Brain tumor segmentation is a routine process in a clinical setting and provides useful information for diagnosis and treatment planning. Manual segmentation, performed by physicians or radiologists, is a time-consuming task due to the large quantity of medical data generated presently. Hence, automatic segmentation methods are needed, and several approaches have been introduced in recent years including the Localized Region-based Active Contour Model (LRACM). There are many popular LRACM, but each of them presents strong and weak points. In this paper, the automatic selection of LRACM based on image content and its application on brain tumor segmentation is presented. Thereby, a framework to select one of three LRACM, i.e., Local Gaussian Distribution Fitting (LGDF), localized Chan-Vese (C-V) and Localized Active Contour Model with Background Intensity Compensation (LACM-BIC), is proposed. Twelve visual features are extracted to properly select the method that may process a given input image. The system is based on a supervised approach. Applied specifically to Magnetic Resonance Imaging (MRI) images, the experiments showed that the proposed system is able to correctly select the suitable LRACM to handle a specific image. Consequently, the selection framework achieves better accuracy performance than the three LRACM separately.

The quality assurance of fabrics is a fundamental issue in the textile manufacturing industry. An automatic and accurate detection of defects is one of the most important and challenging tasks in order to guarantee the quality of fabrics. In this paper, we propose an approach for defect detection on textiles with patterned texture, using a rule-based classification system and local binary features. In our proposal, rules are automatically learned from textile samples using a rough-set-based approach. The proposed system analyzes the texture of fabrics using a combination of local binary features, which have shown to be highly discriminatory. Our approach is performed in two stages: training and testing. During the training stage, binary features from both defective and defect-free images are extracted and used to formulate an ensemble of rough-set-based rules. For the testing stage, we submit different samples of fabrics and they are classified as defective or defect-free. The proposed method is quantitatively evaluated on an extensive dataset of images of defective fabrics. These experiments show that the proposed approach results in a higher accuracy, in comparison with those obtained by the state-of-the-art methods.

In this article, we introduce an image enhancing approach for transforming dark images into lightened scenes, and we evaluate such method in different perceptual color spaces, in order to find the best-suited for this particular task. Specifically, we use a classical color transfer method where we obtain firstorder statistics from a target image and transfer them to a dark input, modifying its hue and brightness. Two aspects are particular to this work, the application of color transfer on dark imagery and in the search for the best color space for the application. In this regard, the tests performed show an accurate transference of colors when using perceptual color spaces, being RLAB the best color space for the procedure. Our results show that the methodology presented in this paper can be a good alternative to low-light or night vision processing techniques. Besides, the proposed method has a low computational complexity, property that is important for real time applications or for low-resource systems. This method can be used as a preprocessing step in order to improve the recognition and interpretation of dark imagery in a wide range of applications.

Autonomous robot visual navigation is a fundamental locomotion task based on extracting relevant features from images taken from the surrounded environment to control an independent displacement. In the navigation, the use of a known visual map helps obtain an accurate localization, but in the absence of this map, a guided or free exploration pathway must be executed to obtain the images sequence representing the visual map. This paper presents an appearance-based localization method based on a visual map and an end-to-end Convolutional Neural Network (CNN). The CNN is initialized via transfer learning (trained using the ImageNet dataset), evaluating four state-of-the-art CNN architectures: VGG16, ResNet50, InceptionV3, and Xception. A typical pipeline for transfer learning includes changing the last layer to adapt the number of neurons according to the number of custom classes. In this work, the dense layers after the convolutional and pooling layers were substituted by a Global Average Pooling (GAP) layer, which is parameter-free. Additionally, an L ₂ -norm constraint was added to the GAP layer feature descriptors, restricting the features from lying on a fixed radius hypersphere. These different pre-trained configurations were analyzed and compared using two visual maps found in the CIMAT-NAO datasets consisting of 187 and 94 images, respectively. For evaluating the localization tasks, a set of 278 and 94 images were available for each visual map, respectively. The numerical results proved that by integrating the L ₂ -norm constraint in the training pipeline, the appearance-based localization performance is boosted. Specifically, the pre-trained VGG16 and Xception networks achieved the best localization results, reaching a top-3 accuracy of 90.70% and 93.62% for each dataset, respectively, overcoming the referenced approaches based on hand-crafted feature extractors.