Oksam Chae

Local Directional Number Pattern for Face Analysis: Face and Expression Recognition

This paper proposes a novel local feature descriptor, local directional number pattern (LDN), for face analysis, i.e., face and expression recognition. LDN encodes the directional information of the faces textures (i.e., the textures structure) in a compact way, producing a more discriminative code than current methods. We compute the structure of each micro-pattern with the aid of a compass mask that extracts directional information, and we encode such information using the prominent direction indices (directional numbers) and sign-which allows us to distinguish among similar structural patterns that have different intensity transitions. We divide the face into several regions, and extract the distribution of the LDN features from them. Then, we concatenate these features into a feature vector, and we use it as a face descriptor. We perform several experiments in which our descriptor performs consistently under illumination, noise, expression, and time lapse variations. Moreover, we test our descriptor with different masks to analyze its performance in different face analysis tasks.

Local Directional Pattern (LDP) for face recognition

This paper presents a novel local feature descriptor, the Local Directional Pattern (LDP), for recognizing human face. A LDP feature is obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Each face is represented as a collection of LDP codes for the recognition process.

Gender Classification Using Local Directional Pattern (LDP)

In this paper, we present a novel texture descriptor Local Directional Pattern (LDP) to represent facial image for gender classification. The face area is divided into small regions, from which LDP histograms are extracted and concatenated into a single vector to efficiently represent the face image. The classification is performed by using support vector machines (SVMs), which had been shown to be superior to traditional pattern classifiers in gender classification problem. Experimental results show the superiority of the proposed method on the images collected from FERET face database and achieved 95.05% accuracy.

Individual tooth segmentation from CT images using level set method with shape and intensity prior

3D visualization of teeth from CT images provides important assistance for dentists performing orthodontic surgery and treatment. However, dental CT images present several major challenges for the segmentation of tooth, which touches with adjacent teeth as well as surrounding periodontium and jaw bones. Moreover, tooth contour suffers from topological changes and splits into several branches. In this work, we focus on the segmentation of individual teeth with complete crown and root parts. To this end, we propose adaptive active contour tracking algorithms: single level set method tracking for root segmentation to handle the complex image conditions as well as the root branching problem, and coupled level set method tracking for crown segmentation in order to separate the touching teeth and create the virtual common boundaries between them. Furthermore, we improve the variational level set method in several aspects: gradient direction is introduced into the level set framework to prevent catching the surrounding object boundaries; in addition to the shape prior, intensity prior is introduced to provide adaptive shrinking or expanding forces in order to deal with the topological changes. The test results for both tooth segmentation and 3D reconstruction show that the proposed method can visualize individual teeth with high accuracy and efficiency.

Facial expression recognition using Local Directional Pattern (LDP)

A robust face descriptor is an essential component for a good facial expression recognition system. In this paper, we analyze the performance of a new feature descriptor, Local Directional Pattern (LDP), for the representation of facial expressions. LDP features are obtained by computing the edge response values in all eight directions at each pixel position and then a code is generated according to the relative magnitudes strength. Thus each expression is represented as a distribution of LDP codes. Different machine learning techniques are compared using Cohn-Kanade facial expression database for classification. Extensive experiments explicate the superiority of the proposed LDP based descriptor over other existing well known descriptors.

Local Directional Pattern (LDP) A Robust Image Descriptor for Object Recognition

This paper presents a novel local feature descriptor, theLocal Directional Pattern (LDP), for describing localimage feature. A LDP feature is obtained by computing theedge response values in all eight directions at each pixelposition and generating a code from the relative strengthmagnitude. Each bit of code sequence is determined byconsidering a local neighborhood hence becomes robust innoisy situation. A rotation invariant LDP code is alsointroduced which uses the direction of the most prominentedge response. Finally an image descriptor is formed todescribe the image (or image region) by accumulating theoccurrence of LDP feature over the whole input image (orimage region). Experimental results on the Brodatz texturedatabase show that LDP impressively outperforms theother commonly used dense descriptors (e.g.,Gabor-wavelet and LBP).

