An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In St...An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In Step 1, the localization and shape of the pupil are roughly determined in iris image, which is used as prior knowledge to quickly locate the inner and outer boundary of iris from rough to fine scale. Eyelids, eyelashes areas and the spot in the pupil are automatically detected and removed to improve the localization accuracy. In Step 2, the possible noise from residual eyelashes is further filtered by selecting a ＂pure＂ iris area as a reference and making a validation judgment pixel-wise. Furthermore, the validation flag for each pixel is introduced into the iris encoding and matching computation, as a result, the rejection rate of iris recognition is reduced. Compared with Daugman algorithm, iris recognition test on collected human eye images shows that our proposed algorithm has an obvious improvement both on boosting the speed and reducing the rejection rate.展开更多
With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the pa...With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the past decades due to the capability of the mobile processors.In recent years,the performance of mobile processors has changed rapidly,which makes it comparable to the desktop processors.This paper proposed and realized an AR system to be used on the Android mobile platform based on the image recognition through EasyAR engine and Unity 3D development tools.In this system,the image recognition could be done locally and/or using cloud recognition.Test results show that the cloud-based recognition is more efficient and accuracy than the local recognition for the mobile AR when there are more images to be recognized at the same time.展开更多
A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely...A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely used descriptors—the local binary pattern（ LBP） and weber local descriptor（ WLD）. The LBP and WLD feature histograms were extracted separately fromeach facial image,and contextualized histogram was generated as feature vectors to feed the classifier. In addition,the human face was divided into sub-blocks and each sub-block was assigned different weights by their different contributions to the intensity of facial expressions to improve the recognition rate. With the support vector machine（SVM） as classifier,the experimental results on the 2D texture images fromthe 3D-BU FE dataset indicated that contextualized histograms improved facial expression recognition performance when local features were employed.展开更多
Can WiFi signals be used for sensing purpose？ The growing PHY layer capabilities of WiFi has made it possible to reuse WiFi signals for both communication and sensing. Sensing via WiFi would enable remote sensing wit...Can WiFi signals be used for sensing purpose？ The growing PHY layer capabilities of WiFi has made it possible to reuse WiFi signals for both communication and sensing. Sensing via WiFi would enable remote sensing without wearable sensors, simultaneous perception and data transmission without extra communication infrastructure, and contactless sensing in privacy-preserving mode. Due to the popularity of WiFi devices and the ubiquitous deployment of WiFi networks, WiFi-based sensing networks, if fully connected, would potentially rank as one of the world＇s largest wireless sensor networks. Yet the concept of wireless and sensorless sensing is not the simple combination of WiFi and radar. It seeks breakthroughs from dedicated radar systems, and aims to balance between low cost and high accuracy, to meet the rising demand for pervasive environment perception in everyday life. Despite increasing research interest, wireless sensing is still in its infancy. Through introductions on basic principles and working prototypes, we review the feasibilities and limitations of wireless, sensorless, and contactless sensing via WiFi. We envision this article as a brief primer on wireless sensing for interested readers to explore this open and largely unexplored field and create next-generation wireless and mobile computing applications.展开更多
基金Supported by the National Natural Science Foundation of China(61367002)the Guangxi Key Laboratory of Automatic Detecting Technology and Instruments(YQ15108)+1 种基金the Guangxi Department of Education Foundation(KY2015YB111)the Innovation Team Foundation of Guilin University of Electronic Technology,the Foundation of Guangxi Experiment Center of Information Science,the Guangxi National Natural Science Foundation(2014GXNSFAA118302)
文摘An improved Daugman iris recognition algorithm is provided in this paper, which embodies in two aspects： 1 Improvement for iris localization and 2 The improvement for both iris encoding and matching algorithms. In Step 1, the localization and shape of the pupil are roughly determined in iris image, which is used as prior knowledge to quickly locate the inner and outer boundary of iris from rough to fine scale. Eyelids, eyelashes areas and the spot in the pupil are automatically detected and removed to improve the localization accuracy. In Step 2, the possible noise from residual eyelashes is further filtered by selecting a ＂pure＂ iris area as a reference and making a validation judgment pixel-wise. Furthermore, the validation flag for each pixel is introduced into the iris encoding and matching computation, as a result, the rejection rate of iris recognition is reduced. Compared with Daugman algorithm, iris recognition test on collected human eye images shows that our proposed algorithm has an obvious improvement both on boosting the speed and reducing the rejection rate.
文摘With the development of computation technology,the augmented reality(AR)is widely applied in many fields as well as the image recognition.However,the AR application on mobile platform is not developed enough in the past decades due to the capability of the mobile processors.In recent years,the performance of mobile processors has changed rapidly,which makes it comparable to the desktop processors.This paper proposed and realized an AR system to be used on the Android mobile platform based on the image recognition through EasyAR engine and Unity 3D development tools.In this system,the image recognition could be done locally and/or using cloud recognition.Test results show that the cloud-based recognition is more efficient and accuracy than the local recognition for the mobile AR when there are more images to be recognized at the same time.
基金Supported by the National Natural Science Foundation of China(60772066)
文摘A new algorithm taking the spatial context of local features into account by utilizing contextualized histograms was proposed to recognize facial expression. The contextualized histograms were extracted fromtwo widely used descriptors—the local binary pattern（ LBP） and weber local descriptor（ WLD）. The LBP and WLD feature histograms were extracted separately fromeach facial image,and contextualized histogram was generated as feature vectors to feed the classifier. In addition,the human face was divided into sub-blocks and each sub-block was assigned different weights by their different contributions to the intensity of facial expressions to improve the recognition rate. With the support vector machine（SVM） as classifier,the experimental results on the 2D texture images fromthe 3D-BU FE dataset indicated that contextualized histograms improved facial expression recognition performance when local features were employed.
文摘Can WiFi signals be used for sensing purpose？ The growing PHY layer capabilities of WiFi has made it possible to reuse WiFi signals for both communication and sensing. Sensing via WiFi would enable remote sensing without wearable sensors, simultaneous perception and data transmission without extra communication infrastructure, and contactless sensing in privacy-preserving mode. Due to the popularity of WiFi devices and the ubiquitous deployment of WiFi networks, WiFi-based sensing networks, if fully connected, would potentially rank as one of the world＇s largest wireless sensor networks. Yet the concept of wireless and sensorless sensing is not the simple combination of WiFi and radar. It seeks breakthroughs from dedicated radar systems, and aims to balance between low cost and high accuracy, to meet the rising demand for pervasive environment perception in everyday life. Despite increasing research interest, wireless sensing is still in its infancy. Through introductions on basic principles and working prototypes, we review the feasibilities and limitations of wireless, sensorless, and contactless sensing via WiFi. We envision this article as a brief primer on wireless sensing for interested readers to explore this open and largely unexplored field and create next-generation wireless and mobile computing applications.
