Search

Automatic text localization and segmentation in a normal environment with vertical or curved texts are core elements of numerous tasks comprising the identification of vehicles and self-driving cars, and preparing significant information from real scenes to visually impaired people. Nevertheless, texts in the real environment can be discovered with a high level of angles, profiles, dimensions, and colors which is an arduous process to detect. In this paper, a new framework based on a convolutional neural network (CNN) is introduced to obtain high efficiency in detecting text even in the presence of a complex background. Due to using a new inception layer and an improved ReLU layer, an excellent result is gained to detect text even in the presence of complex backgrounds. At first, four new m.ReLU layers are employed to explore low-level visual features. The new m.ReLU building block and inception layer are optimized to detect vital information maximally. The effect of stacking up inception layers (kernels with the dimension of 3 × 3 or bigger) is explored and it is demonstrated that this strategy is capable of obtaining mostly varying-sized texts further successfully than a linear chain of convolution layers (Conv layers). The suggested text detection algorithm is conducted in four well-known databases, namely ICDAR 2013, ICDAR 2015, ICDAR 2017, and ICDAR 2019. Text detection results on all mentioned databases with the highest recall of 94.2%, precision of 95.6%, and F-score of 94.8% illustrate that the developed strategy outperforms the state-of-the-art frameworks.

Background Brain cancer is a destructive and life-threatening disease that imposes immense negative effects on patients’ lives. Therefore, detection of brain tumors at an early stage improves the impact of treatments and increases patients' survival rate. However, detecting brain tumors in their initial stages is a demanding task and an unmet need. Methods The present study presents a comprehensive review of the recent Artificial Intelligence (AI) methods of diagnosing brain tumors using MRI images. These AI techniques can be divided into Supervised, Unsupervised, and Deep learning (DL) methods. Results Diagnosing and segmenting brain tumors usually begin with Magnetic Resonance Imaging (MRI) on the brain since MRI is a noninvasive imaging technique. Another existing challenge is that the growth of technology is faster than the rate of increase in the number of medical staff who can employ these technologies. It has resulted in an increased risk of diagnostic misinterpretation. Therefore, developing robust automated brain tumor detection techniques has been studied widely over the past years. Conclusion The current review provides an analysis of the performance of modern methods in this area. Moreover, various image segmentation methods in addition to the recent efforts of researchers are summarized. Finally, the paper discusses open questions and suggests directions for future research.

The COVID-19 pandemic is a global, national, and local public health which causing a significant outbreak in all countries and regions for both males and females around the world. Automated detection of lung infections and their boundaries from medical images offers a great potential to augment the patient treatment healthcare strategies for tackling COVID-19 and its impacts. Detecting this disease from lung CT scan images is perhaps one of the fastest ways to diagnose the patients. However, finding the presence of infected tissues and segment them from CT slices faces numerous challenges, including similar adjacent tissues, vague boundary, and erratic infections. To overcome the mentioned problems, we propose a two-route convolutional neural network (CNN) by extracting global and local features for detecting and classifying COVID-19 infection from CT images. Each pixel from the image is classified into normal and infected tissue. For improving the classification accuracy, we used two different strategies including Fuzzy c-mean clustering and local directional pattern (LDN) encoding methods to represent the input image differently. This allows us to find a more complex pattern from the image. To overcome the overfitting problems due to small samples, an augmentation approach is utilized. The results demonstrated that the proposed framework achieved Precision 96%, Recall 97%, F-score, average surface distance (ASD) of 2.8\pm0.3\ mm and volume overlap error (VOE) of 5.6\pm1.2%.