• A fully automated pipeline for barley root extraction and characterization. • DeepRoot-3H : multi-head network for segmenting roots, tips, and sources. • Post-processing stage handling overlaps and dense root clusters. • Graph-based path analysis for RSML generation and trait extraction • High accuracy and robustness on challenging barley root image datasets Understanding plant root architecture under diverse environmental conditions is crucial for improving crop resilience and ensuring global food security. We present a fully automated method for segmenting barley root systems from high-resolution images and detecting keypoints such as tips and sources with high precision. At the core of our approach is DeepRoot-3H , a novel multi-head deep network built upon the DeepLabv3+ backbone, designed to jointly handle root segmentation and keypoint detection within a unified architecture. This integrated design enhances both the consistency and robustness of the outputs. A dedicated post-processing stage further refines keypoint localization, effectively handling challenges such as dense root clusters and variability in image quality. The resulting predictions are then structured into a graph representation, on which a path-walking algorithm identifies biologically meaningful connections between tips and sources. This enables the generation of RSML files and the extraction of critical morphological traits. To evaluate the system, we employ IoU and Dice scores for segmentation quality, alongside Euclidean and weighted distance metrics for tip and source detection. We also assess the biological consistency of the extracted traits—such as total root length, tortuosity, covered area, and outer angles—through correlation and discrepancy measures. Experimental results on a challenging benchmark dataset demonstrate significant improvements over existing techniques, confirming the effectiveness and reliability of our method for high-fidelity root system analysis.

In recent years, computer vision and deep learning have become increasingly important in the livestock industry, offering innovative animal monitoring and farm management solutions. This paper focuses on the critical task of cattle segmentation, an essential application for weight estimation, body condition scoring, and behavior analysis. Despite advances in segmentation techniques, accurately identifying and isolating cattle in complex farm environments remains challenging due to varying lighting conditions and overlapping objects. This study evaluates state-of-the-art segmentation models based on convolutional neural networks and transformers, which leverage self-attention mechanisms to capture long-range image dependencies. By testing these models across multiple publicly available datasets, we assess their performance and generalization capabilities, providing insights into the most effective methods for accurate cattle segmentation in real-world farm conditions. We also explore ensemble techniques, selecting pairs of segmenters with maximum diversity. The results are promising, as an ensemble of only two models improves performance over all stand-alone methods. The findings contribute to improving computer vision-based solutions for livestock management, enhancing their accuracy and reliability in practical applications.

Covid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China in late 2019 and swiftly spreading globally. Since the virus primarily impacts the lungs, analyzing chest X-rays stands as a reliable and widely accessible means of diagnosing the infection. In computer vision, deep learning models such as CNNs have been the main adopted approach for detection of Covid-19 in chest X-ray images. However, we believe that handcrafted features can also provide relevant results, as shown previously in similar image classification challenges. In this study, we propose a method for identifying Covid-19 in chest X-ray images by extracting and classifying local and global percolation-based features. This technique was tested on three datasets: one comprising 2,002 segmented samples categorized into two groups (Covid-19 and Healthy); another with 1,125 non-segmented samples categorized into three groups (Covid-19, Healthy, and Pneumonia); and a third one composed of 4,809 non-segmented images representing three classes (Covid-19, Healthy, and Pneumonia). Then, 48 percolation features were extracted and give as input into six distinct classifiers. Subsequently, the AUC and accuracy metrics were assessed. We used the 10-fold cross-validation approach and evaluated lesion sub-types via binary and multiclass classification using the Hermite polynomial classifier, a novel approach in this domain. The Hermite polynomial classifier exhibited the most promising outcomes compared to five other machine learning algorithms, wherein the best obtained values for accuracy and AUC were 98.72% and 0.9917, respectively. We also evaluated the influence of noise in the features and in the classification accuracy. These results, based in the integration of percolation features with the Hermite polynomial, hold the potential for enhancing lesion detection and supporting clinicians in their diagnostic endeavors.

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia (OED), is the most reliable way to prevent oral cancer. Computational algorithms have been used as a tool to aid specialists in this process. In recent years, CNN-based methods have gained more attention due to their improved results in nuclei segmentation tasks. Despite these relevant results, achieving high segmentation accuracy remains a challenging task. In this paper, we propose an ensemble of segmentation models to improve the performance of nuclei segmentation in OED histopathology images. The proposed ensemble consists of four CNN segmentation models, which were combined using three ensemble strategies: simple averaging, weighted averaging and majority voting, achieved accuracy of 90.69%, 90.70% and 88.49%, respectively, when applied to OED images. The model's performance was also evaluated on three publicly available datasets and achieved comparable performance to state-of-the-art segmentation methods. These values indicate that the proposed ensemble methods can be used in medical image analysis applications.

