This paper presents a feature selection (FS) algorithm using Ant Colony Optimization (ACO). It is inspired by the particular behavior of real ants, namely by the fact that they are capable of finding the shortest path between a food source and the nest. There are considered two ACO-FS model applications for pattern recognition in remote sensing imagery: ACO Band Selection (ACO-BS) and ACO Training Label Purification (ACO-TLP). The ACO-BS reduces dimensionality of an input multispectral image data by selecting the “best” subset of bands to accomplish the classification task. The ACO-TLP selects the most informative training samples from a given set of labeled vectors in order to optimize the quality of a supervised classifier. The proposed ACO-FS model applications have been evaluated using the dataset of a LANDSAT 7 ETM+ multispectral image. The experimental results have confirmed the effectiveness of the presented approaches.

Colour is used increasingly often as quantitative indicator of combined continuous features such as temperature and humidity on geographical maps, or deformity on two axes in medical diagnosis. As such, generating flexible bivariate legends with particularly tough colour constraints for specific combinations of the variables has come to the forefront. The paper presents a systematic method of generating bivariate legends by first selecting a convenient colour subspace and then adjusting it through image processing techniques. The proposed method can generate a wide variety of legends with smart choices of parameters but remains simple enough to be worthy of consideration by specialists (in various fields) whose representations may benefit by becoming better intelligible. These legends can be used for pseudo-colouring of maps, diagrams, and many other images and graphical representations. An example is also provided for a comprehensive colouring to be used in the medical diagnosis of spine deformity.

In this study, we investigate the application of deep learning techniques for automatic segmentation of the Fluo-N2DH-GOWT1 dataset, which consists of time-lapse grayscale images of rat neural stem cells. We employ the DeepLabV3+ semantic segmentation framework with a ResNet-18 backbone, chosen for its balance between accuracy and computational efficiency on relatively small biomedical datasets. To improve generalization and robustness, we apply data augmentation strategies including rotation, scaling, shear, and reflection. The performance of the proposed model is evaluated using standard metrics such as F1-score, Intersection of Union, Precision and Recall. Experimental results demonstrate that the ResNet-18–based DeepLabV3+ achieves reliable segmentation of stem cells, effectively distinguishing cells from the background.

Although mostly harmless, hemangiomas still need to be monitored and occasionally treated to avoid complications. The method presented for accurately segmenting the hemangioma pixels involves the automatic detection of the number of classes in an initial k-means clustering, followed by binarization, morphological operations and a further adjustment of region of interest using active contours. The method has been tested on a database containing a variety of situations, including multiple hemangioma areas, differently colored and textured skin and intrusive hair. Compared to the results before the addition of active contours, the mean global score shows an improvement of more than 1% (from 96.86% to 97.92%).