25 papers · ranked by Valyu relevance
Aashish Dhawan, Mudgal, Divyanshu
— the major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can overcome the scarcity of data to produce results comparable to previous benchmark…
Chloe A. Game, Nils Piechaud, Kerry L. Howell
Deep learning (DL) is a powerful tool to extract ecological information from large image datasets efficiently and consistently. However, applying these methods remains challenging, due in part to the complexity of DL workflows and the dynamic nature of available tools. To address this, we created a practical guide and…
Serghei Musaji, Pamela Kibsey, Andrei Musaji
This paper reflects on the development and performance of an advanced artificial intelligence (AI) algorithm for the automated processing and classification of Gram stain images obtained from actual microbiology samples used in clinical microbiology. The aim of the project was to effectively categorize non-standardized…
Amr Aboghanem, Mohamed Abd Elfattah, Hanan M. Amer, Abeer Tawkol Khalil
Aerial image classification is considered an open challenge due to its properties and the presence of various complex images. Given the complexity and variation in aerial images, this paper proposes two hybrid models for classification. The first hybrid model combines features extracted from ResNet-50 and the Vision…
Shangdong Liu, Wenxiang Wu, Haijun Chen, Shuai You + 5 more
Cordyceps sinensis (C. sinensis) is a valuable herbal medicine with wide-ranging applications. However, automating C. sinensis recognition is challenging due to the high morphological similarity and limited phenotypic variation among its subspecies. In this paper, we propose a novel approach called Progressive Feature…
Héctor Guillen-Bonilla, José Trinidad Guillen-Bonilla, Maricela Jiménez-Rodríguez, Alex Guillen-Bonilla + 4 more
In this paper, an RGB image with $S$ is separated by its channels, obtaining an image in each color channel $S_{R}$, $S_{G}$ and $S_{B}$. The Vectorial Image Representation on the Texture Space (VIR-TS) transform is calculated for each channel; ergo, each image is represented with a given vector, $S_{R}\rightarrow…
Rui Xing, Runmin Cong, Yingying Wu, Can Wang + 4 more
Understanding the dietary preferences of ancient societies and their evolution across periods and regions is crucial for revealing human–environment interactions. Seeds, as important archaeological artifacts, represent a fundamental subject of archaeobotanical research. However, traditional studies rely heavily on…
Belhasin, Omer, Golan, Shelly + 3 more
Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or training data are limited. Conventional classification approaches typically train models to directly predict class labels from input images, but…
M. A. Rasel, Sameem Abdul Kareem, Unaizah Obaidellah
Early diagnosis of melanoma, which can save thousands of lives, relies heavily on the analysis of dermoscopic images. One crucial diagnostic criterion is the identification of unusual pigment network (PN). However, distinguishing between regular (typical) and irregular (atypical) PN is challenging. This study aims to…
Yue Huang, Yinghao Gao, Xudong Luo, Menglong Guo + 4 more
In recent years, the authenticity of sliced mutton has become a growing concern due to the incorporation of non-mutton ingredients and the increasing use of processed and reconstituted meat products. In this study, a low-cost and non-destructive authentication method integrating smartphone-based image acquisition with…
Shiqi Zhang, Peng Li, Jyh-Cheng Chen, Kuangyu Shi
Class imbalance remains a critical challenge in image classification, where underrepresented classes often receive insufficient training attention and exhibit poor recognition performance. In this study, we propose a hybrid framework that combines weighted sampling with frequency-aware spatial attention (WSFSA) to…
Rahele Allahverdi, Mohammad Mahdi Dehshibi, Azam Bastanfard, Daryoosh Akbarzadeh
Solving pattern recognition problems using imbalanced databases is a hot topic, which entices researchers to bring it into focus. Therefore, we consider this problem in the application of Sassanid coins classification. Our focus is not only on proposing EigenCoin manifold with Bhattacharyya distance for the…
Shawn T. Schwartz, Whitney L.E. Tsai, Elizabeth A. Karan, Mark S. Juhn + 4 more
