Search

The introduction of deep learning caused a significant breakthrough in digital pathology. Thanks to its capability of mining hidden data patterns in digitised histological slides to resolve diagnostic tasks and extract prognostic and predictive information. However, the high performance achieved in classification tasks depends on the availability of large datasets, whose collection and preprocessing are still time-consuming processes. Therefore, strategies to make these steps more efficient are worth investigation. This work introduces SlideTiler, an open-source software with a user-friendly graphical interface. SlideTiler can manage several image preprocessing phases through an intuitive workflow that does not require specific coding skills. The software was designed to provide direct access to virtual slides, allowing custom tiling of specific regions of interest drawn by the user, tile labelling, quality assessment, and direct export to dataset directories. To illustrate the functions and the scalability of SlideTiler, a deep learning-based classifier was implemented to classify 4 different tumour histotypes available in the TCGA repository. The results demonstrate the effectiveness of SlideTiler in facilitating data preprocessing and promoting accessibility to digitised pathology images for research purposes. Considering the increasing interest in deep learning applications of digital pathology, SlideTiler has a positive impact on this field. Moreover, SlideTiler has been conceived as a dynamic tool in constant evolution, and more updated and efficient versions will be released in the future.

This paper presents a study on an automated system for image classification, which is based on the fusion of various deep learning methods. The study explores how to create an ensemble of different Convolutional Neural Network (CNN) models and transformer topologies that are fine-tuned on several datasets to leverage their diversity. The research question addressed in this work is whether different optimization algorithms can help in developing robust and efficient machine learning systems to be used in different domains for classification purposes. To do that, we introduce novel Adam variants. We employed these new approaches, coupled with several CNN topologies, for building an ensemble of classifiers that outperforms both other Adam-based methods and stochastic gradient descent. Additionally, the study combines the ensemble of CNNs with an ensemble of transformers based on different topologies, such as Deit, Vit, Swin, and Coat. To the best of our knowledge, this is the first work in which an in-depth study of a set of transformers and convolutional neural networks in a large set of small/medium-sized images is carried out. The experiments performed on several datasets demonstrate that the combination of such different models results in a substantial performance improvement in all tested problems. All resources are available at https://github.com/LorisNanni.

Multi-camera systems are an effective solution for perceiving large areas or complex scenarios with many occlusions. In such a setup, an accurate camera network calibration is crucial in order to localize scene elements with respect to a single reference frame shared by all the viewpoints of the network. This is particularly important in applications such as object detection and people tracking. Multi-camera calibration is a critical requirement also in several robotics scenarios, particularly those involving a robotic workcell equipped with a manipulator surrounded by multiple sensors. Within this scenario, the robot-world hand-eye calibration is an additional crucial element for determining the exact position of each camera with respect to the robot, in order to provide information about the surrounding workspace directly to the manipulator. Despite the importance of the calibration process in the two scenarios outlined above, namely (i) a camera network, and (ii) a camera network with a robot, there is a lack of standard datasets available in the literature to evaluate and compare calibration methods. Moreover they are usually treated separately and tested on dedicated setups. In this paper, we propose a general standard dataset acquired in a robotic workcell where calibration methods can be evaluated in two use cases: camera network calibration and robot-world hand-eye calibration. The Multi-Eye To Robot Indoor Calibration (METRIC) dataset consists of over 10,000 synthetic and real images of ChAruCo and checkerboard patterns, each one rigidly attached to the robot end-effector, which was moved in front of four cameras surrounding the manipulator from different viewpoints during the image acquisition. The real images in the dataset includes several multi-view image sets captured by three different types of sensor networks: Microsoft Kinect V2, Intel RealSense Depth D455 and Intel RealSense Lidar L515, to evaluate their advantages and disadvantages for calibration. Furthermore, in order to accurately analyze the effect of camera-robot distance on calibration, we acquired a comprehensive synthetic dataset, with related ground truth, with three different camera network setups corresponding to three levels of calibration difficulty depending on the cell size. An additional contribution of this work is to provide a comprehensive evaluation of state-of-the-art calibration methods using our dataset, highlighting their strengths and weaknesses, in order to outline two benchmarks for the two aforementioned use cases.

