Maylor Leung - Academia.edu (original) (raw)
Papers by Maylor Leung
2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008
A novel and automated technique for learning human perspective context (HPC) from a scene is prop... more A novel and automated technique for learning human perspective context (HPC) from a scene is proposed in this paper. It is found that two models are required to describe HPC for camera tilt angle ranging from 0◦ to 50◦ .F rom a scene, the tilt angle can be inferred from the observed human shapes and head/foot positions. Afterward, a novel
Computer Vision and Pattern Recognition, 2001
The paper proposes a novel technique for robust change detection based upon the integration of in... more The paper proposes a novel technique for robust change detection based upon the integration of intensity and texture differences between two frames. A new texture difference measure based on the relations between gradient vectors is described. The robustness of the measure with respect to noise and illumination changes has been analyzed. Two ways to integrate the intensity and texture differences
TENCON, IEEE Region 10 International Conference, 2001
Detecting the presence of people and suspicious objects are the essential tasks for security surv... more Detecting the presence of people and suspicious objects are the essential tasks for security surveillance. This paper presents a new real-time system for this purpose. Two motion cues from background subtraction and temporal differencing are employed to not only get reliable motion detection but also identify detected objects in the scene. A fuzzy reasoning technique is developed to detect and
Proceedings Workshop on Human Motion, 2000
In this paper, a novel study for an automated scene interpretation system, named ELEVIEW, is repo... more In this paper, a novel study for an automated scene interpretation system, named ELEVIEW, is reported to outline the design of the system. It is motivated by the reported crimes that happen inside elevators. The main goal is to investigate techniques that make an ordinary elevator monitoring system intelligent, i.e. see the scene and understand actions that are occurring. The
Pattern Recognition, 2007
The general-purpose shape retrieval problem is a challenging task. Particularly, an ideal techniq... more The general-purpose shape retrieval problem is a challenging task. Particularly, an ideal technique, which can work in clustered environment, meet the requirements of perceptual similarity measure on partial query and overcoming dimensionality curse and adverse environment, is in demand. This paper reports our study on one local structural approach that addresses these issues. Shape representation and indexing are two key points in shape retrieval. The proposed approach combines a novel local-structure-based shape representation and a new histogram indexing structure. The former makes possible partial shape matching of objects without the requirement of segmentation (separation) of objects from complex background, while the latter has an advantage on indexing performance. The search time is linearly proportional to the input complexity. In addition, the method is relatively robust under adverse environments. It is able to infer retrieval results from incomplete information of an input by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Thousands of images have been used to test the proposed concepts on sensitivity analysis, similarity-based retrieval, partial query and mixed object query. Very encouraging experimental results with respect to efficiency and effectiveness have been obtained.
Mug shot photography has been used to identify criminals by the police for more than a century. H... more Mug shot photography has been used to identify criminals by the police for more than a century. However, the common scenario of face recognition using frontal and side-view mug shots as gallery remains largely uninvestigated in computerized face recognition across pose. This paper presents a novel appearance-based approach using frontal and sideface images to handle pose variations in face recognition,
Pattern Recognition, 1987
AIBtract --In this paper, a new technique for partitioning a human body, when it is in motion, in... more AIBtract --In this paper, a new technique for partitioning a human body, when it is in motion, into meaningful parts is presented. The technique is based on classifying coincidence edges which are edges in both the difference picture and the current frame. Each class of edges has a specific voting scheme which can then be used for the identification of regions of interest. Experimental results show that the technique can criminate a lot of stationary regions and thus can reduce the amount of processing required in the interpretation process.
Pattern Recognition, 1987
Human body motion analysis can be roughly divided into three phases. In the first phase, moving b... more Human body motion analysis can be roughly divided into three phases. In the first phase, moving body parts are separated from the background. In the second phase, these body parts are then labelled. In the third phase, the motion verbs are assigned to the movement. An earlier paper by the authors described a novel technique for segmenting the moving body parts from the background. In this paper, techniques developed for the second phase of the analysis are discussed. The notion ofantiparallel lines is employed to abstract the regions into a higher level primitive which enables one to define and develop operations such as concatenation and deletion. A simple heuristic model is then used to map the detected regions into human body parts. Results of which are very encouraging. Future research in the proposed approach is warranted.
