• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.3
• /
• pp.193-198
• /
• 2015

A large number of vision applications rely on matching keypoints across images. Pedestrian detection is under constant pressure to increase both its quality and speed. Such progress allows for new application. A higher speed enables its inclusion into large systems with extensive subsequent processing, and its deployment in computationally constrained scenarios. In this paper, we focus on improving the speed of pedestrian detection using HOG(histogram of oriented gradient) and multi frame operation which is robust to illumination changes in cluttering images. The result of our simulation indicates that the detection rate and speed of the proposed method is much faster than that of conventional HOG and differential images.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.64 no.3
• /
• pp.187-192
• /
• 2015

Detecting human in images is a challenging task owing to their variable appearance and the wide range of poses the they can adopt. The first need is a robust feature set that allows the human form to be discriminated cleanly, even in cluttered background under difficult illumination. A large number of vision application rely on matching keypoints across images. These days, the deployment of vision algorithms on smart phones and embedded device with low memory and computation complexity has even upped the ante: the goal is to make descriptors faster compute, more compact while remaining robust scale, rotation and noise. In this paper we focus on improving the speed of pedestrian(walking person) detection using Histogram of Oriented Gradient(HOG) descriptors provide excellent performance and tracking using kalman filter.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.864-869
• /
• 1993

This paper presents the problem of automatically recognizing embossed or molded characters which are raised from the side wall on rubber tire. In the tire image objects have approximately the same gray-value as the background and because of the tire geometry, illumination of the surface is nonhomogenous. Therefore it is difficult to recognize the raised tire character. In this paper, for describing the process of processing three steps have been proposed: 1) MIN & MAX smoothing operation filter, 2) edge detection algorithm using modified laplacian operator, 3) noise rejection. Afterwards, segmentation is done to attain characters from tire image by projection method. The recognition of the characters in the segmented image is carried out by using multilayered neural network, which is insensitive to the noise.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.641-648
• /
• 2001

A face detection in color images is important for many multimedia applications. It is first step for face recognition and can be used for classifying specific shorts. This paper describes a new method to detect faces in color images based on the skin color and hair color. This paper presents a fuzzy-based method for classifying skin color region in a complex background under varying illumination. The Fuzzy rule bases of the fuzzy system are generated using training method like a genetic algorithm(GA). We find the skin color region and hair color region using the fuzzy system and apply the convex-hull to each region and find the face from their intersection relationship. To validity the effectiveness of the proposed method, we make experiment with various cases.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.138.3-138
• /
• 2001

Because face has non-rigid structure and is influenced by illumination, we need robust face detection algorithm with the variations of external environments (orientation of lighting and face, complex background, etc.). In this paper we develop a new face detection algorithm to achieve robustness. First we transform RGB color into other color space, in which we can reduce lighting effect much. Second, hierarchical image segmentation technique is used for dividing a image into homogeneous regions. This process uses not only color information, but also spatial information. One of them is used in segmentation by histogram analysis, the other is used in segmentation by grouping. And we can select face region among the homogeneous regions by using facial features.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.15-17
• /
• 2006

This paper presents a new global intensity compensation method for extracting moving object in a visual surveillance system by compensating time variant intensity changes of background region. The method that compensates a little changes of intensity due to time variant illumination change and automatic gain control of camera is called global intensity compensation. The proposed method expresses global intensity change with a mapping table to describe complex form of intensity change while the previous method models this global intensity change with a simple function as a straight line. The proposed method builds the mapping table by calculating the cross histogram between two images and then by selecting an initial point for generating the mapping table by using Hough transform applied to the cross histogram image. Then starting from the initial point, the mapping table is generated according to the proposed algorithm based on the assumption that reflects the characteristic of global intensity change. Experimental results show that the proposed method makes the compensation error much smaller than the previous GIC method

• The Journal of Korea Robotics Society
• /
• v.5 no.3
• /
• pp.262-269
• /
• 2010

This paper presents a probabilistic head tracking method, mainly applicable to face recognition and human robot interaction, which can robustly track human head against various variations such as pose/scale change, illumination change, and background clutters. Compared to conventional particle filter based approaches, the proposed method can effectively track a human head by regularizing the sample space and sequentially weighting multiple visual cues, in the prediction and observation stages, respectively. Experimental results show the robustness of the proposed method, and it is worthy to be mentioned that some proposed probabilistic framework could be easily applied to other object tracking problems.

• Proceedings of the KSEEG Conference
• /
• 2002.04a
• /
• pp.159-162
• /
• 2002

We tried to obtain an initial velocity model for prestack depth migration via waveform inversion. For application of any field data we chose a smooth background layered velocity model (v=v0 + k x z) as an initial velocity model. Newton type waveform inversion needs to invert huge Hessian matrix. In order to compute full Hessian matrix arising from full aperture data and full illumination zone, we meet insurmountable difficulties of paying astronomical computing cost. For the layered media, approximate Hessian emerging from single shot aperture data can be used repeatedly for split spread source configuration. In our work of using this Hessian characteristic of layered media we attempted to obtain the approximate velocity model as close as possible to the true velocity model in first iteration.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.5
• /
• pp.1-8
• /
• 2001

A measuring system is developed to acquire static image from rotary state through CCD camera in back light illumination by synchronizing chopper to workpiece. In image processing of acquired image, lowpass filter is very useful in view of noise removal, and optimum binary image can be made through histogram equalization which is one of the histogram technique to maximize brightness intensity between workpiece and background. After image treatment applying Laplacian operator, surface roughness is calculated by introducing conversion coefficient of pixel which edge is composed of.

• Smart Media Journal
• /
• v.2 no.1
• /
• pp.31-36
• /
• 2013

A robust and efficient text extraction is very important for an accuracy of Optical Character Recognition (OCR) systems. Natural scene images with degradations such as uneven illumination, perspective distortion, complex background and multi color text give many challenges to computer vision task, especially in text extraction. In this paper, we propose a method for extraction of the text in signboard images based on a combination of mean shift algorithm and weighting scheme of hue and saturation in HSI color space for clustering algorithm. The number of clusters is determined automatically by mean shift-based density estimation, in which local clusters are estimated by repeatedly searching for higher density points in feature vector space. Weighting scheme of hue and saturation is used for formulation a new distance measure in cylindrical coordinate for text extraction. The obtained experimental results through various natural scene images are presented to demonstrate the effectiveness of our approach.