Study Shows Synthetic Data Can Improve CNN-Based Masonry Crack Detection
Researchers tested combining real and synthetic crack images to train convolutional neural networks for detecting cracks in masonry buildings. The study found that a mix of 20% real data and 80% synthetic data achieved better results than using only real data, with an F1-score of 76% and mean IoU of 80%. This approach could reduce the time and cost of collecting large datasets for building health monitoring applications.
A research team explored using synthetic crack data generated by an overlay tool to supplement real masonry crack images for training deep learning models. The real dataset consisted of crack images from buildings in Bologna, Italy, while synthetic data was created by algorithmically adding cracks to background images with controlled orientation and placement. After identifying InceptionV4 as the best-performing architecture when trained on real data alone, the researchers tested six different ratios of synthetic to real data. The optimal configuration combined 80% synthetic data with 20% real data, achieving an F1-score of 76% and mean Intersection over Union of 80%—outperforming the real-data-only baseline. The findings suggest that synthetic data generation could substantially reduce the labor-intensive process of collecting sufficient real-world training data while simultaneously improving model accuracy for automated crack detection in building maintenance.
What's missing
The study does not discuss potential limitations of the synthetic data generation method, such as whether the overlay approach captures the full complexity of real crack patterns, or whether results generalize to masonry types and environmental conditions beyond the Bologna region. The paper also does not address computational costs of synthetic data generation or provide details on the background image sources used for crack overlay.
What different sources said
- arXiv cs.LGCenter
Balancing Real and Synthetic Data for CNN-based Masonry Crack Detection
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.