A lot of research shows that there could be several reasons why the duality of agricultural products has been reduced. Plant diseases make up one of the most important components of this quality. Therefore, the reduct...
详细信息
Scene text removal is a recent development in computer vision that replaces text patches in natural images with the appropriate background. Text removal is a difficult process leading to faulty areas of text cont...
详细信息
Scene text removal is a recent development in computer vision that replaces text patches in natural images with the appropriate background. Text removal is a difficult process leading to faulty areas of text containing text strokes with their hazy backgrounds. Text in the real world uses a variety of font kinds, some of which are difficult to localize due to their chaotic shapes, varied shading degrees, and orientation *** text erasing may include the subtasks of text detection as well as text inpainting. Both subtasks require a large amount of data to be successful;but, existing approaches were limited by insufficient real-world data for scene-text elimination. Eventhough the existing works produced considerable performance improvement in scene text removal, they often leave many text remains like text strokes, thus producinglow-quality visual outcomes. Therefore, this paper proposes an automatic text inpainting and video quality elevation model by using the Improved Convolutional Network-based ***, the video samples are collected from the diverse datasets and then converted into frames. Next, the frames are deblurred using an enhanced Convolutional Neural Network (CNN) model that has three convolutional layers for accurately localizing the texts in frames. Subsequently, the texts are detected by utilizing the CLARA-based VGG-16 network. Afterward, the text strokes are removed using a convolutional Encoder and decoder network to eliminate the presence of text on complex backgrounds and textures. Here, the coordinates of text in the deblurred frames are used to crop out the text stroke regions. So, the texts are in-painted, and then, the text in-painted regions are pasted back to their original positions in the frames. Furthermore, the video quality is elevated with the help of the DenseNet-centric Enhancement network. The experimental outcomes demonstrate that the proposed model effectively removed scene texts and enhanced the video qu
Newborn brains rapidly learn to solve challenging object perception tasks, including segmenting objects from backgrounds and recognizing objects across new viewing situations. Conversely, modern machine learning (ML) ...
详细信息
Heart attack prediction is a significant contributor to worldwide morbidity. Cardiovascular illness is a critical component of clinical data analysis prediction. A precise diagnosis of cardiac disease can save lives, ...
详细信息
Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increas...
详细信息
Unmanned aerial vehicles (UAVs) are used as supportive edge computing for sparsely located user equipment on a large scale. In this work, we propose and address a collaborative edge computing system involving multiple...
详细信息
Breast cancer is a major health concern for women worldwide, and early detection is vital to improve treatment outcomes. While existing techniques in mammogram classification have demonstrated promising results, their...
详细信息
Breast cancer is a major health concern for women worldwide, and early detection is vital to improve treatment outcomes. While existing techniques in mammogram classification have demonstrated promising results, their limitations become apparent when applied to larger datasets. The decline in performance with increased dataset size highlights the need for further research and advancements in the field to enhance the scalability and generalizability of these techniques. In this study, we propose a framework to classify breast cancer from mammograms using techniques such as mammogram enhancement, discrete cosine transform (DCT) dimensionality reduction, and deep convolutional neural network (DCNN). The first step is to improve the mammogram display to improve the visibility of key features and reduce noise. For this, we use 2-stage Contrast Limited Adaptive Histogram Equalization (CLAHE). DCT is then used to enhance mammograms to reduce residual data. It can provide effective reduction while preserving important diagnostic information. In this way, we reduce the computational complexity and increase the results of subsequent classification algorithms. Finally, DCNN is used on size-reduced DCT coefficients to learn feature discrimination and classification of mammograms. DCNN architectures have been optimized with various techniques to improve their performance, including regularization and hyperparameter tuning. We perform experiments on the DDSM dataset, a large dataset containing approximately 55,000 mammogram images, and demonstrate the effectiveness of the proposed method. We assess the proposed model’s performance by computing the precision, recall, accuracy, F1-Score, and area under the receiver operating characteristic curve (AUC). We achieve Precision and Recall values of 0.929 and 0.963, respectively. The classification accuracy of the proposed models is 0.963. Moreover, the F1-Score and AUC values are 0.962 and 0.987, respectively. These results are better a
The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human *** majority of currently available methods use either a generative adversarial network(GAN)or a recurren...
详细信息
The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human *** majority of currently available methods use either a generative adversarial network(GAN)or a recurrent neural network(RNN)to generate new handwriting *** is why these techniques frequently fall short of producing diverse and realistic text pictures,particularly for terms that are not commonly *** resolve that,this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting *** network excels in generating conditional text by extracting style vectors from a series of style *** model performs admirably on a range of handwriting synthesis tasks,including the production of text that is *** works more effectively than previous approaches by displaying lower values on key Generative Adversarial Network evaluation metrics,such Geometric Score(GS)(3.21×10^(-5))and Fréchet Inception Distance(FID)(8.75),as well as text recognition metrics,like Character Error Rate(CER)and Word Error Rate(WER).A thorough component analysis revealed the steady improvement in image production quality,highlighting the importance of specific handwriting *** fields include digital forensics,creative writing,and document security.
In a collaborative social network data publishing setup, privacy preservation of individuals is a vital issue. Existing privacy-preserving techniques assume the existence of attackers from external data recipients and...
详细信息
Electroencephalography (EEG) is a non-intrusive method used to capture electrical potential generated by brain neurons, which is crucial for diagnosing neurological disorders like epilepsy, sleep disorders, brain tumo...
详细信息
暂无评论