neglect severity-aware assessment, which is critical for risk control and yield optimization. To address these limitations, we design two complementary tracks: Track 1 (Cross-Scenario Defect Detection) targets accurate defect detection, localization, and classification across diverse unseen production environments; Track 2 (Fine-Grained Severity Grading) requires assigning each detected defect an industry-standard severity level, including Acceptable, Marginal NG, NG, and Gross NG. We construct a large-scale industrial dataset of high-resolution microscopic images spanning seven representative defect categories, comprising over 3,800 images with pixel-level instance annotations for Track 1 and over 2,600 images with severity-grade labels for Track 2. The challenge attracted 86 registered participants with 130 submissions; during the final testing phase, 21 teams submitted results and 12 teams provided models with technical reports. The resulting benchmark, together with the diverse and effective solutions contributed by participating teams, sets a new standard for industrial defect analysis research.

Wei Sun, Weixia Zhang, Linhan Cao +30

East China Normal University, Shanghai Jiao Tong University, Tsinghua Shenzhen International Graduate School, and Universit´e de Nantes.

Industrial Anomaly Detection Industrial Inspection Cross-Domain Generalization Automated Grading

Ask PDF

Feb 18, 2026

World Model Failure Classification and Anomaly Detection for Autonomous Inspection

Autonomous inspection robots for monitoring industrial sites can reduce costs and risks associated with human-led inspection. However, accurate readings can be challenging due to occlusions, limited viewpoints, or unexpected environmental conditions. We propose a hybrid framework that combines supervised failure classification with anomaly detection, enabling classification of inspection tasks as a success, known failure, or anomaly (i.e., out-of-distribution) case. Our approach uses a world model backbone with compressed video inputs. This policy-agnostic, distribution-free framework determines classifications based on two decision functions set by conformal prediction (CP) thresholds before a human observer does. We evaluate the framework on gauge inspection feeds collected from office and industrial sites and demonstrate real-time deployment on a Boston Dynamics Spot. Experiments show over 90% accuracy in distinguishing between successes, failures, and OOD cases, with classifications occurring earlier than a human observer. These results highlight the potential for robust, anticipatory failure detection in autonomous inspection tasks or as a feedback signal for model training to assess and improve the quality of training data. Project website: https://autoinspection-classification.github.io

Michelle Ho, Muhammad Fadhil Ginting, Isaac R. Ward +4

Stanford University, Stanford, CA 94305 USA · Field AI, Mission Viejo, CA 92691 USA

Robot Failure Detection Robotic Anomaly Detection Robotic Inspection Anomaly Detection OOD Detection

Ask PDF

Aug 22, 2026

Trustworthy Visual Quality Inspection under Data Scarcity in Manufacturing

Automated visual inspection in manufacturing aims to replace slow and inconsistent manual checks, but its economic value depends on whether its decisions can be trusted enough to automate routine inspection while reserving human expertise for ambiguous cases. In production-line settings, defective samples are scarce, since the process is optimized to produce good parts, which limits any learning-based inspector trained on real data alone. Compounding this, defect decisions emitted as hard labels with no confidence estimate carry an asymmetric cost: a false reject wastes a good product, while a false accept may increase the risk of undetected defects progressing through the production process. We address both problems by mitigating data scarcity through the generation of synthetic defective samples with a diffusion model, and meeting the need for confidence-aware decisions with a Bayesian classifier that defers ambiguous units to human review rather than misclassifying them. These components are embedded in a staged pipeline of successive, complementary checks. We evaluate how synthetic augmentation affects classification and localization on a test set of real defects, and examine the system's trustworthiness at three points: the decision, the synthetic data, and the pipeline structure. This work-in-progress reports preliminary results suggesting that diffusion-generated defects, combined with uncertainty-aware classification, can lower the cost of reaching a trustworthy, deployable inspection model under data scarcity.

Panagiotis Sapoutzoglou, Jessy Ribaira, Martin Kanounnikoff +3

National Technical University of Athens, Athens, Greece · German Aerospace Center (DLR), Germany · Philips, High Tech Campus 52, 5656 AG Eindhoven, The Netherlands +1

Industrial Inspection Industrial Anomaly Detection Synthetic Data Augmentation

Ask PDF

Abstract

Industrial Inspection

Explore similar work

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

World Model Failure Classification and Anomaly Detection for Autonomous Inspection

Trustworthy Visual Quality Inspection under Data Scarcity in Manufacturing