• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.59-68
• /
• 2005

This paper proposes a face recognition under varying poses using local area obtained by side-view pose normalization. General normalization methods for face recognition under varying pose have a problem with the information about invisible area of face. Generally this problem is solved by compensation, but there are many cases where the image is distorted or features lost due to compensation .To solve this problem we normalize the face pose in side-view to reduce distortion that happens mainly in areas that have large depth variation. We only use undistorted area, removing the area that has been distorted by normalization. We consider two cases of yaw pose variation and pitch pose variation, and by experiments, we confirm the improvement of recognition performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.106-109
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of variability in scale, location, orientation and pose. In this paper, we present an efficient linear discriminant for multi-view face detection. Our approaches are based on linear discriminant. We define training data with fisher linear discriminant to efficient learning method. Face detection is considerably difficult because it will be influenced by poses of human face and changes in illumination. This idea can solve the multi-view and scale face detection problem poses. Quickly and efficiently, which fits for detecting face automatically. In this paper, we extract face using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected face and eye detect. The purpose of this paper is to classify face and non-face and efficient fisher linear discriminant..

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.375-380
• /
• 2014

Under controlled environment, such as fixed viewpoints or consistent illumination, the performance of face recognition is usually high enough to be acceptable nowadays. Face recognition is, however, a still challenging task in real world. SIFT(Scale Invariant Feature Transformation) algorithm is scale and rotation invariant, which is powerful only in the case of small viewpoint changes. However, it often fails when viewpoint of faces changes in wide range. In this paper, we use Affine SIFT (Scale Invariant Feature Transformation; ASIFT) to detect affine invariant local descriptors for face recognition under wide viewpoint changes. The ASIFT is an extension of SIFT algorithm to solve this weakness. In our scheme, ASIFT is applied only to gallery face, while SIFT algorithm is applied to probe face. ASIFT generates a series of different viewpoints using affine transformation. Therefore, the ASIFT allows viewpoint differences between gallery face and probe face. Experiment results showed our framework achieved higher recognition accuracy than the original SIFT algorithm on FERET database.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.101.2-101
• /
• 2001

This paper proposes a novel face recognition algorithm to recognize human face robustly under various conditions, such as changes of pose, illumination, and expression, etc. at indoor environments. A conventional automatic face recognition system consists of the detection and the recognition part. Generally, the detection part is dominant over the other part in the estimating whole recognition rate. So, in this paper, we suggest the view-specific eigenface method as preprocessor to estimate various poses of the face in the input image. Then, we apply the Enhanced FLD Models (EFM) to the result of it, twice. Because, the EFM recognizes human face, and reduces the error of standardization effectively. To deal with view-varying problem, we build one basis vector set for each view individually. Finally, the dimensionalities of ...

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.139-144
• /
• 2023

Engineers prefer deep neural networks (DNNs) for solving computer vision problems. However, DNNs pose two major problems. First, neural networks require large amounts of well-labeled data for training. Second, the covariate shift problem is common in computer vision problems. Domain adaptation has been proposed to mitigate this problem. Recent work on adversarial-learning-based unsupervised domain adaptation (UDA) has explained transferability and enabled the model to learn robust features. Despite this advantage, current methods do not guarantee the distinguishability of the latent space unless they consider class-aware information of the target domain. Furthermore, source and target examples alone cannot efficiently extract domain-invariant features from the encoded spaces. To alleviate the problems of existing UDA methods, we propose the mixup regularization in adversarial discriminative domain adaptation (ADDA) method. We validated the effectiveness and generality of the proposed method by performing experiments under three adaptation scenarios: MNIST to USPS, SVHN to MNIST, and MNIST to MNIST-M.

• Journal of Internet Computing and Services
• /
• v.5 no.6
• /
• pp.79-91
• /
• 2004

Various facial pose detection and recognition has been a difficult problem. The problem is due to the fact that the distribution of various poses in a feature space is mere dispersed and more complicated than that of frontal faces, This thesis proposes a robust pose-expression-invariant face recognition method in order to overcome insufficiency of the existing face recognition system. First, we apply the TSL color model for detecting facial region and estimate the direction of face using facial features. The estimated pose vector is decomposed into X-V-Z axes, Second, the input face is mapped by deformable template using this vectors and 3D CANDIDE face model. Final. the mapped face is transformed to frontal face which appropriates for face recognition by the estimated pose vector. Through the experiments, we come to validate the application of face detection model and the method for estimating facial poses, Moreover, the tests show that recognition rate is greatly boosted through the normalization of the poses and expressions.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.536-538
• /
• 2006

The most important factor of mobile robot is to build a map for surrounding environment and estimate its localization. This paper proposes a real-time localization and map building method through 3-D reconstruction using scale invariant feature from monocular camera. Mobile robot attached monocular camera looking wall extracts scale invariant features in each image using SIFT(Scale Invariant Feature Transform) as it follows wall. Matching is carried out by the extracted features and matching feature map that is transformed into absolute coordinates using 3-D reconstruction of point and geometrical analysis of surrounding environment build, and store it map database. After finished feature map building, the robot finds some points matched with previous feature map and find its pose by affine parameter in real time. Position error of the proposed method was maximum. 8cm and angle error was within $10^{\circ}$.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.