11th International Multimedia Modelling Conference, 2005
One of the key remaining problems in face recognition is that of handling the variability in appe... more One of the key remaining problems in face recognition is that of handling the variability in appearance due to changes in pose. One strategy is to synthesize virtual face views from real views. In this paper, a novel 3D face shape-modeling algorithm, Multilevel Quadratic Variation Minimization (MQVM), is proposed. Our method makes sole use of two orthogonal real views of a face, i.e., the frontal and profile views. By applying quadratic variation minimization iteratively in a coarse-to-fine hierarchy of control lattices, the MQVM algorithm can generate -smooth 3D face surfaces. Then realistic virtual face views can be synthesized by rotating the 3D models. The algorithm works properly on sparse constraint points and large images. It is much more efficient than single-level quadratic variation minimization. The modeling results suggest the validity of the MQVM algorithm for 3D face modeling and 2D face view synthesis under different poses.
18th International Conference on Pattern Recognition (ICPR'06), 2006
One possible solution for pose-and illuminationinvariant face recognition is to employ appearance... more One possible solution for pose-and illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existing facial texture analysis algorithms are suboptimal, because they usually neglect specular reflections and require numerous training images for virtual view synthesis. This paper presents a novel texture synthesis approach from a single frontal view for face recognition. Using a generic 3D face shape, facial textures are analyzed with consideration of all of the ambient, diffuse, and specular reflections. Virtual views are synthesized under different poses and illuminations. The proposed approach was evaluated using the CMU-PIE face database. Encouraging results show that the proposed approach improves face recognition performances across pose and illumination variations.
2007 IEEE International Conference on Image Processing, 2007
Abstract The main advantage of using the Hough Transform to detect ellipses is its robustness aga... more Abstract The main advantage of using the Hough Transform to detect ellipses is its robustness against missing data points. However, the storage and computational requirements of the Hough Transform preclude practical applications. Although there are ...
Feature point detection plays a crucial role in shape representation and object recognition. A fe... more Feature point detection plays a crucial role in shape representation and object recognition. A feature point set that can represent the shape honestly and consistently under different scale and environment is desired. The method used should be able to cater to these requirements as much as possible. Regretfully, no method has done completely well. Dynamic two-strip algorithm (Dyn2S) used the strip to extract features. Digitization noise can be tolerated because the strip has width and it can enclose points that can be approximated as a straight line. Unfortunately, its performance seems not very satisfactory on curves. In this paper, further investigation has been carried out along this direction. The proposed method, based on the long and narrow strips that are prominent and reliable, has been applied on logos with encouraging results. This approach is more capable of extracting consistent feature points fiom one instance of a model shape to another.
Pattern Recognition, 2003
Logo recognition is of great interest in the document and shape analysis domain. In order to deve... more Logo recognition is of great interest in the document and shape analysis domain. In order to develop a recognition method that is robust to employ under adverse conditions such as di erent scale/orientation, broken curves, added noise and occlusion, a modiÿed line segment Hausdor distance is proposed in this paper. The new approach has the advantage to incorporate structural and spatial information to compute dissimilarity between two sets of line segments rather than two sets of points. The proposed technique has been applied on line segments generated from logos with encouraging results. Clear cut distinction between the correct and incorrect matches has been observed. This suggests a strong potential for logo and shape recognition system.