This work presents a system based on an ensemble of Convolutional Neural Networks (CNNs) and descriptors for bioimage classification that has been validated on different datasets of color images. The proposed system represents a very simple yet effective way of boosting the performance of trained CNNs by composing multiple CNNs into an ensemble and combining scores by sum rule. Several types of ensembles are considered, with different CNN topologies along with different learning parameter sets. The proposed system not only exhibits strong discriminative power but also generalizes well over multiple datasets thanks to the combination of multiple descriptors based on different feature types, both learned and handcrafted. Separate classifiers are trained for each descriptor, and the entire set of classifiers is combined by sum rule. Results show that the proposed system obtains state-of-the-art performance across four different bioimage and medical datasets. The MATLAB code of the descriptors will be available at https://github.com/LorisNanni.

Classification of biological images plays a crucial role in many biological problems, e.g. recognition of cell phenotypes and maturation levels, localization of cell organelles and histopathological classification, and holds the potential to support early diagnosis, which is critical in disease prevention. In this paper, we tested different ensemble of canonical and deep classifiers to provide accurate identification of actinic keratosis (AK), one of the most common skin lesions that could degenerate into lethal squamous cell carcinomas. We used a clinical image dataset to build and test different ensembles of support vector machines trained by handcrafted descriptors and convolutional neural networks (CNNs) for which we experimented different learning rates, augmentation techniques (e.g. warping) and topologies. Our results show that the proposed ensemble obtains performance comparable to the state of the art. To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni.

Increasing the flexibility of robots needs systems more capable in perceiving and interacting with the environment. A challenge is still to easy design the robotic system around the application, especially when the objects to be manipulated are bulky, and the relative positions between the robot and the objects to be manipulated are uncertain and high precision is required to successfully complete a task. In this paper a possible guideline to design a system capable to localize itself, identify a target, bulky, object and manipulate it, is presented. A method for tuning the impedance control parameters is shown, to keep interaction forces below dangerous values. The autonomous localization, grasping and assembly of a sidewall panel of an airplane is used as test. Experiments show that the success rate of completing a task increases, combining vision perception and force control, with respect to the single use of visual localization and position control.

CNNs and other deep learners are now state-of-the-art in medical imaging research. However, the small sample size of many medical data sets dampens performance and results in overfitting. In some medical areas, it is simply too labor-intensive and expensive to amass images numbering in the hundreds of thousands. Building Deep CNN ensembles of pre-trained CNNs is one powerful method for overcoming this problem. Ensembles combine the outputs of multiple classifiers to improve performance. This method relies on the introduction of diversity, which can be introduced on many levels in the classification workflow. A recent ensembling method that has shown promise is to vary the activation functions in a set of CNNs or within different layers of a single CNN. This study aims to examine the performance of both methods using a large set of twenty activations functions, six of which are presented here for the first time: 2D Mexican ReLU, TanELU, MeLU + GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The proposed method was tested on fifteen medical data sets representing various classification tasks. The best performing ensemble combined two well-known CNNs (VGG16 and ResNet50) whose standard ReLU activation layers were randomly replaced with another. Results demonstrate the superiority in performance of this approach.

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features now are often learned using different layers in convolutional neural networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs. Multiple learned features are combined into a single structure to work on different image classification tasks. The proposed system was derived by testing several approaches for extracting features from the inner layers of CNNs and using them as inputs to support vector machines that are then combined by sum rule. Several dimensionality reduction techniques were tested for reducing the high dimensionality of the inner layers so that they can work with SVMs. The empirically derived generic vision system based on applying a discrete cosine transform (DCT) separately to each channel is shown to significantly boost the performance of standard CNNs across a large and diverse collection of image data sets. In addition, an ensemble of different topologies taking the same DCT approach and combined with global mean thresholding pooling obtained state-of-the-art results on a benchmark image virus data set.

