Background Large screen visualization sys tems have been widely utilized in many industries.Such systems can help illustrate the working states of different production systems.However,efficient interaction with such s...Background Large screen visualization sys tems have been widely utilized in many industries.Such systems can help illustrate the working states of different production systems.However,efficient interaction with such systems is still a focus of related research.Methods In this paper,we propose a touchless interaction system based on RGB-D camera using a novel bone-length constraining method.The proposed method optimizes the joint data collected from RGB-D cameras with more accurate and more stable results on very noisy data.The user can customize the system by modifying the finite-state machine in the system and reuse the gestures in multiple scenarios,reducing the number of gestures that need to be designed and memorized.Results/Conclusions The authors tested the system in two cases.In the first case,we illustrated a process in which we improved the gesture designs on our system and tested the system through user study.In the second case,we utilized the system in the mining industry and conducted a user study,where users say that they think the system is easy to use.展开更多
Background Several face detection and recogni tion methods have been proposed in the past decades that have excellent performance.The conventional face recognition pipeline comprises the following:(1)face detection,(2...Background Several face detection and recogni tion methods have been proposed in the past decades that have excellent performance.The conventional face recognition pipeline comprises the following:(1)face detection,(2)face alignment,(3)feature extraction,and(4)similarity,which are independent of each other.The separate facial analysis stages lead to redundant model calculations,and are difficult for use in end-to-end training.Methods In this paper,we propose a novel end-to-end trainable convolutional network framework for face detection and recognition,in which a geometric transformation matrix is directly learned to align the faces rather than predicting the facial landmarks.In the training stage,our single CNN model is supervised only by face bounding boxes and personal identities,which are publicly available from WIDER FACE and CASIA-WebFace datasets.Our model is tested on Face Detection Dataset and Benchmark(FDDB)and Labeled Face in the Wild(LFW)datasets.Results The results show 89.24%recall for face detection tasks and 98.63%accura cy for face recognition tasks.展开更多
基金the National Key Research and Development Project of China(2017 YFC 0804401)National Natural Science Foundation of China(U 1909204).
文摘Background Large screen visualization sys tems have been widely utilized in many industries.Such systems can help illustrate the working states of different production systems.However,efficient interaction with such systems is still a focus of related research.Methods In this paper,we propose a touchless interaction system based on RGB-D camera using a novel bone-length constraining method.The proposed method optimizes the joint data collected from RGB-D cameras with more accurate and more stable results on very noisy data.The user can customize the system by modifying the finite-state machine in the system and reuse the gestures in multiple scenarios,reducing the number of gestures that need to be designed and memorized.Results/Conclusions The authors tested the system in two cases.In the first case,we illustrated a process in which we improved the gesture designs on our system and tested the system through user study.In the second case,we utilized the system in the mining industry and conducted a user study,where users say that they think the system is easy to use.
文摘Background Several face detection and recogni tion methods have been proposed in the past decades that have excellent performance.The conventional face recognition pipeline comprises the following:(1)face detection,(2)face alignment,(3)feature extraction,and(4)similarity,which are independent of each other.The separate facial analysis stages lead to redundant model calculations,and are difficult for use in end-to-end training.Methods In this paper,we propose a novel end-to-end trainable convolutional network framework for face detection and recognition,in which a geometric transformation matrix is directly learned to align the faces rather than predicting the facial landmarks.In the training stage,our single CNN model is supervised only by face bounding boxes and personal identities,which are publicly available from WIDER FACE and CASIA-WebFace datasets.Our model is tested on Face Detection Dataset and Benchmark(FDDB)and Labeled Face in the Wild(LFW)datasets.Results The results show 89.24%recall for face detection tasks and 98.63%accura cy for face recognition tasks.