Liver cancer is one of the most common types of cancer according to World Health Statistics. Computer-aided diagnosis (CAD) systems are used in medical imaging for liver tumor identification and classification. Texture is a type of feature that can provide measurements of properties such as smoothness and regularity of the image. Handcraft techniques based on fractal geometry allow quantifying self-similarity properties present in images. However, new studies have shown that using information obtained from deep-learned feature maps can maximize the results of classical classifiers. This work presents an approach that investigates descriptors obtained by handcrafted and deep learning features, feature selection methods and the Hermite polynomial (HP) algorithm to classifier liver histological images. The results were evaluated using metrics such as accuracy (ACC) and the imbalance accuracy metric (IAM). The association with fractal features, Lasso regularization and the HP algorithm achieved 0.98 of IAM and 99.53% ACC, which was relevant when evaluated with other studies in the literature.

Deep semantic segmentation is a task that identifies objects and their boundaries in images, to do that a classification task is performed at the pixel level to tag whether a pixel belongs to an object.In skin detection, areas of images are classified as skin or non-skin regions.In this work, we report a short survey of the recent literature covering the task to help researchers in selecting the most suitable method for their application and to expand the knowledge about the available datasets for this topic.A compact empirical evaluation comparing recent models and a new ensemble model is reported.

Abstract A problem with convolutional neural networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been proposed to overcome this shortcoming with CNNs. In cases where additional samples cannot easily be collected, a common approach is to generate more data points from existing data using an augmentation technique. In image classification, many augmentation approaches utilize simple image manipulation algorithms. In this work, we propose some new methods for data augmentation based on several image transformations: the Fourier transform (FT), the Radon transform (RT), and the discrete cosine transform (DCT). These and other data augmentation methods are considered in order to quantify their effectiveness in creating ensembles of neural networks. The novelty of this research is to consider different strategies for data augmentation to generate training sets from which to train several classifiers which are combined into an ensemble. Specifically, the idea is to create an ensemble based on a kind of bagging of the training set, where each model is trained on a different training set obtained by augmenting the original training set with different approaches. We build ensembles on the data level by adding images generated by combining fourteen augmentation approaches, with three based on FT, RT, and DCT, proposed here for the first time. Pretrained ResNet50 networks are finetuned on training sets that include images derived from each augmentation method. These networks and several fusions are evaluated and compared across eleven benchmarks. Results show that building ensembles on the data level by combining different data augmentation methods produce classifiers that not only compete competitively against the state-of-the-art but often surpass the best approaches reported in the literature.

The absence of a previous collaborative manual enrolment represents a significant handicap towards designing a face verification system for face re-identification purposes. In this scenario, the system must learn the target identity incrementally, using data from the video stream during the operational authentication phase. So, manual labelling cannot be assumed apart from the first few frames. On the other hand, even the most advanced methods trained on large-scale and unconstrained datasets suffer performance degradation when no adaptation to specific contexts is performed. This work proposes an adaptive face verification system, for the continuous re-identification of target identity, within the framework of incremental unsupervised learning. Our Dynamic Ensemble of SVM is capable of incorporating non-labelled information to improve the performance of any model, even when its initial performance is modest. The proposal uses the self-training approach and is compared against other classification techniques within this same approach. Results show promising behaviour in terms of both knowledge acquisition and impostor robustness.

Bioimage classification is increasingly becoming more important in many biological studies including those that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new General Purpose (GenP) bioimage classification method that can be applied to a large range of classification problems. The GenP system we propose is an ensemble that combines multiple texture features (both handcrafted and learned descriptors) for superior and generalizable discriminative power. Our ensemble obtains a boosting of performance by combining local features, dense sampling features, and deep learning features. Each descriptor is used to train a different Support Vector Machine that is then combined by sum rule. We evaluate our method on a diverse set of bioimage classification tasks each represented by a benchmark database, including some of those available in the IICBU 2008 database. Each bioimage classification task represents a typical subcellular, cellular, and tissue level classification problem. Our evaluation on these datasets demonstrates that the proposed GenP bioimage ensemble obtains state-of-the-art performance without any ad-hoc dataset tuning of the parameters (thereby avoiding any risk of overfitting/overtraining). To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni and https://www.dropbox.com/s/bguw035yrqz0pwp/ElencoCode.docx?dl=0.

