A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color "like" that of human skin ar...A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color "like" that of human skin are selected as candidates for human face. In the next stage, the candidates are matched with a face model and given an evaluation of the match degree by the matching module. And if the evaluation of the match result is too low, a reinforcement learning stage will start to search the best parameters of the skin-color selector. It has been tested using many photos of various ethnic groups under various lighting conditions, such as different light source, high light and shadow. And the experiment result proved that this algorithm is robust to the vary-ing lighting conditions and personal conditions.展开更多
A core characteristics based human face recognition method under the condition of illumination is proposed according to the problem of the sharply declining human face recognition rate under the condition of lighL Wit...A core characteristics based human face recognition method under the condition of illumination is proposed according to the problem of the sharply declining human face recognition rate under the condition of lighL With this method, if human face image is affected by light and the illumination is forward or side can be judged; the images affect by illumination are processed using the strategy of frequency domain replacement, and then the key areas of human face image are divided and then are recognized using support vector machine （SVM） based on the unit of area, and finally the recognition results are integrated. The experimental result shows that this method can produce a better recognition effect than other methods in view of the problem of illumination.展开更多
Short Retraction Notice The authors claim that this paper needs modifications. This article has been retracted to straighten the academic record. In making this decision the Editorial Board follows COPE's Retracti...Short Retraction Notice The authors claim that this paper needs modifications. This article has been retracted to straighten the academic record. In making this decision the Editorial Board follows COPE's Retraction Guidelines. The aim is to promote the circulation of scientific research by offering an ideal research publication platform with due consideration of internationally accepted standards on publication ethics. The Editorial Board would like to extend its sincere apologies for any inconvenience this retraction may have caused. Editor guiding this retraction: Prof. Baozong Yuan(EiC of JSIP) The full retraction notice in PDF is preceding the original paper, which is marked "RETRACTED".展开更多
The ding is an ancient cooking vessel with two loop handles standing on three or four legs. During the Shang and Zhou dynasties, the ding was used as a sacrificial vessel. It was also a symbol of power of the ruling c...The ding is an ancient cooking vessel with two loop handles standing on three or four legs. During the Shang and Zhou dynasties, the ding was used as a sacrificial vessel. It was also a symbol of power of the ruling class. This ding, a quadripod, is the only relic which has a pattern of human faces among the 10,000 Shang Dynasty bronzeware items展开更多
Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we eva...Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for“hit” and “rejection”and this may provide implications for biologically-inspired computational systems.展开更多
This paper presents an image processing design flow for virtual fitting room (VFR) applications, targeting both personal computers and mobile devices. The proposed human friendly interface is implemented by a three-st...This paper presents an image processing design flow for virtual fitting room (VFR) applications, targeting both personal computers and mobile devices. The proposed human friendly interface is implemented by a three-stage algorithm: Detection and sizing of the user's body, detection of reference points based on face detection and augmented reality markers, and superimposition of the clothing over the user's image. Compared to other existing VFR systems, key difference is the lack of any proprietary hardware components or peripherals. Proposed VFR is software based and designed to be universally compatible as long as the device has a camera. Furthermore, JAVA implementation on Android based mobile systems is computationally efficient and it can run in real-time on existing mobile devices.展开更多
The human face consists of three dimensions： （1） the visible, static sur-face, （2） the mobile dimension, which communicates thoughts, emotions, and states of mind, and （3） the invisible dimension, the face aspa...The human face consists of three dimensions： （1） the visible, static sur-face, （2） the mobile dimension, which communicates thoughts, emotions, and states of mind, and （3） the invisible dimension, the face aspars-pro-toto for the whole person who owns the face. In this latter sense, the human face is at the center of Emmanuel Levinas＇ theory of ethics： We encounter each other face-to-face, he argues, and it is the other＇s face that calls for my ethical response to the holiness of his/her wholeness and essence. The primary ethical imperative is： ＂Thou shalt not kill.