Automatic caption generation of an image requires both computer vision and natural language processing techniques. Despite of advanced research in English caption generation, research on generating Arabic descriptions...
详细信息
ISBN:
(纸本)9781577358008
Automatic caption generation of an image requires both computer vision and natural language processing techniques. Despite of advanced research in English caption generation, research on generating Arabic descriptions of an image is extremely limited. Semitic languages like Arabic are heavily influenced by root-words. We leverage this critical dependency of Arabic and in this paper are the first to generate captions of an image directly in Arabic using root-word based Recurrent neuralnetworks and Deep neuralnetworks. We report the first BLEU score for direct Arabic caption generation. Experimental results confirm that generating image captions using root-words directly in Arabic significantly outperforms the English-Arabic translated captions using state-of-the-art methods.
Battelle scientists have assembled a reconfigurable multispectral imaging and classification system which can be taken into the field to support automated real-time target/background discrimination. The system may be ...
详细信息
Battelle scientists have assembled a reconfigurable multispectral imaging and classification system which can be taken into the field to support automated real-time target/background discrimination. The system may be used for a variety of applications including environmental remote sensing, industrial inspection and medical imaging. This paper discusses hard tactical target and runway detection applications performed with the multispectral system. The Battelle-developed system consists of a passive, multispectral imaging electro-optical (EO) sensor suite and a real-time digital data collection and data fusion image processor. The EO sensor suite, able to collect imagery in 12 distinct wavebands from the ultraviolet (UV) through the long wave infrared (LWIR), consists of five charge-coupled device (CCD) cameras and two thermal IR imagers integrated on a common portable platform. The data collection and processing system consists of video switchers, recorders and a real-time sensor fusion/classification hardware system which combines any three input wavebands to perform real-time data fusion by applying ''look-up tables,'' derived from tailored neural network algorithms, to classify the imaged scene pixel by pixel. The result is then visualized in a video format on a full color, 9-inch, active matrix Liquid Crystal Display (LCD). A variety of classification algorithms including artificialneuralnetworks and data clustering techniques were successfully optimized to perform pixel-level classification of imagery in complex scenes comprised of tactical targets, buildings, roads, aircraft runways, and vegetaton. Algorithms implemented included unsupervised maximum likelihood, Linde Buzo Gray, and ''fuzzy'' clustering algorithms along with Multilayer Perceptron and Learning Vector Quantization (LVQ) neuralnetworks. Supervised clustering of the data was also evaluated. To assess classification robustness, algorithms were tested on imagery recorded over broad periods of tim
Imaging sensors have been deployed for a variety of nonintrusive diagnostics in photogrammetry, videometry, and other pertinent gross-field visualization. Especially, three-dimensional (3-D) remote sensing based on st...
详细信息
Imaging sensors have been deployed for a variety of nonintrusive diagnostics in photogrammetry, videometry, and other pertinent gross-field visualization. Especially, three-dimensional (3-D) remote sensing based on stereoscopic vision has become increasingly important in many research and industrial applications. Typical applications can be particle tracking in flow visualization, motion/deformation detection in dynamics and stress analysis, and robot vision in automation and quality control, to name a few. The use of an appropriate calibration technique for image sensing is thus essential in both laboratory and field applications. To provide a robust and reliable calibration capability for stereoscopic 3-D detection, we develop a hybrid technique that is based on the use of artificialneuralnetworks and a conventional physical-mathematical model. The hybrid technique is advantageous in procedural simplicity;that is, ease in hardware setup and speed in data processing. Our results show that the hybrid approach can improve the accuracy in predicting the object space coordinates by about 30% compared to those based on a purely physical-mathematical model. It appears that the hybrid technique can combine the merits of both physical-mathematical model and artificialneuralnetworks to improve the overall performance. (c) 2006 Society of Photo-Optical Instrumentation Engineers.
image style transfer is an emerging technique based on deep learning, which takes advantage of the impressive feature extraction of convolutional neuralnetworks (CNN). The extraction of high-level features of images ...
详细信息
image style transfer is an emerging technique based on deep learning, which takes advantage of the impressive feature extraction of convolutional neuralnetworks (CNN). The extraction of high-level features of images makes the separation of style information and image content possible. image style conversion technique aims to learn the style characteristics of various paintings, and then apply the learned style to another image. The combination of artificial intelligence and art makes this technique highly concerned in the relevant technical fields and art fields, and has been applied in many different fields of society. In this paper, we conduct a comprehensive study on image style transfer techniques. Firstly, we analyze and classify the existing algorithms of the current style transfer algorithms, and then elaborate on their applications in different fields. In addition, we also summarize the future development and prospect of the image transfer technique.
In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression, This technique has been implemented using neuralnetworks. A Kohonen self organized feature may, ...
详细信息
ISBN:
(纸本)0819424412
In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression, This technique has been implemented using neuralnetworks. A Kohonen self organized feature may, is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. Simulation results demonstrate that the proposed technique provides a 5-10% improvement in coding performance over the existing neuralnetworks based PVQ techniques.
artificialneuralnetworks are widely used in many different applications because of their ability to deal with a range of complex problems generally involving massive data sets. These networks are made up of nodes, c...
