• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.7
• /
• pp.1047-1054
• /
• 2004

Internal defects in the glass, like-as micro-voids, micro-cracks, or inclusions, easily cause the failure when the glass is exposed to the shock or the thermal variation. In order to produce the highly reliable glass product, the precision inspection of the defect in the glass is required. For this purpose, this paper proposes a machine vision technique based on the auto-focusing method, which searches the defect and measures the location under the fact that the edge image of defect must be the most clear when the focal plane of CCD camera is coincided with the defect. As for the search index, the gradient indicator is presented. The basic principles are verified through the simulations for the computer-generated defect images, where the affects of defect shape, gray level of background, and the brightness of the defect image are also analyzed. Finally, experimental results for actual glass specimens are shown to confirm the applicability of this method to the actual field.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.120-127
• /
• 2010

This paper presents a SR method using adaptive interpolation based on local gradient features to obtain a high quality SR image. In this method, the distance between the interpolated pixel and the neighboring valid pixel is considered by using local gradient properties. The interpolation coefficients take the local gradient of the LR images into account. The smaller the local gradient of a pixel is, the more influence it should have on the interpolated pixel. And the median filter is finally applied to reduce the blurring and noise of the interpolated HR image. Experiment results show the effectiveness of the proposed method in comparison with other methods, especially in the edge areas of the images.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.502-504
• /
• 1995

In video image compression, it is important to extract the exact notion information from image sequence in order to perform the data compression, the field rate conversion, and the motion compensated interpolation effectively. It is well known that the location of the smallest sum of absolute difference(SAD) does not always give the true motion vector(MV) since the MV obtained via full block search is often corrupted by noise. In this paper, we first classifies the input blocks into 3 categories : the background, the shade-motion, and the edge-motion. According to the characteristics of the classified blocks, multiple locations of relatively small SAD are searched with an adaptive search window by using the proposed method. The proposed method picks MVs among those candidates by using temporal correlation. Since temporal correlation reveals the noise level in a particular region of the video image sequence, we are able to reduce the search are very effectively.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.10
• /
• pp.468-476
• /
• 2002

Digital images are easily corrupted by noise during the data transmission, data capture and data processing. A technical method of noise analyzing and adaptive filtering for reducing of quantum noise in medical radio-fluoroscopy images is presented. By adjusting the characteristics of the filter according to local statistics around each pixel of the image as moving windowing, it is possible to suppress noise sufficiently while preserve edge and other significant information required in diagnosis. We proposed adaptive weighed median(AWM) filters based on local statistics. We showed two ways of realizing the AWM filters. One is a simple type of AWM filter, which is constructed by Homogeneous factor(HF). Homogeneous factor(HF) from the noise models that enables the filter to recognize the local structures of the image is introduced, and an algorithm for determining the HF fitted to the diagnostic systems with various inner statistical properties is proposed. We show by the experimented that the performances of proposed method is superior to these of other filters and models in preserving small details and suppressing the noise at homogeneous region. The proposed algorithms were implemented by Visual C++ language on a IBM-PC Pentium 550 for testing purposes and the effects and results of the filter in the various levels of noise and images were proposed by comparing the values of NMSE(normalized mean square error) with the value of the other existing filtering methods.

• Textile Coloration and Finishing
• /
• v.20 no.1
• /
• pp.48-56
• /
• 2008

A real-time inspection system has been developed by combining CCD based image processing algorithm and a standard lighting equipment. The system was tested for defective fabrics showing nozzle contact scratch marks, which are one of the frequently occurring defects. Two algorithms used were compared according to both their processing time and detection rate. First algorithm (algorithm A) was based on morphological image processing such as dilation and opening for effective treatment of defective printing areas while second one (algorithm B) mainly employs well-defined edge detection technique based on canny detector and Zermike moment. It was concluded' that although both algorithms were quite successful, algorithm B showed relatively consistent performance than algorithm A in detecting complex patterns.

• Economic and Environmental Geology
• /
• v.29 no.4
• /
• pp.429-437
• /
• 1996

The purpose of this study is to correct the nodule abundance of FFG (Free Fall Grab) sampler on KODOS (Korea Deep Ocean Study) area in North-East Pacific Ocean. The image analysis of sea-floor photography was carried out for correcting the abundance of nodules, and the image enhancement techniques and edge detection method were used to discriminate between nodules and sediments. The trace of nodules on sediments was detected to reduce the fractionation effect in calculating the coverage of nodules. The three methods, using the coverage of nodules, using the volume density, and using corrected volume density, were utilized for the correction of the nodule abundance. The method using the coverage of nodules was more convenient and available for the correction of nodule abundance than the other two methods. The method using the corrected volume density had the highest confidence level compared with the other methods.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.4
• /
• pp.81-88
• /
• 2011

Mini Double Gears Frame is critical part of PDP and also produces couple hundred thousand every month. In the process of mass production, product inspection is very important process. Double Gear, one of the part of machine, was inspected by human eyes which caused mistakes and slow progress. To achieve the speed and accuracy the system was compensated by vision system which is inspecting automatically. The focus value is measured based on the fact that high contrast images have much high frequency edge information. High frequency term of the image is extracted using the high-pass filter and the sum of the high frequency term is used as the focus value. We used a Gaussian smoothing filter to reduce the noise and then measures the focus value using the modified Laplacian filter called a Sum modified Laplacian Focus values for the various lens positions are calculated and the position with the maximum focus value is decided as the focused position. The focus values calculated in various lens position showed the Gaussian distribution. We proposed a method to estimate the best focus position using the Gaussian curve fitting. Focus values of the uniform interval lens positions are calculated and the values are used to estimate the Gaussian distribution parameters to find the best focus position.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.1 no.1
• /
• pp.10-16
• /
• 2002

In this paper, a novel algorithm for segmentation of moving multiple vehicles in video sequences using logic operations is proposed. For the case of multiple vehicles in a scene, the proposed algorithm begins with a robust double-edge image derived from the difference between two successive frames using exclusive OR operation. After extracting only the edges of moving multiple vehicles using Laplacian filter, AND operation and dilation operation, the image is segmented into moving multiple vehicle image. The features of moving vehicles can be directly extracted from the segmented images. The proposed algorithm has no the two preprocessing steps, so it can reduce noises which are norm at in preprocessing of the original images. The algorithm is more simplified using logic operations. The proposed algorithm is evaluated on an outdoor video sequence with moving multiple vehicles in 90,000 frames of 30fps by a low-end video camera and produces promising results.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.74-86
• /
• 1994

In this paper a hierarchical stereo matching algorithm to obtain the disparity in wavelet transformed domain by using locally adaptive window and weights is proposed. The pyramidal structure obtained by wavelet transform is used to solve the loss of information which the conventional Gaussian or Laplacian pyramid have. The wavelet transformed images are decomposed into the blurred image the horizontal edges the vertical edges and the diagonal edges. The similarity between each wavelet channel of left and right image determines the relative importance of each primitive and make the algorithm perform the area-based and feature-based matching adaptively. The wavelet transform can extract the features that have the dense resolution as well as can avoid the duplication or loss of information. Meanwhile the variable window that needs to obtain precise and stable estimation of correspondense is decided adaptively from the disparities estimated in coarse resolution and LL(low-low) channel of wavelet transformed stereo image. Also a new relaxation algorithm that can reduce the false match without the blurring of the disparity edge is proposed. The experimental results for various images show that the proposed algorithm has good perfpormance even if the images used in experiments have the unfavorable conditions.