＂ When we encounter a facially disfigured person, we usually fail to respond ethically because we concentrate on the disfigurement. The second dimension, as a result of the disfigurement, is often impaired and thus incapable of communicating in such a way that we can ＂read＂ the face. With our gaze fixed on the disfigured part of the face, we lose sight of the person as a whole. Metaphorically speaking, we could even say that we ＂kill＂ the person. Levinas conceives of the other＇s face not in its plastic manifestation. But the encounter with the other does at first take place as embodiment. According to Merleau-Ponty, this encounter is by definition interactive and dialogical. In Willa Cather＇s short story ＂The Profile,＂ young beautiful Virginia marries a portrait painter after he has finished her portrait in profile. The left side of her face is severely disfigured because of a burn. Her husband is waiting impatiently for her to talk about ＂it＂ and the suffering it must cause her in order to ＂heal＂ her with his love, but she behaves as if it did not exist and even likes to dress extravagantly. In the following analysis of the short story, it will be illustrated how the husband fails to respond to his wife＇s face＇s invitation to interact with it and get in touch with the wholeness of her person that it stands for. Instead, he reduces her to the disfigurement. When he finally names the scar, he metaphorically ＂kills＂ her, as well as their marriage.展开更多
Face recognition provides a natural visual interface for human computer interaction （HCI） applications. The process of face recognition, however, is inhibited by variations in the appearance of face images caused by...Face recognition provides a natural visual interface for human computer interaction （HCI） applications. The process of face recognition, however, is inhibited by variations in the appearance of face images caused by changes in lighting, expression, viewpoint, aging and introduction of occlusion. Although various algorithms have been presented for face recognition, face recognition is still a very challenging topic. A novel approach of real time face recognition for HCI is proposed in the paper. In view of the limits of the popular approaches to foreground segmentation, wavelet multi-scale transform based background subtraction is developed to extract foreground objects. The optimal selection of the threshold is automatically determined, which does not require any complex supervised training or manual experimental calibration. A robust real time face recognition algorithm is presented, which combines the projection matrixes without iteration and kernel Fisher discriminant analysis （KFDA） to overcome some difficulties existing in the real face recognition. Superior performance of the proposed algorithm is demonstrated by comparing with other algorithms through experiments. The proposed algorithm can also be applied to the video image sequences of natural HCI.展开更多
Automatic face detection and localization is a key problem in many computer vision tasks. In this paper, a simple yet effective approach for detecting and locating human faces in color images is proposed. The contribu...Automatic face detection and localization is a key problem in many computer vision tasks. In this paper, a simple yet effective approach for detecting and locating human faces in color images is proposed. The contribution of this paper is twofold. First, a particular reference to face detection techniques along with a background to neural networks is given. Second, and maybe most importantly, an adaptive cubic-spline neural network is designed to be used to detect and locate human faces in uncontrolled environments. The experimental results conducted on our test set show the effectiveness of the proposed approach and it can compare favorably with other state-of-the-art approaches in the literature.展开更多
文摘A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color "like" that of human skin are selected as candidates for human face. In the next stage, the candidates are matched with a face model and given an evaluation of the match degree by the matching module. And if the evaluation of the match result is too low, a reinforcement learning stage will start to search the best parameters of the skin-color selector. It has been tested using many photos of various ethnic groups under various lighting conditions, such as different light source, high light and shadow. And the experiment result proved that this algorithm is robust to the vary-ing lighting conditions and personal conditions.
文摘A core characteristics based human face recognition method under the condition of illumination is proposed according to the problem of the sharply declining human face recognition rate under the condition of lighL With this method, if human face image is affected by light and the illumination is forward or side can be judged; the images affect by illumination are processed using the strategy of frequency domain replacement, and then the key areas of human face image are divided and then are recognized using support vector machine （SVM） based on the unit of area, and finally the recognition results are integrated. The experimental result shows that this method can produce a better recognition effect than other methods in view of the problem of illumination.
文摘Short Retraction Notice The authors claim that this paper needs modifications. This article has been retracted to straighten the academic record. In making this decision the Editorial Board follows COPE's Retraction Guidelines. The aim is to promote the circulation of scientific research by offering an ideal research publication platform with due consideration of internationally accepted standards on publication ethics. The Editorial Board would like to extend its sincere apologies for any inconvenience this retraction may have caused. Editor guiding this retraction: Prof. Baozong Yuan(EiC of JSIP) The full retraction notice in PDF is preceding the original paper, which is marked "RETRACTED".