MOTIVATION: The microarray report measures the expressions of tens of thousands of genes, producing a feature vector that is high in dimensionality and that contains much irrelevant information. This dimensionality degrades classification performance. Moreover, datasets typically contain few samples for training, leading to the 'curse of dimensionality' problem. It is essential, therefore, to find good methods for reducing the size of the feature set. RESULTS: In this article, we propose a method for gene microarray classification that combines different feature reduction approaches for improving classification performance. Using a support vector machine (SVM) as our classifier, we examine an SVM trained using a set of selected genes; an SVM trained using the feature set obtained by Neighborhood Preserving Embedding feature transform; a set of SVMs trained using a set of orthogonal wavelet coefficients of different wavelet mothers; a set of SVMs trained using texture descriptors extracted from the microarray, considering it as an image; and an ensemble that combines the best feature extraction methods listed above. The positive results reported offer confirmation that combining different features extraction methods greatly enhances system performance. The experiments were performed using several different datasets, and our results [expressed as both accuracy and area under the receiver operating characteristic (ROC) curve] show the goodness of the proposed approach with respect to the state of the art. AVAILABILITY: The MATHLAB code of the proposed approach is publicly available at bias.csr.unibo.it/nanni/micro.rar.

The availability of a reliable prediction method for prediction of bacterial virulent proteins has several important applications in research efforts targeted aimed at finding novel drug targets, vaccine candidates, and understanding virulence mechanisms in pathogens. In this work, we have studied several feature extraction approaches for representing proteins and propose a novel bacterial virulent protein prediction method, based on an ensemble of classifiers where the features are extracted directly from the amino acid sequence and from the evolutionary information of a given protein. We have evaluated and compared several ensembles obtained by combining six feature extraction methods and several classification approaches based on two general purpose classifiers (i.e., Support Vector Machine and a variant of input decimated ensemble) and their random subspace version. An extensive evaluation was performed according to a blind testing protocol, where the parameters of the system are optimized using the training set and the system is validated in three different independent data sets, allowing selection of the most performing system and demonstrating the validity of the proposed method. Based on the results obtained using the blind test protocol, it is interesting to note that even if in each independent data set the most performing stand-alone method is not always the same, the fusion of different methods enhances prediction efficiency in all the tested independent data sets.

This work reports a preliminary study on the vulnerability evaluation of fingerprint verification systems to direct attacks carried out with fake fingertips created from minutiae templates. The attack is performed by presenting to the acquisition sensor a fake fingertip generated from an image reconstructed from a compromised minutiae-based template. Experiments carried out against a state-of-the-art fingerprint recognition algorithm show that the proposed attack scheme is definitely feasible and highlight a potential security threat in the use of non-encrypted minutiae-based templates.

BACKGROUND: In this paper, it is proposed an optimization approach for producing reduced alphabets for peptide classification, using a Genetic Algorithm. The classification task is performed by a multi-classifier system where each classifier (Linear or Radial Basis function Support Vector Machines) is trained using features extracted by different reduced alphabets. Each alphabet is constructed by a Genetic Algorithm whose objective function is the maximization of the area under the ROC-curve obtained in several classification problems. RESULTS: The new approach has been tested in three peptide classification problems: HIV-protease, recognition of T-cell epitopes and prediction of peptides that bind human leukocyte antigens. The tests demonstrate that the idea of training a pool classifiers by reduced alphabets, created using a Genetic Algorithm, allows an improvement over other state-of-the-art feature extraction methods. CONCLUSION: The validity of the novel strategy for creating reduced alphabets is demonstrated by the performance improvement obtained by the proposed approach with respect to other reduced alphabets-based methods in the tested problems.