Content-Aware Dark Image Enhancement Through Channel Division

The current contrast enhancement algorithms occasionally result in artifacts, overenhancement, and unnatural effects in the processed images. These drawbacks increase for images taken under poor illumination conditions. In this paper, we propose a content-aware algorithm that enhances dark images, sharpens edges, reveals details in textured regions, and preserves the smoothness of flat regions. The algorithm produces an ad hoc transformation for each image, adapting the mapping functions to each images characteristics to produce the maximum enhancement. We analyze the contrast of the image in the boundary and textured regions, and group the information with common characteristics. These groups model the relations within the image, from which we extract the transformation functions. The results are then adaptively mixed, by considering the human vision system characteristics, to boost the details in the image. Results show that the algorithm can automatically process a wide range of images—e.g., mixed shadow and bright areas, outdoor and indoor lighting, and face images—without introducing artifacts, which is an improvement over many existing methods.

A Local Directional Pattern Variance (LDPv) Based Face Descriptor for Human Facial Expression Recognition

Automatic facial expression recognition is a challengingproblem in computer vision, and has gained significantimportance in applications of human-computer interaction.This paper presents a new appearance-based feature descriptor,the Local Directional Pattern Variance (LDPv), torepresent facial components for human expression recognition.In contrast with LDP, the proposed LDPv introducesthe local variance of directional responses to encodethe contrast information within the descriptor. Here,the LDPv represenation characterizes both spatial structureand contrast information of each micro-patterns. Templatematching and Support Vector Machine (SVM) classifierare used to classify the LDPv feature vector of differentprototypic expression images. Experimental results usingthe Cohn-Kanade database show that the LDPv descriptoryields an improved recognition rate, as compared to existingappearance-based feature descriptors, such as the Gaborwaveletand Local Binary Pattern (LBP).

A skin detection approach based on the Dempster--Shafer theory of evidence

Skin detection is an important step for a wide range of research related to computer vision and image processing and several methods have already been proposed to solve this problem. However, most of these methods suffer from accuracy and reliability problems when they are applied to a variety of images obtained under different conditions. Performance degrades further when fewer training data are available. Besides these issues, some methods require long training times and a significant amount of parameter tuning. Furthermore, most state-of-the-art methods incorporate one or more thresholds, and it is difficult to determine accurate threshold settings to obtain desirable performance. These problems arise mostly because the available training data for skin detection are imprecise and incomplete, which leads to uncertainty in classification. This requires a robust fusion framework to combine available information sources with some degree of certainty. This paper addresses these issues by proposing a fusion-based method termed Dempster-Shafer-based Skin Detection (DSSD). This method uses six prominent skin detection criteria as sources of information (SoI), quantifies their reliabilities (confidences), and then combines their confidences based on the Dempster-Shafer Theory (DST) of evidence. We use the DST as it offers a powerful and flexible framework for representing and handling uncertainties in available information and thus helps to overcome the limitations of the current state-of-the-art methods. We have verified this method on a large dataset containing a variety of images, and achieved a 90.17% correct detection rate (CDR). We also demonstrate how DSSD can be used when very little training data are available, achieving a CDR as high as 87.47% while the best result achieved by a Bayesian classifier is only 68.81% on the same dataset. Finally, a generalized DSSD (GDSSD) is proposed achieving 91.12% CDR.

Moving Object Detection for Real Time Video Surveillance: An Edge Based Approach

SUMMARY This paper presents an automatic edge segment based algorithm for the detection of moving objects that has been specially developed to deal with the variations in illumination and contents of background. We investigated the suitability of the proposed edge segment based moving object detection algorithm in comparison with the traditional intensity based as well as edge pixel based detection methods. In our method, edges are extracted from video frames and are represented as segments using an efficiently designed edge class. This representation helps to obtain the geometric information of edge in the case of edge matching and shape retrieval; and creates effective means to incorporate knowledge into edge segment during background modeling and motion tracking. An efficient approach for background edge generation and a robust method of edge matching are presented to effectively reduce the risk of false alarm due to illumination change and camera motion while maintaining the high sensitivity to the presence of moving object. The proposed method can be successfully realized in video surveillance applications in home networking environment as well as various monitoring systems. As, video coding standard MPEG-4 enables content based functionality, it can successfully utilize the shape information of the detected moving objects to achieve high coding efficiency. Experiments with real image sequences, along with comparisons with some other existing methods are presented, illustrating the robustness of the pro