Pattern Recognition, 2002
A novel concept of line segment Hausdor! distance is proposed in this paper. Researchers apply Ha... more A novel concept of line segment Hausdor! distance is proposed in this paper. Researchers apply Hausdor! distance to measure the similarity of two point sets. It is extended here to match two sets of line segments. The new approach has the advantage to incorporate structural and spatial information to compute the similarity. The added information can conceptually provide more and better distinctive capability for recognition. This would strengthen and enhance the matching process of similar objects such as faces. The proposed technique has been applied on line segments generated from the edge maps of faces with encouraging result that supports the concept experimentally. The results also implicate that line segments could provide su$cient information for face recognition. This might imply a new way for face coding and recognition.
Pattern Recognition, 2002
A new attributed string matching method for human face pro"le recognition is proposed in this wor... more A new attributed string matching method for human face pro"le recognition is proposed in this work. It is a novel idea to apply structural and syntactic technique on face pro"le matching. The approach works on a chain of pro"le line segments and highlights the favor of curve matching by suppressing the operations of insert and delete. The technique relies mainly on the merge and change operations of string to tackle the inconsistency problem of feature point detection. A quadratic penalty function is proposed to prohibit large angle changes and overmerging. The method produces very encouraging results and is found to be suitable for similar shape classi"cation.
Pattern Recognition, 1997
This paper proposes a novel method in detecting the four reference lines of a cursive word at any... more This paper proposes a novel method in detecting the four reference lines of a cursive word at any skew angle. The proposed method is rotation independent because the detection is based on points determined by their relative positions between the outer contour of a cursive word and its convex hull. Features like bounding box, contour area, convex hull and furthest
IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2003
The automatic recognition of facial expression presents a significant challenge to the pattern an... more The automatic recognition of facial expression presents a significant challenge to the pattern analysis and man-machine interaction research community. Recognition from a single static image is particularly a difficult task. In this paper, we present a methodology for facial expression recognition from a single static image using line-based caricatures. The recognition process is completely automatic. It also addresses the computational expensive problem and is thus suitable for real-time applications. The proposed approach uses structural and geometrical features of a user sketched expression model to match the line edge map (LEM) descriptor of an input face image. A disparity measure that is robust to expression variations is defined. The effectiveness of the proposed technique has been evaluated and promising results are obtained. This work has proven the proposed idea that facial expressions can be characterized and recognized by caricatures.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
AbstractÐThe automatic recognition of human faces presents a significant challenge to the pattern... more AbstractÐThe automatic recognition of human faces presents a significant challenge to the pattern recognition research community. Typically, human faces are very similar in structure with minor differences from person to person. They are actually within one class of ªhuman face.º Furthermore, lighting condition changes, facial expressions, and pose variations further complicate the face recognition task as one of the difficult problems in pattern analysis. This paper proposed a novel concept, ªfaces can be recognized using line edge map.º A compact face feature, Line Edge Map (LEM), is generated for face coding and recognition. A thorough investigation on the proposed concept is conducted which covers all aspects on human face recognition, i.e., face recognition, under 1) controlled/ideal condition and size variation, 2) varying lighting condition, 3) varying facial expression, and 4) varying pose. The system performances are also compared with the eigenface method, one of the best face recognition techniques, and reported experimental results of other methods. A face prefiltering technique is proposed to speed up the searching process. It is a very encouraging finding that the proposed face recognition technique has performed superior to the eigenface method in most of the comparison experiments. This research demonstrates that LEM together with the proposed generic line segment Hausdorff distance measure provide a new way for face coding and recognition.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
Abstract-First Sight, a vision system in labeling the outline of a moving human body, is proposed... more Abstract-First Sight, a vision system in labeling the outline of a moving human body, is proposed in this paper. The emphasis of First Sight is on the analysis of motion information gathered solely from the outline of a moving human object. Two main processes are implemented in First ...
