Multi-view hashing efficiently integrates multi-view data for learning compact hash codes, and achieves impressive large-scale retrieval performance. In real-world applications, multi-view data are often stored or col...
详细信息
ISBN:
(纸本)9781728163956
Multi-view hashing efficiently integrates multi-view data for learning compact hash codes, and achieves impressive large-scale retrieval performance. In real-world applications, multi-view data are often stored or collected in different locations, where hash code learning is more challenging yet less studied. To fulfill this gap, this paper proposes a novel supervised multi-view distributed hashing (SMvDisH) for hash code learning from multi-view data in a distributed manner. SMvDisH yields the discriminative latent hash codes by joint learning of latent factor model and classifier. With local consistency assumption among neighbor nodes, the distributed learning problem is divided into a set of decentralized subproblems. The subproblems can be solved in parallel, and the computational and communication costs are low. Experimental results on three large-scale image datasets demonstrate that SMvDisH achieves competitive retrieval performance and trains faster than state-of-the-art multi-view hashing methods.
In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms. Vario...
详细信息
A computer system was developed to classify human facial expressions for emotion recognition using a distributed computer architecture within the scope of big data. Computers with normal standards and features were us...
详细信息
ISBN:
(纸本)9781728175652
A computer system was developed to classify human facial expressions for emotion recognition using a distributed computer architecture within the scope of big data. Computers with normal standards and features were used in the distributed computer architecture. Necessary system software for the distributed computer architecture was established and mutual communication protocols were provided between the computers and databases in the computer network. Visual C# parallel programming was used as the software language on the distributed computer architecture. In the software prepared, face image files were processed and threads were created. The threads created later were processed in the processors of the computers. The threads were run on the processors in the distributed computer system, and facial expressions were classified for emotion recognition. In the distributed computer architecture: the number of image files, the volume of big data and the load of the threads to be processed arc taken into account;and databases and parallel programming were used and the classification of human face images was performed. Emotion analysis methods and facial expression recognition techniques were used in the classification process. The distributed computer system is in low cost and high processing speed. With the distributed computer system architecture, big data analytics has become convenient and feasible.
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network’s ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI.
Detecting objects in the aerial-view scene is challenging for the objects usually have small scales relative to the image, making it hard to achieve high accuracy in full-image detection. Slice detection tries to over...
详细信息
ISBN:
(纸本)9781665475938
Detecting objects in the aerial-view scene is challenging for the objects usually have small scales relative to the image, making it hard to achieve high accuracy in full-image detection. Slice detection tries to overcome this by cutting the full image into slices before detecting them, but objects are sparsely distributed and usually clustered in local areas, a large number of background areas without objects can be ignored to improve detection efficiency. In this paper, we present PickDet, a framework for efficient and effective object detection in the aerial-view scene, which only chooses slices containing objects to conduct detection. The key components of PickDet include a lightweight convolutional network (PickNet), a screening strategy (SoftPick), and fine-tuned detectors. Given slices of aerial-view images, PickNet first outputs the probability of object existence. Then SoftPick conducts a double-threshold screening strategy to pick the slices which contain objects. Finally, all picked slices are fed into the detector in parallel and full-image detection is used as an auxiliary mean. Compared with previous methods, PickDet achieves higher accuracy and more efficiency in the aerial-view scene. We evaluate PickDet on Visdrone and Oiltank datasets, experiments show that PickDet can result in up to 28.0% AP improvement compared to full-image detection, and can result in up to 2.9% AP increase and up to 5 times inference speedup compared to slice detection.
The identification of traditional Chinese medicine is the key to control the quality of traditional Chinese medicine and ensure the safety and effectiveness of clinical medication. Compared with the physical and chemi...
详细信息
The identification of traditional Chinese medicine is the key to control the quality of traditional Chinese medicine and ensure the safety and effectiveness of clinical medication. Compared with the physical and chemical identification methods with expensive equipment and complex operation, microscopic image identification of traditional Chinese medicine is an effective method with low cost. However, this method still has a high learning cost and identification errors due to staff fatigue. Therefore, this paper designs an effective automatic recognition approach of Chinese herbal medicine by micro imageprocessing. The core of this method is the introduction of transfer learning and data enhancement methods, which effectively alleviates the problem of insufficient number of microscopic image data samples in the microscopic recognition of traditional Chinese medicine, and realizes the automatic recognition of traditional Chinese medicine. We construct a library of microscopic recognition features of Chinese herbal medicine, and designe evaluation experiments on this basis. The results show that the recognition performance of our method is better than that of SSD method, especially the F1 value is increased by 7.25 %.
Gridding operation, which is to map non-uniform data samples on to a uniformly distributed grid, is one of the key steps in radio astronomical data reduction process. One of the main bottlenecks of gridding is the poo...
详细信息
Gridding operation, which is to map non-uniform data samples on to a uniformly distributed grid, is one of the key steps in radio astronomical data reduction process. One of the main bottlenecks of gridding is the poor computing performance, and a typical solution for such performance issue is the implementation of multicore CPU platforms. Although such a method could usually achieve good results, in many cases, the performance of gridding is still restricted to an extent due to the limitations of CPU, since the main workload of gridding is a combination of a large number of single instruction, multidata stream operations, which is more suitable for GPU, rather than CPU implementations. To meet the challenge of massive data gridding for the modern large single-dish radio telescopes, e.g. the Five-hundred-meter Aperture Spherical radio Telescope, inspired by existing multicore CPU gridding algorithms such as Cygrid, here we present an easy-to-install, high-performance, and open-source convolutional gridding framework, HCGrid, in CPU-GPU heterogeneous platforms. It optimizes data search by employing multithreading on CPU, and accelerates the convolution process by utilizing massive parallelization of GPU. In order to make HCGrid a more adaptive solution, we also propose the strategies of thread organization and coarsening, as well as optimal parameter settings under various GPU architectures. A thorough analysis of computing time and performance gain with several GPU parallel optimization strategies show that it can lead to excellent performance in hybrid computing environments.
In order to realize the concrete quality monitoring, the displacement detection method based on computer vision is adopted by adding the identification label to the concrete specimen The traditional camera calibration...
详细信息
ISBN:
(纸本)9781665414852
In order to realize the concrete quality monitoring, the displacement detection method based on computer vision is adopted by adding the identification label to the concrete specimen The traditional camera calibration methods often need to make standard checkerboard to calculate the camera parameters. If users use different mobile phones to shoot the same scene, it is impossible to calibrate each mobile camera in advance. Therefore, aiming at the problem that the traditional camera calibration method can't meet the needs of some application scenarios, this paper proposes a method to calibrate the camera by extracting a small number of feature points in the image. Experimental data show that the method can calibrate the camera accurately, and then calculate the reference moving distance according to the basic principle of computer vision, and it has good flexibility.
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a ne...
详细信息
ISBN:
(纸本)9781665448994
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of imageprocessing technology, perceptual imageprocessing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challenges, the training and testing datasets in this challenge include the outputs of perceptual imageprocessing algorithms and the corresponding subjective scores. Thus they can be used to develop and evaluate IQA methods on GAN-based distortions. The challenge has 270 registered participants in total. In the final testing stage, 13 participating teams submitted their models and fact sheets. Almost all of them have achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
In recent years, the problem of lake eutrophication has become increasingly severe. The monitoring and control of cyanobacteria in lakes are of great significance. The information obtained by existing monitoring metho...
详细信息
暂无评论