• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.304-306
• /
• 2007

Methods of Object recognition from camera image are to compare features of color. edge or pattern with model in a general way. SIFT(scale-invariant feature transform) has good performance but that has high complexity of computation. Using simple color histogram has low complexity. but low performance. In this paper we represent a model as a color cooccurrence histogram. and we improve performance using pyramid matching. The color cooccurrence histogram keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color cooccurrence histogram adds geometric information to the normal color histogram. We suggest object recognition by pyramid matching of color cooccurrence histogram.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.199-204
• /
• 2008

Visual surveillance is an active topic recently in Computer Vision. Event detection and recognition is one important and useful application of visual surveillance system. In this paper, we propose a new method to recognize the entering and exiting events based on the human's movement feature and the door's state. Without sensors, the proposed approach is based on novel and simple vision method as a combination of edge detection, motion history image and geometrical characteristic of the human shape. The proposed method includes several applications such as access control in visual surveillance and computer vision fields.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.217-221
• /
• 2002

In this paper, we propose a new scheme of motion tracking based on fuzzy inference (FI)and wavelet transform (WT) from image sequences. First, we present a WT to segment a feature extraction of dynamic image . The coefficient matrix for 2-level DWT tent to be clustered around the location of important features in the images, such as edge discontinuities, peaks, and corners. But these features are time varying owing to the environment conditions. Second, to reduce the spatio-temporal error, We develop a fuzzy inference algorithm. Some experiments are peformed to testify the validity and applicability of the proposed system. As a result, proposed method is relatively simple compared with the traditional space domain method. It is also well suited for motion tracking under the conditions of variation of illumination.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.934-936
• /
• 1995

To get a good result of the feature-based stereo matching, contour of buildings must be extracted exactly. In this paper, an algorithm that extracts contour of flat top buildings exactly is proposed. The Algorithm is composed of three steps. One is to find corner points of 4 types in whole image and another is to extract exact lines between coners by edge following technique, the third is to extract exact contour of buildings using binding structures. We have a good result in extracting contour of buildings.

• Journal of information and communication convergence engineering
• /
• v.5 no.1
• /
• pp.50-53
• /
• 2007

This paper presents face features detection and a new physiological neuro-fuzzy learning method by using two-dimensional variances based on variation of gray level and by learning for a statistical distribution of the detected face features. This paper reports a method to learn by not using partial face image but using global face image. Face detection process of this method is performed by describing differences of variance change between edge region and stationary region by gray-scale variation of global face having featured regions including nose, mouse, and couple of eyes. To process the learning stage, we use the input layer obtained by statistical distribution of the featured regions for performing the new physiological neuro-fuzzy algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1718-1723
• /
• 2014

We proposes the method to detect the Hangul and English character region from natural image using structural feature of Hangul and English Characters. First, we extract edge features from natural image, Next, if features are not corresponding to the heuristic rule of character features, extracted features filtered out and select candidates of character region. Next, candidates of Hangul character region are merged into one Hangul character using Hangul character merging algorithm. Finally, we detect the final character region by Hangul character class decision algorithm. English character region detected by edge features of English characters. Experimental result, proposed method could detect a character region effectively in images that contains a complex background and various environments. As a result of the performance evaluation, A proposed method showed advanced results about detection of Hangul and English characters region from natural image.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.125-132
• /
• 2021

As the layers of artificial neural network deepens, and the dimension of data used as an input increases, there is a problem of high arithmetic operation requiring a lot of arithmetic operation at a high speed in the learning and recognition of the neural network (NN). Thus, this study proposes a data dimensionality reduction method to reduce the dimension of the input data in the NN. The proposed Line-segment Feature Analysis (LFA) algorithm applies a gradient-based edge detection algorithm using median filters to analyze the line-segment features of the objects existing in an image. Concerning the extracted edge image, the eigenvalues corresponding to eight kinds of line-segment are calculated, using 3×3 or 5×5-sized detection filters consisting of the coefficient values, including [0, 1, 2, 4, 8, 16, 32, 64, and 128]. Two one-dimensional 256-sized data are produced, accumulating the same response values from the eigenvalue calculated with each detection filter, and the two data elements are added up. Two LFA256 data are merged to produce 512-sized LAF512 data. For the performance evaluation of the proposed LFA algorithm to reduce the data dimension for the recognition of handwritten numbers, as a result of a comparative experiment, using the PCA technique and AlexNet model, LFA256 and LFA512 showed a recognition performance respectively of 98.7% and 99%.

• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.239-245
• /
• 2017

For privacy protection, we propose a vehicle license plate region detection method in road view image served from portal site. Because vehicle license plate regions in road view images have different feature depending on distance, long distance vehicle license plate regions are not detected by feature of low resolution. Therefore, we suggest a method to detect short distance vehicle license plate regions by edge feature and long distance vehicle license plate regions using MSER feature. And then, we select candidate region of vehicle license plate region from detected region of each method, because the number of the vehicle license plate has a structural feature, we used it to detect the final vehicle license plate region. As the experiment result, we got a recall rate of 93%, precision rate of 75%, and F-Score rate of 80% in various road view images.

• Journal of the Optical Society of Korea
• /
• v.17 no.2
• /
• pp.188-199
• /
• 2013

This paper presents a novel algorithm for nighttime detection of the lane markers painted on a road at night. First of all, the proposed algorithm uses neighborhood average filtering, 8-directional Sobel operator and thresholding segmentation based on OTSU's to handle raw lane images taken from a digital CCD camera. Secondly, combining intensity map and gradient map, we analyze the distribution features of pixels on boundaries of lanes in the nighttime and construct 4 feature sets for these points, which are helpful to supply with sufficient data related to lane boundaries to detect lane markers much more robustly. Then, the searching method in multiple directions- horizontal, vertical and diagonal directions, is conducted to eliminate the noise points on lane boundaries. Adapted Hough transformation is utilized to obtain the feature parameters related to the lane edge. The proposed algorithm can not only significantly improve detection performance for the lane marker, but it requires less computational power. Finally, the algorithm is proved to be reliable and robust in lane detection in a nighttime scenario.

• Smart Structures and Systems
• /
• v.33 no.2
• /
• pp.105-118
• /
• 2024

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.