A widely studied problem in computer science is the restoration, segmentation, and classification of images, which involves imageprocessing, computer vision, and machine learning techniques. Deep learning has made si...
详细信息
We are training neuralnetworks to predict house rents using artificial intelligence and deep learning, which is being used in the real estate and financial industries. Real estate agents, financial institutions, and ...
详细信息
Medical imaging has been utilized in various forms in clinical applications for better diagnosis and treatment of diseases. These imaging technologies help in recognizing body's ailing region easily. In addition, ...
详细信息
In augmented reality(AR) applications, it is a challenging task to generate virtual object shadows while maintaining the precision and consistency of virtual and real areas. To achieve the above target, we propose a l...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
In augmented reality(AR) applications, it is a challenging task to generate virtual object shadows while maintaining the precision and consistency of virtual and real areas. To achieve the above target, we propose a learnable weighted recurrent generative adversarial network(LRGAN) for end-to-end shadow generation. Without any additional computational overhead, LRGAN only needs to analyze the background context to create a bridge between the target shadows and the background. Our model incorporates multiple progressive steps to recurrently compute the precise reference masks, based on which a fine-grained shadow generation module generates the shadows. A learnable weighted fusion module, which can normalize pixel values to deal with pixel overflow, fuses the generated shadows with the original image. In addition, we adopt the combined method of module training and the whole model training. Experimental results show that our proposed LRGAN not only improves the plausibility of shadow location and shape but also achieves color harmony in the shadow areas. In the absence of other prior knowledge or post-processing, it outperforms the State-of-the-Art end-to-end methods.
The rapid enhancement in the development of information technology has driven the development of human facial image recognition. Recently, facial recognition has been successfully applied in several distinct domains w...
详细信息
The rapid enhancement in the development of information technology has driven the development of human facial image recognition. Recently, facial recognition has been successfully applied in several distinct domains with the help of computing and information technology. This kind of application plays a significant role in the process of digital forensics investigation, recognizing the patterns of a human face based on the partial matching of images that would be in 24-bit color image format, including the spacing of the eyes, the bridging of the nose, the contour of the lips, ears, and chin. In this paper, we have proposed and implemented an image recognition model based on principal component analysis, genetic algorithms, and neuralnetworks, in which PCA reduces the dimension of the benchmark dataset, while genetic algorithms and neural nets optimize the searching patterns of image matching and provide highly efficient output with a minimal amount of time. Through the experiment results on the human facial images dataset of the Georgia Institute of Technology, the overall match showed that the proposed model can achieve the recognition of human face images with an accuracy rate of 93.7%. Moreover, this model helps to examine, analyze, and detect individuals by partial matching with reidentification in the procedure of forensics investigation. The experimental result shows the robustness of the proposed model in terms of efficiency compared to other state-of-the-art methods.
Remote sensing image (RSI) dehazing methods have gained significant attention for their ability to restore clear images, which are crucial for applications such as mineral exploration and flood range forecasting. The ...
详细信息
Remote sensing image (RSI) dehazing methods have gained significant attention for their ability to restore clear images, which are crucial for applications such as mineral exploration and flood range forecasting. The haze present in foggy RSIs is typically nonhomogeneous, posing a challenge for existing dehazing methods, which often struggle with the effective removal of such haze. Furthermore, current approaches primarily address foggy inputs within the spatial domain, neglecting the potential advantages of exploring the frequency domain for dehazing. To address these challenges, in this article, we propose a density-guided and frequency modulation dehazing network (DFDNet) specifically designed for RSI dehazing. The DFDNet integrates a density-guided transformer dehazing subnet (DTDN) and a frequency dual-path enhancing subnet (FDEN), enabling the restoration of clear RSIs by combined spatial- and frequency-domain processing. The DTDN leverages the dark channel prior to generate the density-aware attention and guide the removal of nonhomogeneous haze within the spatial domain. The FDEN is a dual-path structure that modulates the frequencies to enhance the details of dehazed images produced by the DTDN. Comprehensive quantitative and qualitative evaluations on StateHaze1k, RICE, and RRSD300 datasets demonstrate the superiority and generalization of the proposed DFDNet. Especially, the proposed DFDNet outperforms recent FSNet by 0.81 dB on the StateHaze1k-thick dataset.
Deep Learning has been very successful in automating the feature engineering process, widely applied for various tasks, such as speech recognition, classification, segmentation of images, time-series forecasting, amon...
详细信息
Deep Learning has been very successful in automating the feature engineering process, widely applied for various tasks, such as speech recognition, classification, segmentation of images, time-series forecasting, among others. Deep neuralnetworks (DNNs) incorporate the power to learn patterns through data, following an end-to-end fashion and expand the applicability in real world problems, since less pre-processing is necessary. With the fast growth in both scale and complexity, a new challenge has emerged regarding the design and configuration of DNNs. In this work, we present a study on applying an evolutionary grammar-based genetic programming algorithm (GP) as a unified approach to the design of DNNs. Evolutionary approaches have been growing in popularity for this subject as Neuroevolution is studied more. We validate our approach in three different applications: the design of Convolutional neuralnetworks for image classification, Graph neuralnetworks for text classification, and U-Nets for image segmentation. The results show that evolutionary grammar-based GP can efficiently generate different DNN architectures, adapted to each problem, employing choices that differ from what is usually seen in networks designed by hand. This approach has shown a lot of promise regarding the design of architectures, reaching competitive results with their counterparts.
Hyperspectral image (HSI) classification is valuable in remote sensing due to its rich spectral and spatial information. In the last decade, deep learning methods, especially Convolutional neuralnetworks (CNNs), have...
详细信息
ISBN:
(纸本)9798350350920
Hyperspectral image (HSI) classification is valuable in remote sensing due to its rich spectral and spatial information. In the last decade, deep learning methods, especially Convolutional neuralnetworks (CNNs), have revolutionized HSI classification by extracting intangible semantic features and maintaining the spatial structure during feature extraction. However, the efficacy of these techniques can be constrained by the limited availability of labeled samples in HSI data. To address the issue of small-sample HSI classification, a Lightweight Multiscale Feature Fusion Network (L-MFFN) is introduced. The Multiscale Feature Extraction Module (MFEM) and the enhanced Spectral-Spatial Attention Module (SSAM) are designed and combined in L-MFFN, optimizing the use of deep and shallow features. This integration improves the extraction and fusion of multiscale spectral-spatial features, enhancing classification performance. The proposed model demonstrates state-of-the-art performance across two HSI datasets and stands out in situations with limited labeled samples, highlighting its capability to effectively tackle the challenge of small-sample HSI classification.
Thyroid nodule detection in ultrasonic images mostly rely on conventional imageprocessing techniques, which have major negative effects including high false positive and negative rates, limited generalizability over ...
详细信息
In recent years, convolutional neuralnetworks (CNNs) have become the core of many artificial intelligence applications, especially in fields such as image recognition and speech recognition. Deploying convolutional n...
详细信息
暂无评论