Hyeran Byun

Applications of Support Vector Machines for Pattern Recognition: A Survey

In this paper, we present a comprehensive survey on applications of Support Vector Machines (SVMs) for pattern recognition. Since SVMs show good generalization performance on many real-life data and the approach is properly motivated theoretically, it has been applied to wide range of applications. This paper describes a brief introduction of SVMs and summarizes its numerous applications.

A SURVEY ON PATTERN RECOGNITION APPLICATIONS OF SUPPORT VECTOR MACHINES

In this paper, we present a survey on pattern recognition applications of Support Vector Machines (SVMs). Since SVMs show good generalization performance on many real-life data and the approach is properly motivated theoretically, it has been applied to wide range of applications. This paper describes a brief introduction of SVMs and summarizes its various pattern recognition applications.

Scene text extraction in natural scene images using hierarchical feature combining and verification

We propose a method that extracts text regions in natural scene images using low-level image features and that verifies the extracted regions through a high-level text stroke feature. Then the two level features are combined hierarchically. The low-level features are color continuity, gray-level variation and color variance. The color continuity is used since most of the characters in a text region have the same color, and the gray-level variation is used since the text strokes are distinctive to the background in their gray-level values. Also, the color variance is used since the text strokes are distinctive in their colors to the background, and this value is more sensitive than the gray-level variations. As a high level feature, text stroke is examined using multi-resolution wavelet transforms on local image areas and the feature vector is input to a SVM (support vector machine) for verification. We tested the proposed method with various kinds of the natural scene images and confirmed that extraction rates are high even in complex images.

Realtime training on mobile devices for face recognition applications

Due to the increases in processing power and storage capacity of mobile devices over the years, an incorporation of realtime face recognition to mobile devices is no longer unattainable. However, the possibility of the realtime learning of a large number of samples within mobile devices must be established. In this paper, we attempt to establish this possibility by presenting a realtime training algorithm in mobile devices for face recognition related applications. This is differentiated from those traditional algorithms which focused on realtime classification. In order to solve the challenging realtime issue in mobile devices, we extract local face features using some local random bases and then a sequential neural network is trained incrementally with these features. We demonstrate the effectiveness of the proposed algorithm and the feasibility of its application in mobile devices through empirical experiments. Our results show that the proposed algorithm significantly outperforms several popular face recognition methods with a dramatic reduction in computational speed. Moreover, only the proposed method shows the ability to train additional samples incrementally in realtime without memory failure and accuracy degradation using a recent mobile phone model.

Efficient Measurement of Eye Blinking under Various Illumination Conditions for Drowsiness Detection Systems

In this paper, we propose an efficient way of measuring the level of eye blinking under various illumination conditions (such as day and night) for drowsiness detection systems which use a single camera. Determining the level of drowsiness by using eye blinking, it is an important way of detecting eye positions and measuring eyelid movements. For robust eye detection under various illumination conditions, we propose a simple illumination compensation algorithm and a novel way of measuring of eyelid movements. In order to estimate the performance of the proposed methods, we collected video data during real driving situations under various illumination conditions, such as during the day and during the night. Experimental results demonstrate an average eye detection rate of over 98% and an accurate measurement of eye blinking when using the proposed drowsiness detection system

Incremental face recognition for large-scale social network services

Due to the rapid growth of social network services such as Facebook and Twitter, incorporation of face recognition in these large-scale web services is attracting much attention in both academia and industry. The major problem in such applications is to deal efficiently with the growing number of samples as well as local appearance variations caused by diverse environments for the millions of users over time. In this paper, we focus on developing an incremental face recognition method for Twitter application. Particularly, a data-independent feature extraction method is proposed via binarization of a Gabor filter. Subsequently, the dimension of our Gabor representation is reduced considering various orientations at different grid positions. Finally, an incremental neural network is applied to learn the reduced Gabor features. We apply our method to a novel application which notifies new photograph uploading to related users without having their ID being identified. Our extensive experiments show that the proposed algorithm significantly outperforms several incremental face recognition methods with a dramatic reduction in computational speed. This shows the suitability of the proposed method for a large-scale web service with millions of users.

Real-time pedestrian detection using support vector machines

In this paper, we present a real-time pedestrian detection method in outdoor environments. It is necessary for pedestrian detection to implement obstacle and face detection which are major parts of a walking guidance system for the visually impaired. It detects foreground objects on the ground, discriminates pedestrians from other noninterest objects, and extracts candidate regions for face detection and recognition. For effective real-time pedestrian detection, we have developed a method using stereo-based segmentation and the SVM (Support Vector Machines), which works well particularly in binary classification problem (e.g. object detection). We used vertical edge features extracted from arms, legs and torso. In our experiments, test results on a large number of outdoor scenes demonstrated the effectiveness of the proposed pedestrian detection method.

A new face authentication system for memory-constrained devices

Though biometrics to authenticate a person is a convenient tool, typical authentication algorithms by using biometrics may not be executable on the memory-constrained devices such as smart cards. We present a solution of a face authentication algorithm for open issue. Our achievement is two-fold. One is to present a face authentication algorithm with low memory requirement, which uses support vector machines (SVM) with the feature set extracted by genetic algorithms (GA). The other contribution is to suggest a method to reduce further, if needed, the amount of memory required in the authentication at the expense of verification rate by changing a controllable system parameter for a feature set size. Given a pre-defined amount of memory, this capability is quite effective to mount our algorithm on memory-constrained devices. Our experimental results show that the proposed method provides good performance in terms of accuracy and memory requirement.

Integrated region-based image retrieval using region's spatial relationships

Among representative content-based image retrieval schemes, region-based retrieval has shown promise in retrieving similar images that exhibit considerable local variations. However, since humans are accustomed to relying on object-level concepts rather than low-level regions, robust and accurate object segmentation is an essential step. We propose a new multiple-region level image retrieval algorithm based on region-level image segmentation and its spatial relationship. To capture spatial similarity, we apply Hausdorff distance (HD) to our region-based image retrieval system, FRIP (finding region in the pictures). In contrast to other object or multiple region-based retrieval systems, we update classical HD to retrieve similar regions regardless of their spatial translation, insertion, and deletion. Furthermore, we incorporate relevance feedback to reflect the users high-level query and subjectivity to the system and to compensate for performance degradation due to imperfect image segmentation. The efficacy of our method is validated using a set of 3000 images from Corel-photo CD.

SVM-based salient region(s) extraction method for image retrieval

In region-based image retrieval, not all the regions are important for retrieving similar images and rather, the user is often interested in performing a query on only salient regions. Therefore, we propose a new method for extraction of salient regions using support vector machines (SVM) and a method for importance score learning according to the users interaction. Once an image is segmented, our algorithm permits the attention window (AW) according to the variation of an image and selects salient regions by using the pre-defined feature vector and SVM within the AW. By using SVM, we do not need to determine the heuristic feature parameters and produce more reasonable results. The distance values from SVM are used for initial importance scores of salient regions and our proposed updating algorithm using relevance feedback updates them automatically. Through performance comparison with parametric salient extraction method, our proposed method shows better performance as well as semantic query interface for object-level image retrieval.