Junmo Kim

Salient Region Detection via High-Dimensional Color Transform

In this paper, we introduce a novel technique to automatically detect salient regions of an image via high-dimensional color transform. Our main idea is to represent a saliency map of an image as a linear combination of high-dimensional color space where salient regions and backgrounds can be distinctively separated. This is based on an observation that salient regions often have distinctive colors compared to the background in human perception, but human perception is often complicated and highly nonlinear. By mapping a low dimensional RGB color to a feature vector in a high-dimensional color space, we show that we can linearly separate the salient regions from the background by finding an optimal linear combination of color coefficients in the high-dimensional color space. Our high dimensional color space incorporates multiple color representations including RGB, CIELab, HSV and with gamma corrections to enrich its representative power. Our experimental results on three benchmark datasets show that our technique is effective, and it is computationally efficient in comparison to previous state-of-the-art techniques.

Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition

Temporal information has useful features for recognizing facial expressions. However, to manually design useful features requires a lot of effort. In this paper, to reduce this effort, a deep learning technique, which is regarded as a tool to automatically extract useful features from raw data, is adopted. Our deep network is based on two different models. The first deep network extracts temporal appearance features from image sequences, while the other deep network extracts temporal geometry features from temporal facial landmark points. These two models are combined using a new integration method in order to boost the performance of the facial expression recognition. Through several experiments, we show that the two models cooperate with each other. As a result, we achieve superior performance to other state-of-the-art methods in the CK+ and Oulu-CASIA databases. Furthermore, we show that our new integration method gives more accurate results than traditional methods, such as a weighted summation and a feature concatenation method.

Deep Saliency with Encoded Low Level Distance Map and High Level Features

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level features for saliency detection. In this paper, we demonstrate that hand-crafted features can provide complementary information to enhance performance of saliency detection that utilizes only high level features. Our method utilizes both high level and low level features for saliency detection under a unified deep learning framework. The high level features are extracted using the VGG-net, and the low level features are compared with other parts of an image to form a low level distance map. The low level distance map is then encoded using a convolutional neural network(CNN) with multiple 1 1 convolutional and ReLU layers. We concatenate the encoded low level distance map and the high level features, and connect them to a fully connected neural network classifier to evaluate the saliency of a query region. Our experiments show that our method can further improve the performance of state-of-the-art deep learning-based saliency detection methods.

Rotating your face using multi-task deep neural network

Face recognition under viewpoint and illumination changes is a difficult problem, so many researchers have tried to solve this problem by producing the pose- and illumination- invariant feature. Zhu et al. [26] changed all arbitrary pose and illumination images to the frontal view image to use for the invariant feature. In this scheme, preserving identity while rotating pose image is a crucial issue. This paper proposes a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity. The target pose can be controlled by the users intention. This novel type of multi-task model significantly improves identity preservation over the single task model. By using all the synthesized controlled pose images, called Controlled Pose Image (CPI), for the pose-illumination-invariant feature and voting among the multiple face recognition results, we clearly outperform the state-of-the-art algorithms by more than 4~6% on the MultiPIE dataset.

Face Recognition System Using Multiple Face Model of Hybrid Fourier Feature Under Uncontrolled Illumination Variation

The authors present a robust face recognition system for large-scale data sets taken under uncontrolled illumination variations. The proposed face recognition system consists of a novel illumination-insensitive preprocessing method, a hybrid Fourier-based facial feature extraction, and a score fusion scheme. First, in the preprocessing stage, a face image is transformed into an illumination-insensitive image, called an “integral normalized gradient image,” by normalizing and integrating the smoothed gradients of a facial image. Then, for feature extraction of complementary classifiers, multiple face models based upon hybrid Fourier features are applied. The hybrid Fourier features are extracted from different Fourier domains in different frequency bandwidths, and then each feature is individually classified by linear discriminant analysis. In addition, multiple face models are generated by plural normalized face images that have different eye distances. Finally, to combine scores from multiple complementary classifiers, a log likelihood ratio-based score fusion scheme is applied. The proposed system using the face recognition grand challenge (FRGC) experimental protocols is evaluated; FRGC is a large available data set. Experimental results on the FRGC version 2.0 data sets have shown that the proposed method shows an average of 81.49% verification rate on 2-D face images under various environmental variations such as illumination changes, expression changes, and time elapses.