详细信息
artificialneuralnetworks are widely used in many different applications because of their ability to deal with a range of complex problems generally involving massive data sets. These networks are made up of nodes, connections, and nonlinear response connections, which are typically implemented as software code running on ordinary electronic computers. In such systems, electrons, with their advantages and drawbacks, are in charge of storing, processing, and transmitting information. Signal processing in the optical domain can provide ultrafast, parallel operation, nonlinear dynamics, and high energy efficiency, making photonics a suitable technology for the realization of neuroinspired computing platforms. This advantage stimulated the development of photonics neuralnetworks based on single and multiple lasers with classical optical cavities. Recently, networks made of random lasers emerged as a novel concept that uses randomly placed scattering elements to create nonlinearity and complexity in photonics neuralnetworks. In this review paper, we present the general framework for networks of coupled lasers, discuss recent advances in networks of random lasers, and outline future directions in this area. We also examine the challenges and limitations of using random lasers in photonic networks, as well as potential solutions. By harnessing the properties of random lasers, such as their unique spectral characteristics in pulsed emission mode and their robustness against noise, networks of interacting random lasers can explore new and exciting possibilities for photonics technology that could find applications in a variety of fields, including image recognition and encryption.(c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
This paper deals with coupled oscillators as the building blocks of a bioinspired computing paradigm and their implementation. In order to accomplish the low-power and fast-processing requirements of autonomous applic...
详细信息
This paper deals with coupled oscillators as the building blocks of a bioinspired computing paradigm and their implementation. In order to accomplish the low-power and fast-processing requirements of autonomous applications, we study the microelectronic analog implementation of physical oscillators, instead of the software computer-simulated implementation. With this aim, the original oscillator has been adapted to a suitable microelectronic form. So as to study the hardware nonlinear oscillators, we propose two macro models, demonstrating that they preserve the synchronization properties. Secondary effects such as mismatch and output delay and their relation to network synchronization are analyzed and discussed. We show the correct operation of the proposed electronic oscillators with simulations and experimental results from a manufactured integrated test circuit. The proposed architecture is intended to perform the scene segmentation stage of an autonomous focal-plane self-contained visual processing system for artificial vision applications.
imageprocessing has many applications in different fields of agriculture. The present study aimed to use imageprocessing techniques and artificialneuralnetworks (ANN) to estimate oil and protein contents of sesame...
详细信息
imageprocessing has many applications in different fields of agriculture. The present study aimed to use imageprocessing techniques and artificialneuralnetworks (ANN) to estimate oil and protein contents of sesame genotypes without the use of time-consuming and costly laboratory methods. The proposed method accurately estimates the parameters in sesame seeds without destructing the genetically valuable material. In this study, a set of 138 morphological features were extracted from the digital image of 125 sesame seed genotypes. A multilayer perceptron (MLP) ANN was then employed to estimate oil and protein contents and determine the relationship between estimated values and laboratory-measured values. The efficiency of this model was compared to radial bases function (RBF), extended RBF (ERBF), GRNN, M5-Rule, M5-Tree, support vector machine regression, and linear regression models. Results showed that MLP performed better in estimating qualitative parameters of seeds in the sesame germplasm. The model estimated oil content with an root mean square error (RMSE) of 2.13% (the accuracy of 97.87%) and an R-2 of 0.93. Protein content was estimated by an RMSE of 0.378% (the accuracy of 99.62%) and an R-2 of 0.96.
artificialneuralnetworks (ANNs) have strong learning and computing capabilities, and alleviate the problem of high power consumption of traditional von Neumann architectures, providing a solid basis for advanced ima...
详细信息
artificialneuralnetworks (ANNs) have strong learning and computing capabilities, and alleviate the problem of high power consumption of traditional von Neumann architectures, providing a solid basis for advanced image recognition, information processing, and low-power detection. Recently, a two-dimensional (2D) MoS2 field-effect transistor (FET) integrating a Zr-doped HfO2 (HZO) ferroelectric layer has shown potential for both logic and memory applications with low power consumption, which is promising for parallel processing of massive data. However, the long-term potentiation (LTP) characteristics of such devices are usually non-linear, which will affect the replacement of ANN weight values and degrade the ANN recognition rate. Here, we propose a dual-gate-controlled 2D MoS2 FET employing HZO gate stack with a crested symmetric structure to reduce power consumption. Improved nonlinearity of the LTP properties has been achieved through the electrical control of the dual gates. A recognition rate reaching 100% is obtained after 60 training epochs, and is 7.89% higher than that obtained from single-gate devices. Our proposed device structure and experimental results provide an attractive pathway towards high-efficiency data processing and image classification in the advanced artificial intelligence field.
The application of the artificialneural network for the processing of one-dimensional micro-PIXE data is described. The network architecture, selection of the transfer function as well as the training and verificatio...
详细信息
The application of the artificialneural network for the processing of one-dimensional micro-PIXE data is described. The network architecture, selection of the transfer function as well as the training and verification operations are described in detail. The performed reconstructions confirm that the neural network may be used for improvement of the resolution and for processing of low statistics data. The limitations of the neural network application for two-dimensional images are discussed. (C) 1999 Elsevier Science B.V. All rights reserved.
暂无评论