Edge Enhancement Based Active Contour Model for Segmentation of Brain Tumor in MRI Images

Tumor segmentation is one of the most significant tasks in brain image analysis due to the significant information obtained by the tumor region. Therefore, many methods have been proposed during the last two decades for segmenting the tumor in MRI images. In this paper, an automated method is proposed using an active contour model with an initial contour creation using edge sharpening, thresholding, and morphological operations. Four methods of edge detection are utilized in the edge sharpening process (Sobel, Roberts, Prewitt, and Canny) and their performance was investigated in terms of Dice, Jaccard, and F1 score. The experiments were implemented on BRATS datasets with both HGG and LGG images. The study indicates that sharpening the edges using edge detection is essential to improve the segmentation of the tumor region especially when it is used with an active contour model. The achieved results show the effectiveness of the proposed method and it outperformed some recent existing methods.

Unsupervised Haze Removal for High-Resolution Optical Remote-Sensing Images Based on Improved Generative Adversarial Networks

One major limitation of remote-sensing images is bad weather conditions, such as haze. Haze significantly reduces the accuracy of satellite image interpretation. To solve this problem, this paper proposes a novel unsupervised method to remove haze from high-resolution optical remote-sensing images. The proposed method, based on cycle generative adversarial networks, is called the edge-sharpening cycle-consistent adversarial network (ES-CCGAN). Most importantly, unlike existing methods, this approach does not require prior information; the training data are unsupervised, which mitigates the pressure of preparing the training data set. To enhance the ability to extract ground-object information, the generative network replaces a residual neural network (ResNet) with a dense convolutional network (DenseNet). The edge-sharpening loss function of the deep-learning model is designed to recover clear ground-object edges and obtain more detailed information from hazy images. In the high-frequency information extraction model, this study re-trained the Visual Geometry Group (VGG) network using remote-sensing images. Experimental results reveal that the proposed method can recover different kinds of scenes from hazy images successfully and obtain excellent color consistency. Moreover, the ability of the proposed method to obtain clear edges and rich texture feature information makes it superior to the existing methods.