Deep Pyramidal Residual Networks

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage. Concurrently, the feature map dimension (i.e., the number of channels) is sharply increased at downsampling locations, which is essential to ensure effective performance because it increases the diversity of high-level attributes. This also applies to residual networks and is very closely related to their performance. In this research, instead of sharply increasing the feature map dimension at units that perform downsampling, we gradually increase the feature map dimension at all units to involve as many locations as possible. This design, which is discussed in depth together with our new insights, has proven to be an effective means of improving generalization ability. Furthermore, we propose a novel residual unit capable of further improving the classification accuracy with our new network architecture. Experiments on benchmark CIFAR-10, CIFAR-100, and ImageNet datasets have shown that our network architecture has superior generalization ability compared to the original residual networks. Code is available at https://github.com/jhkim89/PyramidNet.

Salient Region Detection via High-Dimensional Color Transform and Local Spatial Support

In this paper, we introduce a novel approach to automatically detect salient regions in an image. Our approach consists of global and local features, which complement each other to compute a saliency map. The first key idea of our work is to create a saliency map of an image by using a linear combination of colors in a high-dimensional color space. This is based on an observation that salient regions often have distinctive colors compared with backgrounds in human perception, however, human perception is complicated and highly nonlinear. By mapping the low-dimensional red, green, and blue color to a feature vector in a high-dimensional color space, we show that we can composite an accurate saliency map by finding the optimal linear combination of color coefficients in the high-dimensional color space. To further improve the performance of our saliency estimation, our second key idea is to utilize relative location and color contrast between superpixels as features and to resolve the saliency estimation from a trimap via a learning-based algorithm. The additional local features and learning-based algorithm complement the global estimation from the high-dimensional color transform-based algorithm. The experimental results on three benchmark datasets show that our approach is effective in comparison with the previous state-of-the-art saliency estimation methods.

Unsupervised Simultaneous Orthogonal basis Clustering Feature Selection

In this paper, we propose a novel unsupervised feature selection method: Simultaneous Orthogonal basis Clustering Feature Selection (SOCFS). To perform feature selection on unlabeled data effectively, a regularized regression-based formulation with a new type of target matrix is designed. The target matrix captures latent cluster centers of the projected data points by performing orthogonal basis clustering, and then guides the projection matrix to select discriminative features. Unlike the recent unsupervised feature selection methods, SOCFS does not explicitly use the pre-computed local structure information for data points represented as additional terms of their objective functions, but directly computes latent cluster information by the target matrix conducting orthogonal basis clustering in a single unified term of the proposed objective function. It turns out that the proposed objective function can be minimized by a simple optimization algorithm. Experimental results demonstrate the effectiveness of SOCFS achieving the state-of-the-art results with diverse real world datasets.

Rigid Motion Segmentation Using Randomized Voting

In this paper, we propose a novel rigid motion segmentation algorithm called randomized voting (RV). This algorithm is based on epipolar geometry, and computes a score using the distance between the feature point and the corresponding epipolar line. This score is accumulated and utilized for final grouping. Our algorithm basically deals with two frames, so it is also applicable to the two-view motion segmentation problem. For evaluation of our algorithm, Hopkins 155 dataset, which is a representative test set for rigid motion segmentation, is adopted, it consists of two and three rigid motions. Our algorithm has provided the most accurate motion segmentation results among all of the state-of-the-art algorithms. The average error rate is 0.77%. In addition, when there is measurement noise, our algorithm is comparable with other state-of-the-art algorithms.

Face recognition system using Extended Curvature Gabor classifier bunch for low-resolution face image

We describe a face recognition framework based on Extended Curvature Gabor (ECG) Classifier Bunch. First we extend Gabor wavelet kernels into the ECG wavelet kernels by adding a spatial curvature term to the kernel and adjusting the width of the Gaussian at the kernel, which leads to extraction of numerous feature candidates from a low-resolution image. To handle them efficiently, we divide a pool of feature candidates into plural ECG wavelet coefficient sets according to different kernel parameters. For each ECG wavelet coefficient set, the boosting learning scheme selects significant features. A single ECG classifier is implemented by applying Linear Discriminant Analysis (LDA) to the selected feature, and then, to overcome the accuracy limitation of a single classifier, we propose the ECG classifier bunch that combines plural ECG classifiers by means of the proposed log-likelihood ratio-based score fusion scheme. For evaluations of the proposed method, we use Face Recognition Grand Challenge (FRGC) ver 2.0 experimental protocols and database. The proposed method shows an average of 90.67% verification rate on 2D face images under uncontrolled environmental variations.