IEEE Transactions on Information Forensics and Security, 2000
Mug shot photography has been used to identify criminals by the police for more than a century. H... more Mug shot photography has been used to identify criminals by the police for more than a century. However, the common scenario of face recognition using frontal and side-view mug shots as gallery remains largely uninvestigated in computerized face recognition across pose. This paper presents a novel appearance-based approach using frontal and sideface images to handle pose variations in face recognition,
2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008
A novel and automated technique for learning human perspective context (HPC) from a scene is prop... more A novel and automated technique for learning human perspective context (HPC) from a scene is proposed in this paper. It is found that two models are required to describe HPC for camera tilt angle ranging from 0◦ to 50◦ .F rom a scene, the tilt angle can be inferred from the observed human shapes and head/foot positions. Afterward, a novel
Computer Vision and Pattern Recognition, 2001
The paper proposes a novel technique for robust change detection based upon the integration of in... more The paper proposes a novel technique for robust change detection based upon the integration of intensity and texture differences between two frames. A new texture difference measure based on the relations between gradient vectors is described. The robustness of the measure with respect to noise and illumination changes has been analyzed. Two ways to integrate the intensity and texture differences
TENCON, IEEE Region 10 International Conference, 2001
Detecting the presence of people and suspicious objects are the essential tasks for security surv... more Detecting the presence of people and suspicious objects are the essential tasks for security surveillance. This paper presents a new real-time system for this purpose. Two motion cues from background subtraction and temporal differencing are employed to not only get reliable motion detection but also identify detected objects in the scene. A fuzzy reasoning technique is developed to detect and
Proceedings Workshop on Human Motion, 2000
In this paper, a novel study for an automated scene interpretation system, named ELEVIEW, is repo... more In this paper, a novel study for an automated scene interpretation system, named ELEVIEW, is reported to outline the design of the system. It is motivated by the reported crimes that happen inside elevators. The main goal is to investigate techniques that make an ordinary elevator monitoring system intelligent, i.e. see the scene and understand actions that are occurring. The
Pattern Recognition, 2007
The general-purpose shape retrieval problem is a challenging task. Particularly, an ideal techniq... more The general-purpose shape retrieval problem is a challenging task. Particularly, an ideal technique, which can work in clustered environment, meet the requirements of perceptual similarity measure on partial query and overcoming dimensionality curse and adverse environment, is in demand. This paper reports our study on one local structural approach that addresses these issues. Shape representation and indexing are two key points in shape retrieval. The proposed approach combines a novel local-structure-based shape representation and a new histogram indexing structure. The former makes possible partial shape matching of objects without the requirement of segmentation (separation) of objects from complex background, while the latter has an advantage on indexing performance. The search time is linearly proportional to the input complexity. In addition, the method is relatively robust under adverse environments. It is able to infer retrieval results from incomplete information of an input by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Thousands of images have been used to test the proposed concepts on sensitivity analysis, similarity-based retrieval, partial query and mixed object query. Very encouraging experimental results with respect to efficiency and effectiveness have been obtained.
Mug shot photography has been used to identify criminals by the police for more than a century. H... more Mug shot photography has been used to identify criminals by the police for more than a century. However, the common scenario of face recognition using frontal and side-view mug shots as gallery remains largely uninvestigated in computerized face recognition across pose. This paper presents a novel appearance-based approach using frontal and sideface images to handle pose variations in face recognition,
Pattern Recognition, 1987
AIBtract --In this paper, a new technique for partitioning a human body, when it is in motion, in... more AIBtract --In this paper, a new technique for partitioning a human body, when it is in motion, into meaningful parts is presented. The technique is based on classifying coincidence edges which are edges in both the difference picture and the current frame. Each class of edges has a specific voting scheme which can then be used for the identification of regions of interest. Experimental results show that the technique can criminate a lot of stationary regions and thus can reduce the amount of processing required in the interpretation process.
Pattern Recognition, 1987
Human body motion analysis can be roughly divided into three phases. In the first phase, moving b... more Human body motion analysis can be roughly divided into three phases. In the first phase, moving body parts are separated from the background. In the second phase, these body parts are then labelled. In the third phase, the motion verbs are assigned to the movement. An earlier paper by the authors described a novel technique for segmenting the moving body parts from the background. In this paper, techniques developed for the second phase of the analysis are discussed. The notion ofantiparallel lines is employed to abstract the regions into a higher level primitive which enables one to define and develop operations such as concatenation and deletion. A simple heuristic model is then used to map the detected regions into human body parts. Results of which are very encouraging. Future research in the proposed approach is warranted.
