Towards Cognitive Defect Analysis in Active Infrared Thermography with Vision-Text Cues

Mohammed Salah; Eman Ouda; Giuseppe Dell'Avvocato; Fabrizio Sarasini; Ester D'Accardi; Jorge Dias; Davor Svetinovic; Stefano Sfarra

cs.CVMar 11, 2026

Towards Cognitive Defect Analysis in Active Infrared Thermography with Vision-Text Cues

Authors: Mohammed Salah, Eman Ouda, Giuseppe Dell'Avvocato, Fabrizio Sarasini, Ester D'Accardi, Jorge Dias, Davor Svetinovic, Stefano Sfarra,

Abstract

Active infrared thermography (AIRT) is currently witnessing a surge of artificial intelligence (AI) methodologies being deployed for automated subsurface defect analysis of high performance carbon fiber-reinforced polymers (CFRP). Deploying AI-based AIRT methodologies for inspecting CFRPs requires the creation of time consuming and expensive datasets of CFRP inspection sequences to train neural networks. To address this challenge, this work introduces a novel language-guided framework for cognitive defect analysis in CFRPs using AIRT and vision-language models (VLMs). Unlike conventional learning-based approaches, the proposed framework does not require developing training datasets for extensive training of defect detectors, instead it relies solely on pretrained multimodal VLM encoders coupled with a lightweight adapter to enable generative zero-shot understanding and localization of subsurface defects. By leveraging pretrained multimodal encoders, the proposed system enables generative zero-shot understanding of thermographic patterns and automatic detection of subsurface defects. Given the domain gap between thermographic data and natural images used to train VLMs, an AIRT-VLM Adapter is proposed to enhance the visibility of defects while aligning the thermographic domain with the learned representations of VLMs. The proposed framework is validated using three representative VLMs; specifically, GroundingDINO, Qwen-VL-Chat, and CogVLM. Validation is performed on 25 CFRP inspection sequences with impacts introduced at different energy levels, reflecting realistic defects encountered in industrial scenarios. Experimental results demonstrate that the AIRT-VLM adapter achieves signal-to-noise ratio (SNR) gains exceeding 10 dB compared with conventional thermographic dimensionality-reduction methods, while enabling zero-shot defect detection with intersection-over-union values reaching 70%.

Figures & tables

Fig. 1: Front-side view of the impacted specimens, subjected to low-velocity impact at 5 J and 15 J.

Fig. 2: Top: Front-side heating with pulsed flash lamps (A.1-A.2) and front-side long-pulse halogen heating (A.3). Bottom: Schematic representation of inspection setup.

Fig. 3: Top: Backside heating with flash (B.1) and halogen lamp (B.2). Bottom: Schematic representation of transmission inspection setup.

Fig. 4: Overview of the defect analysis framework. The inspection sequence is preprocessed to generate a compact single image representation similar to the VLMs pretraining domain. Consequently, a VLM generates bounding boxes for defects.

Defect Class	Temp.	Samples	Metric	Raw	TSR	PCA	DAT	1D-DCAE-AIRT	C-AET	Ours
5 J	Ambient	6	Contrast	0.207	0.241	0.302	0.366	0.383	0.361	0.478
	Ambient	6	SNR (dB)	21.75	24.50	30.71	33.48	35.83	34.11	42.18
	$-70^{\circ}$ C	7	Contrast	0.198	0.229	0.289	0.351	0.366	0.344	0.456
	$-70^{\circ}$ C	7	SNR (dB)	20.90	23.62	29.40	32.05	34.21	32.88	40.27
15 J	Ambient	7	Contrast	0.227	0.287	0.387	0.395	0.436	0.387	0.534
	Ambient	7	SNR (dB)	22.11	24.74	32.95	38.29	38.37	36.58	43.19

TABLE I: Quantified contrast and SNR for the AIRT-VLM adapter representation benchmarked against state-of-the-art thermography dimensionality reduction methods, TSR, PCA, DAT [ 22 ] , 1D-DCAE-AIRT [ 23 ] , and C-AET [ 29 ] , under ambient and low-temperature (

-70^{\circ}

C) conditions.

Panel of Table 6 — TABLE II: Qualitative comparisons between state-of-the-art AIRT dimensionality reduction techniques: TSR [ 33 ] , PCA [ 34 ] , DAT [ 22 ] , 1D-DCAE-AIRT [ 23 ] , C-AET [ 29 ] , and the proposed AIRT-VLM adapter representation, under ambient and low-temperature ( $-70^{\circ}$ C) conditions.

Fig. 5: Aggregate a) contrast and b) SNR on all 25 CFRP inspection sequences.