文摘The ding is an ancient cooking vessel with two loop handles standing on three or four legs. During the Shang and Zhou dynasties, the ding was used as a sacrificial vessel. It was also a symbol of power of the ruling class. This ding, a quadripod, is the only relic which has a pattern of human faces among the 10,000 Shang Dynasty bronzeware items
基金Supported by the National Basic Research Program of China (Grant No.2006CB303101)the National Natural Science Foundation of China(Grant Nos.60433030,30600182 and 30500157)the Royal Society
文摘Computational similarity measures have been evaluated in a variety of ways, but few of the validated computational measures are based on a high-level, cognitive criterion of objective similarity. In this paper, we evaluate two popular objective similarity measures by comparing them with face matching performance in human observers. The results suggest that these measures are still limited in predicting human behavior, especially in rejection behavior, but objective measure taking advantage of global and local face characteristics may improve the prediction. It is also suggested that human may set different criterions for“hit” and “rejection”and this may provide implications for biologically-inspired computational systems.
文摘This paper presents an image processing design flow for virtual fitting room (VFR) applications, targeting both personal computers and mobile devices. The proposed human friendly interface is implemented by a three-stage algorithm: Detection and sizing of the user's body, detection of reference points based on face detection and augmented reality markers, and superimposition of the clothing over the user's image. Compared to other existing VFR systems, key difference is the lack of any proprietary hardware components or peripherals. Proposed VFR is software based and designed to be universally compatible as long as the device has a camera. Furthermore, JAVA implementation on Android based mobile systems is computationally efficient and it can run in real-time on existing mobile devices.
文摘The human face consists of three dimensions： （1） the visible, static sur-face, （2） the mobile dimension, which communicates thoughts, emotions, and states of mind, and （3） the invisible dimension, the face aspars-pro-toto for the whole person who owns the face. In this latter sense, the human face is at the center of Emmanuel Levinas＇ theory of ethics： We encounter each other face-to-face, he argues, and it is the other＇s face that calls for my ethical response to the holiness of his/her wholeness and essence. The primary ethical imperative is： ＂Thou shalt not kill.＂ When we encounter a facially disfigured person, we usually fail to respond ethically because we concentrate on the disfigurement. The second dimension, as a result of the disfigurement, is often impaired and thus incapable of communicating in such a way that we can ＂read＂ the face. With our gaze fixed on the disfigured part of the face, we lose sight of the person as a whole. Metaphorically speaking, we could even say that we ＂kill＂ the person. Levinas conceives of the other＇s face not in its plastic manifestation. But the encounter with the other does at first take place as embodiment. According to Merleau-Ponty, this encounter is by definition interactive and dialogical. In Willa Cather＇s short story ＂The Profile,＂ young beautiful Virginia marries a portrait painter after he has finished her portrait in profile. The left side of her face is severely disfigured because of a burn. Her husband is waiting impatiently for her to talk about ＂it＂ and the suffering it must cause her in order to ＂heal＂ her with his love, but she behaves as if it did not exist and even likes to dress extravagantly. In the following analysis of the short story, it will be illustrated how the husband fails to respond to his wife＇s face＇s invitation to interact with it and get in touch with the wholeness of her person that it stands for. Instead, he reduces her to the disfigurement. When he finally names the scar, he metaphorically ＂kills＂ her, as well as their marriage.
基金supported by the National Natural Science Foundation of China (Grant No.60872117)the Leading Academic Discipline Project of Shanghai Municipal Education Commission (Grant No.J50104)
文摘Face recognition provides a natural visual interface for human computer interaction （HCI） applications. The process of face recognition, however, is inhibited by variations in the appearance of face images caused by changes in lighting, expression, viewpoint, aging and introduction of occlusion. Although various algorithms have been presented for face recognition, face recognition is still a very challenging topic. A novel approach of real time face recognition for HCI is proposed in the paper. In view of the limits of the popular approaches to foreground segmentation, wavelet multi-scale transform based background subtraction is developed to extract foreground objects. The optimal selection of the threshold is automatically determined, which does not require any complex supervised training or manual experimental calibration. A robust real time face recognition algorithm is presented, which combines the projection matrixes without iteration and kernel Fisher discriminant analysis （KFDA） to overcome some difficulties existing in the real face recognition. Superior performance of the proposed algorithm is demonstrated by comparing with other algorithms through experiments. The proposed algorithm can also be applied to the video image sequences of natural HCI.
文摘Automatic face detection and localization is a key problem in many computer vision tasks. In this paper, a simple yet effective approach for detecting and locating human faces in color images is proposed. The contribution of this paper is twofold. First, a particular reference to face detection techniques along with a background to neural networks is given. Second, and maybe most importantly, an adaptive cubic-spline neural network is designed to be used to detect and locate human faces in uncontrolled environments. The experimental results conducted on our test set show the effectiveness of the proposed approach and it can compare favorably with other state-of-the-art approaches in the literature.
