This paper presents an efficient graph-based method to detect salient objects from color images and to extract their color and geometric features. Despite of the majority of the segmentation methods our method is totally adaptive and it do not require any parameter to be chosen in order to produce a better segmentation. The proposed segmentation method uses a hexagonal structure defined on the set of the image pixels ant it performs two different steps: a pre-segmentation step that will produce a maximum spanning tree of the connected components of the visual graph constructed on the hexagonal structure of an image, and the final segmentation step that will produce a minimum spanning tree of the connected components, representing the visual objects, by using dynamic weights based on the geometric features of the regions. Experimental results are presented indicating a good performance of our method.

An approach to the Colored Petri Nets (CPN)-based control is proposed in this paper. CPN are used for modeling the dynamics of both the controller and the controlled process in the control system structure. The mathematical model of the controlled process is discretized in order to use CPN in modeling the controlled process and the control system as well. The proposed controller implements a Moore automaton. The theoretical aspects of the controller design are presented in the paper, as well as aspects of the system controllability. The level control of three-tank systems is considered to validate the proposed controller. Extensive simulations are performed using the CPN Tools tool and experimental results on laboratory equipment are included.

Our goal is to organize the image contents semantically. In this paper, we propose a method to classify the images semantically, using the C-fuzzy algorithm to segment the natural scenes into perceptually uniform regions. The low-level characteristics that are taken into account are: color, texture, shape, absolute spatial arrangement, spatial coherency, and dimension. Since humans are the ultimate users of most image retrieval systems, it is important to organize the contents semantically, according to meaningful categories. This requires an understanding of the important semantic categories that humans use for image classification, and the extraction of meaningful image features that can discriminate between these categories. A lot of experiments, in which the human subjects had to group images into semantic categories and to explain the criteria for their choice, were realized. From these experiments, we identify the semantic categories (landscapes, animals, flowers, etc), the semantic indicators or intermediate descriptors and their visual characteristics.

Background/Objectives: Breast cancer diagnosis based on histopathological examination remains the most reliable and widely accepted approach in clinical practice, despite being time-consuming and prone to inter-observer variability. While deep learning methods have achieved high accuracy in medical image classification, their cross-site generalization remains limited due to differences in staining protocols and image acquisition. This study aims to evaluate and compare three clinically relevant adaptation strategies to improve model robustness under domain shift. Methods: The ResNet50V2 model, pretrained on ImageNet and further fine-tuned on the Kaggle Breast Histopathology Images dataset, was subsequently adapted to the BreaKHis dataset under three clinically relevant transfer strategies: (i) threshold calibration without retraining (site calibration), (ii) head-only fine-tuning (light FT), and (iii) full fine-tuning (full FT). Experiments were performed on an internal balanced dataset and on the public BreaKHis dataset using strict patient-level splitting to avoid data leakage. Evaluation metrics included accuracy, precision, recall, F1-score, ROC-AUC, and PR-AUC, computed per magnification level (40×, 100×, 200×, 400×). Results: Full fine-tuning consistently yielded the highest performance across all magnifications, reaching up to 0.983 ROC-AUC and 0.980 sensitivity at 400×. At 40× and 100×, the model correctly identified over 90% of malignant cases, with ROC-AUC values of 0.9500 and 0.9332, respectively. Head-only fine-tuning led to moderate gains (e.g., sensitivity up to 0.859 at 200×), while threshold calibration showed limited improvements (ROC-AUC ranging between 0.60–0.73). Grad-CAM analysis revealed more stable and focused attention maps after full fine-tuning, though they did not always align with diagnostically relevant regions. Conclusions: Our findings confirm that full fine-tuning is essential for robust cross-site deployment of histopathology AI systems, particularly at high magnifications. Lighter strategies such as threshold calibration or head-only fine-tuning may serve as practical alternatives in resource-constrained environments where retraining is not feasible.