11th International Multimedia Modelling Conference, 2005
One of the key remaining problems in face recognition is that of handling the variability in appe... more One of the key remaining problems in face recognition is that of handling the variability in appearance due to changes in pose. One strategy is to synthesize virtual face views from real views. In this paper, a novel 3D face shape-modeling algorithm, Multilevel Quadratic Variation Minimization (MQVM), is proposed. Our method makes sole use of two orthogonal real views of a face, i.e., the frontal and profile views. By applying quadratic variation minimization iteratively in a coarse-to-fine hierarchy of control lattices, the MQVM algorithm can generate -smooth 3D face surfaces. Then realistic virtual face views can be synthesized by rotating the 3D models. The algorithm works properly on sparse constraint points and large images. It is much more efficient than single-level quadratic variation minimization. The modeling results suggest the validity of the MQVM algorithm for 3D face modeling and 2D face view synthesis under different poses.
18th International Conference on Pattern Recognition (ICPR'06), 2006
One possible solution for pose-and illuminationinvariant face recognition is to employ appearance... more One possible solution for pose-and illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existing facial texture analysis algorithms are suboptimal, because they usually neglect specular reflections and require numerous training images for virtual view synthesis. This paper presents a novel texture synthesis approach from a single frontal view for face recognition. Using a generic 3D face shape, facial textures are analyzed with consideration of all of the ambient, diffuse, and specular reflections. Virtual views are synthesized under different poses and illuminations. The proposed approach was evaluated using the CMU-PIE face database. Encouraging results show that the proposed approach improves face recognition performances across pose and illumination variations.
2007 IEEE International Conference on Image Processing, 2007
Abstract The main advantage of using the Hough Transform to detect ellipses is its robustness aga... more Abstract The main advantage of using the Hough Transform to detect ellipses is its robustness against missing data points. However, the storage and computational requirements of the Hough Transform preclude practical applications. Although there are ...
Feature point detection plays a crucial role in shape representation and object recognition. A fe... more Feature point detection plays a crucial role in shape representation and object recognition. A feature point set that can represent the shape honestly and consistently under different scale and environment is desired. The method used should be able to cater to these requirements as much as possible. Regretfully, no method has done completely well. Dynamic two-strip algorithm (Dyn2S) used the strip to extract features. Digitization noise can be tolerated because the strip has width and it can enclose points that can be approximated as a straight line. Unfortunately, its performance seems not very satisfactory on curves. In this paper, further investigation has been carried out along this direction. The proposed method, based on the long and narrow strips that are prominent and reliable, has been applied on logos with encouraging results. This approach is more capable of extracting consistent feature points fiom one instance of a model shape to another.
Pattern Recognition, 2003
Logo recognition is of great interest in the document and shape analysis domain. In order to deve... more Logo recognition is of great interest in the document and shape analysis domain. In order to develop a recognition method that is robust to employ under adverse conditions such as di erent scale/orientation, broken curves, added noise and occlusion, a modiÿed line segment Hausdor distance is proposed in this paper. The new approach has the advantage to incorporate structural and spatial information to compute dissimilarity between two sets of line segments rather than two sets of points. The proposed technique has been applied on line segments generated from logos with encouraging results. Clear cut distinction between the correct and incorrect matches has been observed. This suggests a strong potential for logo and shape recognition system.
