A5101498948- Advanced Image Fusion Techniques
- Hand Gesture Recognition Systems
- Video Surveillance and Tracking Methods
- Image and Video Quality Assessment
- Food composition and properties
- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- Gaze Tracking and Assistive Technology
- Vehicle License Plate Recognition
- Digital Media Forensic Detection
- Image Processing and 3D Reconstruction
- Non-Destructive Testing Techniques
- Interactive and Immersive Displays
- Tactile and Sensory Interactions
- Generative Adversarial Networks and Image Synthesis
- Spectroscopy and Chemometric Analyses
- Advanced Neural Network Applications
- Advancements in Photolithography Techniques
- Industrial Vision Systems and Defect Detection
Meizu (China)
2021
University of Chinese Academy of Sciences
2017-2018
Institute of Automation
2015-2017
Chinese Academy of Sciences
2014-2017
Samsung (China)
2017
Traffic sign recognition plays an important role in driver assistant systems and intelligent autonomous vehicles. Its real-time performance is highly desirable addition to its performance. This paper aims deal with traffic recognition, i.e., localizing what type of appears which area input image at a fast processing time. To achieve this goal, we first propose extremely detection module, 20 times faster than the existing best module. Our module based on proposal extraction classification...
Although traffic sign recognition has been studied for many years, most existing works are focused on the symbol-based signs. This paper proposes a new data-driven system to recognize all categories of signs, which include both and text-based in video sequences captured by camera mounted car. The consists three stages, regions interest (ROIs) extraction, ROIs refinement classification, post-processing. Traffic from each frame first extracted using maximally stable extremal gray normalized...
Despite the increasing popularity of head mounted displays (HMDs), development efficient text entry methods on these devices has remained under explored. In this paper, we investigate feasibility head-based for HMDs, by which, user controls a pointer virtual keyboard using rotation. Specifically, three techniques: TapType, DwellType, and GestureType. Users TapType select letter pointing to it tapping button. DwellType dwelling over period time. GestureType perform word-level input gesture...
This paper reports on the NTIRE 2021 challenge perceptual image quality assessment (IQA), held in conjunction with New Trends Image Restoration and Enhancement workshop (NTIRE) at CVPR 2021. As a new type of processing technology, algorithms based Generative Adversarial Networks (GAN) have produced images more realistic textures. These output completely different characteristics from traditional distortions, thus pose for IQA methods to evaluate their visual quality. In comparison previous...
Image Quality Assessment (IQA), which aims to provide computational models for automatically predicting perceptual image quality, is an important computer vision task with many applications. In recent years, a variety of IQA methods have been proposed based on different metric de-signs, measure the quality images affected by various types distortion. However, rapid development Generative Adversarial Networks (GAN), new challenge has brought community. Especially, GAN-based Reconstruction...
This paper aims to deal with real-time traffic sign recognition, i.e. localizing what type of appears in which area an input image at a fast processing time. To achieve this goal, two-module framework (detection module and classification module) is proposed. In detection module, we firstly transform the color probability maps by using model. Then proposals are extracted finding maximally stable extremal regions on these maps. Finally, SVM classifier trained HOG features utilized further...
Deep convolutional neural networks (CNN) has achieved state-of-the-art result on traffic sign classification, which plays a key role in intelligent transportation system. However, it usually requires large number of labeled training data, is not always available, to guarantee good performance. In this paper, we propose synthesize images by generative adversarial (GANs). It takes standard template and background image as input the network GANs, where defines class include controls visual...
Abstract. Fissures in rice kernels that develop prior to harvest and post-harvest processing significantly reduce head yield, a crucial parameter for evaluating quality economic value the industry. In this study, fissures rough were revealed by scanning approximately 50 at time using an x-ray system. An algorithm was developed detect measure images Python programming language coupled with OpenCV library. This successfully segmented individual gap-filling method. The detected adaptive...
<b><sc>Abstract.</sc></b> <b>Fissures in rice kernels developed prior to harvest and post-harvest processing significantly reduce head yield, a crucial parameter for evaluating quality economic value the industry. In this study, fissures rough were revealed by scanning using an X-ray system. An algorithm was open source programming language python âOpenCVâ library detect measure from images. This can automatically segment size of image. The detects adaptive thresholding individual kernel...
The Vision Challenge Track 1 for Data-Effificient Defect Detection requires competitors to instance segment 14 industrial inspection datasets in a data-defificient setting. This report introduces the technical details of team Aoi-overfifitting-Team this challenge. Our method focuses on key problem segmentation quality defect masks scenarios with limited training samples. Based Hybrid Task Cascade (HTC) algorithm, we connect transformer backbone (Swin-B) through composite connections inspired...
This paper reports on the NTIRE 2021 challenge perceptual image quality assessment (IQA), held in conjunction with New Trends Image Restoration and Enhancement workshop (NTIRE) at CVPR 2021. As a new type of processing technology, algorithms based Generative Adversarial Networks (GAN) have produced images more realistic textures. These output completely different characteristics from traditional distortions, thus pose for IQA methods to evaluate their visual quality. In comparison previous...