In this paper, a new approach for pedestrian detection is presented. We design an ensemble of classifiers that employ different feature representation schemes of the pedestrian images: Laplacian EigenMaps, Gabor filters, and invariant local binary patterns. Each ensemble is obtained by varying the patterns used to train the classifiers and extracting from each image two feature vectors for each feature extraction method: one for the upper part of the image and one for the lower part of the image. A different radial basis function support vector machine (SVM) classifier is trained using each feature vector; finally, these classifiers are combined by the ldquosum rule.rdquo Experiments are performed on a large data set consisting of 4000 pedestrian and more than 25 000 nonpedestrian images captured in outdoor urban environments. Experimental results confirm that the different feature representations give complementary information, which has been exploited by fusion rules, and we have shown that our method outperforms the state-of-the-art approaches among pedestrian detectors.

The problem addressed in this letter concerns the multiclassifier generation by a random subspace method (RSM). In the RSM, the classifiers are constructed in random subspaces of the data feature space. In this letter, we propose an evolved feature weighting approach: in each subspace, the features are multiplied by a weight factor for minimizing the error rate in the training set. An efficient method based on particle swarm optimization (PSO) is here proposed for finding a set of weights for each feature in each subspace. The performance improvement with respect to the state-of-the-art approaches is validated through experiments with several benchmark data sets.

A minutiae-based template is a very compact representation of a fingerprint image and for a long time it has been assumed that it did not contain enough information to allow the reconstruction of the original fingerprint. This work proposes a novel approach to reconstruct fingerprint images from standard templates and investigates to what extent the reconstructed images are similar to the original ones (i.e., those the templates were extracted from). The efficacy of the reconstruction technique has been assessed by estimating the success chances of a masquerade attack against nine different fingerprint recognition algorithms. The experimental results show that the reconstructed images are very realistic and that, although it is unlikely they can fool a human expert, there is a high chance to deceive state-of-the-art commercial fingerprint recognition systems.

For a long time it has been assumed that a minutiae-based fingerprint template did not contain enough information to allow reconstructing the original fingerprint image. This work proposes an approach to reconstruct fingerprint images from ISO standard templates and investigates to what extent the reconstructed fingerprints are similar to the original ones. The results show that the reconstructed images have a very good quality and may be used to attack existing fingerprint recognition systems. Systematic studies to understand the success chances of such attacks are currently being carried out

Prediction of protein-protein interaction is a difficult and important problem in biology. In this paper, we propose a new method based on an ensemble of K-local hyperplane distance nearest neighbor (HKNN) classifiers, where each HKNN is trained using a different physicochemical property of the amino acids. Moreover, we propose a new encoding technique that combines the amino acid indices together with the 2-Grams amino acid composition. A fusion of HKNN classifiers combined with the 'Sum rule' enables us to obtain an improvement over other state-of-the-art methods. The approach is demonstrated by building a learning system based on experimentally validated protein-protein interactions in human gastric bacterium Helicobacter pylori and in Human dataset.

Digital watermarking has recently emerged as a solution to the problem of providing guarantees about copyright protection of digital images. However, several problems related to robustness of invisible watermarking techniques to malicious or nonmalicious attacks still remain unsolved. However, visible watermarking is an effective technique for preventing unauthorized use of an image, based on the insertion of a translucent mark, which provides immediate claim of ownership. This paper describes an approach for adaptive positioning of a visible watermark based on the analysis of local characteristics of the host image. Watermark positioning deals with the problem of selecting the most suitable image position to place the visible mark. Our efforts have been directed to find the best region of the host image where watermark insertion can ensure robustness and unobtrusiveness to the watermark

Describes a color-based approach to effectively resolve query-by-examples in an image database. We present a prototype database system designed to store and query a collection of ceramics. Our case study is a database of images representing ceramics from the International Museum of Ceramics in Faenza. We consider statistical features on color distribution, not requiring a strong segmentation procedure to detect the object from the background. Results on a collection of about 2000 images are reported providing a validation of the approach.

In this work, we introduce a new approach to automatic fingerprint classification. The directional image is partitioned into "homogeneous" connected regions according to the fingerprint topology, thus giving a synthetic representation which can be exploited as a basis for the classification. A set of dynamic masks, together with an optimization criterion, are used to guide the partitioning. The adaptation of the masks produces a numerical vector representing each fingerprint as a multidimensional point, which can be conceived as a continuous classification. Different search strategies are discussed to efficiently retrieve fingerprints both with continuous and exclusive classification. Experimental results have been given for the most commonly used fingerprint databases and the new method has been compared with other approaches known in the literature: As to fingerprint retrieval based on continuous classification, our method gives the best performance and exhibits a very high robustness.