Advances in digital imaging and software tools have provided increasingly accessible datasets and methods for analyzing color evolution. Despite the variety of computational packages available, most rely on color classification before running analyses. Previous methods to characterize color limit the ability to analyze…
Ihab Asaad, Maha Shadaydeh, Joachim Denzler
Patch-wise multi-label classification provides an efficient alternative to full pixelwise segmentation on high-resolution images, particularly when the objective is to determine the presence or absence of target objects within a patch rather than their precise spatial extent. This formulation substantially reduces…
Gül Ateş, Fuat Türk, Elif Tuba Akçın, Müjgan Güngör + 1 more
Highlights What are the main findings?1. A hybrid HGWO-PSO + SVM pipeline achieved the best five-class performance on panoramic radiographs (Accuracy 73.15%, macro-F1 0.728), outperforming a baseline CNN and conventional ML models. 2. A patient-level 80/20 split and 5-fold CV showed stable results despite class…
Mateus Braga Oliveira, Heder Soares Bernardino, Alex Borges Vieira, Antônio Arbex Barroso + 1 more
The automated classification of animals from photos is important in ecology and conservation biology for organizing and understanding the immense diversity of species, as well as facilitating effective conservation and management practices. It is equally important for disease surveillance systems, allowing prompt…
Janis Mohr, Jörg Frochte
Convolutional neural networks (CNNs) have been widely used in the computer vision community, significantly improving the state-of-the-art. But learning good features often is computationally expensive in machine learning settings and is especially difficult when there is a lack of data. One-shot learning is one such…
Fabio Neves Souza, Adedayo Michael Awoniyi, Rodrigo Dalvit Carvalho da Silva, Nivison Nery Jr + 9 more
Effective management of rodent pests necessitates efficient population surveillance. Many of the available methods currently used for estimating rodent populations are either costly or time-intensive. Rodent trapping demands significant resources, while tracking plates (TP) require high technical expertise and weeks to…
E. Ramírez-Aportela, O. L. Zarrabeitia, Y. C. Fonseca, T. Ceska + 3 more
Finally, given an experimental image y and a set of reference images {x_i_}, the alignment problem consists in finding both the reference and the geometric transformation that best match y. Each reference x_i_ can be transformed according to a set of parameters θ (e.g., in-plane rotation and translation), yielding the…
Wen Han Chia, Ilia Jahanshahi, Le Yang Loh, Anqi Zheng + 4 more
Community science platforms like iNaturalist generate unprecedented volumes of biodiversity data, but their scientific utility depends critically on accurate species identification—a persistent challenge when contributors often lack taxonomic expertise. We developed “LizardLens”, a two-stage machine learning pipeline…
Authors not listed
Localized detection of hydrogen permeation in steel membranes is crucial for practical applications but remains challenging. We present a reflective microscopy (RM) approach combined with machine learning (ML)-driven image analysis to address this issue. Hydrogen permeation in press-hardened steel alters the…
Authors not listed
Infrared (IR) spectroscopy provides rich structural information but interpreting spectra at scale remains challenging. Here we introduce j-IR-vis, a vision-based neural model that learns chemically interpretable representations directly from IR spectra for functional-group prediction and downstream molecular…
Authors not listed
Terminally labeled DNA oligonucleotides have wide applications in modern biology and biotechnological applications. It has been observed that the fluorescent intensity of light released from these fluorescent labels is heavily influenced by the terminal sequence of nucleotides. Recent studies have assayed and published…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Authors not listed
Olfaction arises from the interaction of odorants with olfactory receptors, a process shaped by molecular geometry, electron distribution, and conformational preference. We present ConfDENSE, a Set2Set enhanced PointNet model that learns directly from Hirshfeld promolecule electron-density point clouds, preserving full…