An ensemble of approaches for reliable person re-identification is proposed in this paper. The proposed ensemble is built combining widely used person re-identification systems using different color spaces and some variants of state-of-the-art approaches that are proposed in this paper. Different descriptors are tested, and both texture and color features are extracted from the images; then the different descriptors are compared using different distance measures (e.g., the Euclidean distance, angle, and the Jeffrey distance). To improve performance, a method based on skeleton detection, extracted from the depth map, is also applied when the depth map is available. The proposed ensemble is validated on three widely used datasets (CAVIAR4REID, IAS, and VIPeR), keeping the same parameter set of each approach constant across all tests to avoid overfitting and to demonstrate that the proposed system can be considered a general-purpose person re-identification system. Our experimental results show that the proposed system offers significant improvements over baseline approaches. The source code used for the approaches tested in this paper will be available at https://www.dei.unipd.it/node/2357 and http://robotics.dei.unipd.it/reid/.

In recent years, the field of deep learning has achieved considerable success in pattern recognition, image segmentation, and many other classification fields. There are many studies and practical applications of deep learning on images, video, or text classification. Activation functions play a crucial role in discriminative capabilities of the deep neural networks and the design of new “static” or “dynamic” activation functions is an active area of research. The main difference between “static” and “dynamic” functions is that the first class of activations considers all the neurons and layers as identical, while the second class learns parameters of the activation function independently for each layer or even each neuron. Although the “dynamic” activation functions perform better in some applications, the increased number of trainable parameters requires more computational time and can lead to overfitting. In this work, we propose a mixture of “static” and “dynamic” activation functions, which are stochastically selected at each layer. Our idea for model design is based on a method for changing some layers along the lines of different functional blocks of the best performing CNN models, with the aim of designing new models to be used as stand-alone networks or as a component of an ensemble. We propose to replace each activation layer of a CNN (usually a ReLU layer) by a different activation function stochastically drawn from a set of activation functions: in this way, the resulting CNN has a different set of activation function layers.

Industry 4.0 aims to make collaborative robotics accessible and effective inside factories. Human–robot interaction is enhanced by means of advanced perception systems which allow a flexible and reliable production. We are one of the contenders of a challenge with the intent of improve cooperation in industry. Within this competition, we developed a novel visual servoing system, based on a machine learning technique, for the automation of the winding of copper wire during the production of electric motors. Image-based visual servoing systems are often limited by the speed of the image processing module that runs at a frequency on the order of magnitude lower with respect to the robot control speed. In this article, a solution to this problem is proposed: the visual servoing function is synthesized using the Gaussian mixture model (GMM) machine learning system, which guarantees an extremely fast response. Issues related to data size reduction and collection of the data set needed to properly train the learner are discussed, and the performance of the proposed method is compared against the standard visual servoing algorithm used for training the GMM. The system has been developed and tested for a path following application on an aluminium bar to simulate the real stator teeth of a generic electric motor. Experimental results demonstrate that the proposed method is able to reproduce the visual servoing function with a minimal error while guaranteeing extremely high working frequency.

In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different strategies for extending these descriptors. The following approaches are compared: the standard approach proposed by Haralick, two methods that consider the co-occurrence matrix as a three-dimensional shape, a gray-level run-length set of features and the direct use of the co-occurrence matrix projected onto a lower dimensional subspace by principal component analysis. Texture descriptors are extracted from the co-occurrence matrix evaluated at multiple scales. Moreover, the descriptors are extracted not only from the entire co-occurrence matrix but also from subwindows. The resulting texture descriptors are used to train a support vector machine and ensembles. Results show that our novel extraction methods improve the performance of standard methods. We validate our approach across six medical datasets representing different image classification problems using the Wilcoxon signed rank test. The source code used for the approaches tested in this paper will be available at: http://www.dei.unipd.it/wdyn/?IDsezione=3314&IDgruppo_pass=124&preview=.

This paper presents two different modules for the validation of human shape presence in far-infrared images. These modules are part of a more complex system aimed at the detection of pedestrians by means of the simultaneous use of two stereo vision systems in both far-infrared and daylight domains. The first module detects the presence of a human shape in a list of areas of attention using active contours to detect the object shape and evaluating the results by means of a neural network. The second validation subsystem directly exploits a neural network for each area of attention in the far-infrared images and produces a list of votes.