Fig. 6: IoU and normalized center distance achieved by Qwen-VL, CogVLM, and GroundingDINO when coupled with AIRT-VLM adapter on all 25 CFRP inspection sequences. The performances of these models are also presented when coupled with state-of-the-art AIRT dimensionality reduction methods.

Panel of Table 9 — TABLE III: Defect detection results of Qwen-VL, CogVLM, and GroundingDINO coupled with the AIRT-VLM adapter, under ambient and low-temperature. The results show consistent defect detection performances across all samples.

Metric	Average Pooling	Max Pooling	PCA
Contrast	0.522	0.471	0.547
SNR (dB)	42.87	39.18	42.41
IoU	0.691	0.539	0.701
Normalized Center Distance	0.0138	0.0378	0.0118

TABLE IV: Quantified performances of average, max, and PCA pooling operations.

Metric	Average Pooling	NMS
IoU	0.691	0.707
Normalized Center Distance	0.0138	0.0136
Execution Time (s)	4.3	37.8

TABLE V: Defect detection performance when the pooling operation is replaced with non-maximum suppression (NMS).

Fault Detection

Fault detection identifies abnormal behavior in machines, sensors, infrastructure, software, and autonomous systems before it causes harm or disruption.

See all 104 papers

Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection
Mar 13, 2026Eman Ouda, Mohammed Salah, Arsenii O. Chulkov +4Thermal Imaging Anomaly Detection
Khalifa University of Science and Technology, Department of Aerospace Engineering, Abu Dhabi, United Arab Emirates · National Research Tomsk Polytechnic University, Russia · Academy of Fine Arts of Naples, Naples, Italy +3
Computational Depth Measurement in Thermographic Video: Overcoming Spatial Overfitting via Spatio-Temporal Decoupling
Aug 29, 2026Zain Ul Abidin, Habeeban Memon, Junaid AhmedNon-Destructive Testing Depth Estimation
Department of Computer Systems Engineering, Sukkur IBA University, Sukkur, Pakistan
Data-Driven Automated Identification of Optimal Feature-Representative Images in Infrared Thermography Using Statistical and Morphological Metrics
Apr 9, 2026Harutyun Yagdjian, Martin GurkaNon-Destructive Testing Thermal Imaging
Leibniz-Institut für Verbundwerkstoffe GmbH, Erwin-Schrödinger-Straße 58, 67663 Kaiserslautern

Mar 13, 2026J/K move · Enter open · S save

Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection

Eman Ouda, Mohammed Salah, Arsenii O. Chulkov, Gianfranco Gargiulo+3

Khalifa University of Science and Technology, Department of Aerospace Engineering, Abu Dhabi, United Arab Emirates · National Research Tomsk Polytechnic University, Russia · Academy of Fine Arts of Naples, Naples, Italy+3

Thermal Imaging Anomaly Detection Multimodal Anomaly Detection

Open paper AskPDF arXiv

Authenticity and condition assessment are central to conservation decision-making, yet interpretation and reporting of thermographic output remain largely bespoke and expert-dependent, complicating comparison across collections and limiting systematic integration into conservation documentation. Pulsed Active Infrared Thermography (AIRT) is sensitive to subsurface features such as material heterogeneity, voids, and past interventions; however, its broader adoption is constrained by artifact misinterpretation, inter-laboratory variability, and the absence of standardized, explainable reporting frameworks. Although multi-modal thermographic processing techniques are established, their integration with structured natural-language interpretation has not been explored in cultural heritage. A fully automated thermography-vision-language model (VLM) framework is presented. It combines multi-modal AIRT analysis with modality-aware textual reporting, without human intervention during inference. Thermal sequences are processed using Principal Component Thermography (PCT), Thermographic Signal Reconstruction (TSR), and Pulsed Phase Thermography (PPT), and the resulting anomaly masks are fused into a consensus segmentation that emphasizes regions supported by multiple thermal indicators while mitigating boundary artifacts. The fused evidence is provided to a VLM, which generates structured reports describing the location of the anomaly, thermal behavior, and plausible physical interpretations while explicitly acknowledging the uncertainty and diagnostic limitations. Evaluation on two marquetries demonstrates consistent anomaly detection and stable structured interpretations, indicating reproducibility and generalizability across samples.

Abstract

Fault Detection

Explore similar work

Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection

Computational Depth Measurement in Thermographic Video: Overcoming Spatial Overfitting via Spatio-Temporal Decoupling

Data-Driven Automated Identification of Optimal Feature-Representative Images in Infrared Thermography Using Statistical and Morphological Metrics