Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Scene recognition is the task of identifying the environment shown in an image. Spectral filter array cameras allow for fast capture of multispectral images. Scene recognition in multispectral images is usually performed after demosaicing the raw image. Along with adding latency, this makes the classification algorithm limited by the artifacts produced by the demosaicing process. This work explores scene recognition performed on raw spectral filter array images using convolutional neural networks. For this purpose, a new raw image dataset is collected for scene recognition with a spectral filter array camera. The classification is performed using a model constructed based on the pretrained Places-CNN. This model utilizes all nine channels of spectral information in the images. A label mapping scheme is also applied to classify the new dataset. Experiments are conducted with different pre-processing steps applied on the raw images and the results are compared. Higher-resolution images are found to perform better even if they contain mosaic patterns.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10974342 | PMC |
| http://dx.doi.org/10.3390/s24061961 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
GPT-4V shows human-like social perceptual capabilities at phenomenological and neural levels.
Imaging Neurosci (Camb)
September 2025
Turku PET Centre, University of Turku, Turku, Finland.
Humans navigate the social world by rapidly perceiving social features from other people and their interaction. Recently, large-language models (LLMs) have achieved high-level visual capabilities for detailed object and scene content recognition and description. This raises the question whether LLMs can infer complex social information from images and videos, and whether the high-dimensional structure of the feature annotations aligns with that of humans.
View Article and Find Full Text PDFThe impact of scene inversion on early scene-selective activity.
Biol Psychol
September 2025
Department of Psychology, Wright State University, Dayton OH. Electronic address:
Category-selectivity is a ubiquitous property of high-level visual cortex manifested in distinct cortical responses to faces, objects, and scenes. These signatures emerge early during visual processing, with each category sensitive to specific types of visual information at different time points. However, it is still not clear what information is extracted during early scene-selective processing, as scenes are rich, complex, and multidimensional stimuli.
View Article and Find Full Text PDFDeep learning-driven multi-hierarchical granularity integration for surgical scene understanding: experimental study.
Int J Surg
September 2025
Institute of Medical Robotics and Intelligent Systems, Tianjin University, Tianjin, China.
Background: A comprehensive understanding of surgical scenes by computers is a crucial foundation for achieving intelligent surgical assistance and autonomous decision-making. Surgical scene information encompasses coarse-grained data reflecting the overall process and fine-grained details showcasing specific operations. This study aims to construct a standardized, full-grained annotation dataset for laparoscopic radical nephrectomy and develop a deep learning framework for multi-hierarchical granularity integration, providing support for clinical intelligent applications.
View Article and Find Full Text PDFSonar image denoising based on clustering and Bayesian sparse coding.
PLoS One
September 2025
School of Electrical and Information Technology, Yunnan Minzu University, Kunming, China.
Side-scan sonar image (SSI) are often affected by a combination of multiplicative speckle noise and additive noise, which degrades image quality and hinders target recognition and scene interpretation. To address this problem, this paper proposes a denoising algorithm that integrates non-local similar block clustering with Bayesian sparse coding. The proposed method leverages cross-scale structural features and noise statistical properties of image patches, and employs a similarity metric based on the Equivalent Number of Looks (ENL) along with an improved K-means clustering algorithm to achieve accurate classification and enhance intra-class noise consistency.
View Article and Find Full Text PDFInfluence of simulated spatial conditions and reverberation on speech intelligibility prediction accuracy with the Simulation Framework for Auditory Discrimination Experiments (FADE).
Hear Res
August 2025
Medizinische Physik and Cluster of Excellence Hearing4all, Carl von Ossietzky Universität Oldenburg, Germany. Electronic address:
Considering complex acoustic scenes in rehabilitative audiology and hearing device assessments requires understanding the influence of multiple interacting factors. Speech intelligibility models provide a systematic way to explore and predict these effects. However, they must be able to deal with acoustic conditions including different numbers and spatial configurations of sound sources, and the presence of reverberation.
View Article and Find Full Text PDF