Pattern Recognition, 2002
A novel concept of line segment Hausdor! distance is proposed in this paper. Researchers apply Ha... more A novel concept of line segment Hausdor! distance is proposed in this paper. Researchers apply Hausdor! distance to measure the similarity of two point sets. It is extended here to match two sets of line segments. The new approach has the advantage to incorporate structural and spatial information to compute the similarity. The added information can conceptually provide more and better distinctive capability for recognition. This would strengthen and enhance the matching process of similar objects such as faces. The proposed technique has been applied on line segments generated from the edge maps of faces with encouraging result that supports the concept experimentally. The results also implicate that line segments could provide su$cient information for face recognition. This might imply a new way for face coding and recognition.
Pattern Recognition, 2002
A new attributed string matching method for human face pro"le recognition is proposed in this wor... more A new attributed string matching method for human face pro"le recognition is proposed in this work. It is a novel idea to apply structural and syntactic technique on face pro"le matching. The approach works on a chain of pro"le line segments and highlights the favor of curve matching by suppressing the operations of insert and delete. The technique relies mainly on the merge and change operations of string to tackle the inconsistency problem of feature point detection. A quadratic penalty function is proposed to prohibit large angle changes and overmerging. The method produces very encouraging results and is found to be suitable for similar shape classi"cation.
Pattern Recognition, 1997
This paper proposes a novel method in detecting the four reference lines of a cursive word at any... more This paper proposes a novel method in detecting the four reference lines of a cursive word at any skew angle. The proposed method is rotation independent because the detection is based on points determined by their relative positions between the outer contour of a cursive word and its convex hull. Features like bounding box, contour area, convex hull and furthest
IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2003
The automatic recognition of facial expression presents a significant challenge to the pattern an... more The automatic recognition of facial expression presents a significant challenge to the pattern analysis and man-machine interaction research community. Recognition from a single static image is particularly a difficult task. In this paper, we present a methodology for facial expression recognition from a single static image using line-based caricatures. The recognition process is completely automatic. It also addresses the computational expensive problem and is thus suitable for real-time applications. The proposed approach uses structural and geometrical features of a user sketched expression model to match the line edge map (LEM) descriptor of an input face image. A disparity measure that is robust to expression variations is defined. The effectiveness of the proposed technique has been evaluated and promising results are obtained. This work has proven the proposed idea that facial expressions can be characterized and recognized by caricatures.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
AbstractÐThe automatic recognition of human faces presents a significant challenge to the pattern... more AbstractÐThe automatic recognition of human faces presents a significant challenge to the pattern recognition research community. Typically, human faces are very similar in structure with minor differences from person to person. They are actually within one class of ªhuman face.º Furthermore, lighting condition changes, facial expressions, and pose variations further complicate the face recognition task as one of the difficult problems in pattern analysis. This paper proposed a novel concept, ªfaces can be recognized using line edge map.º A compact face feature, Line Edge Map (LEM), is generated for face coding and recognition. A thorough investigation on the proposed concept is conducted which covers all aspects on human face recognition, i.e., face recognition, under 1) controlled/ideal condition and size variation, 2) varying lighting condition, 3) varying facial expression, and 4) varying pose. The system performances are also compared with the eigenface method, one of the best face recognition techniques, and reported experimental results of other methods. A face prefiltering technique is proposed to speed up the searching process. It is a very encouraging finding that the proposed face recognition technique has performed superior to the eigenface method in most of the comparison experiments. This research demonstrates that LEM together with the proposed generic line segment Hausdorff distance measure provide a new way for face coding and recognition.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
Abstract-First Sight, a vision system in labeling the outline of a moving human body, is proposed... more Abstract-First Sight, a vision system in labeling the outline of a moving human body, is proposed in this paper. The emphasis of First Sight is on the analysis of motion information gathered solely from the outline of a moving human object. Two main processes are implemented in First ...
IEEE Transactions on Information Forensics and Security, 2000
Mug shot photography has been used to identify criminals by the police for more than a century. H... more Mug shot photography has been used to identify criminals by the police for more than a century. However, the common scenario of face recognition using frontal and side-view mug shots as gallery remains largely uninvestigated in computerized face recognition across pose. This paper presents a novel appearance-based approach using frontal and sideface images to handle pose variations in face recognition,