• Journal of the Korea Society of Computer and Information
• /
• v.20 no.7
• /
• pp.9-16
• /
• 2015

This paper proposes the parallel design of a shot change detection algorithm using frame segmentation and moving blocks. In the proposed approach, the high parallel processing components, such as frame histogram calculation, block histogram calculation, Otsu threshold setting function, frame moving operation, and block histogram comparison, are designed in parallel for NVIDIA GPU. In order to minimize memory access delay time and guarantee fast computation, the output of a GPU kernel becomes the input data of another kernel in a pipeline way using the shared memory of GPU. In addition, the optimal sizes of CUDA processing blocks and threads are estimated through the prior experiments. In the experimental test of the proposed shot change detection algorithm, the detection rate of the GPU based parallel algorithm is the same as that of the CPU based algorithm, but the average of processing time speeds up about 6~8 times.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.149-156
• /
• 2003

This paper proposes a face recognition method based on modified Otsu binarization, Hu moment and linear discriminant analysis (LDA). Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. Modified Otsu binarization can make binary images that have the invariant characteristic in brightness and contrast changes. From edge and multi-level binary images obtained by the threshold method, we compute the 17 dimensional Hu moment and then extract feature vector using LDA algorithm. Especially, our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. Experimental results showed that our method had almost a superior performance compared with the conventional well-known principal component analysis (PCA) and the method combined PCA and LDA in the perspective of brightness, contrast, scale, rotation, and translation changes with Olivetti Research Laboratory (ORL) database and the AR database.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.2
• /
• pp.590-599
• /
• 2017

In South Korea, sewage pipeline exploration devices have been developed using high resolution digital cameras of 2 mega-pixels or more. On the other hand, most devices are less than 300 kilo-pixels. Moreover, because 100 kilo-pixels devices are used widely, the environment for image processing is very poor. In this study, very low resolution ($240{\times}320$ = 76,800 pixels) images were adapted when it is difficult to detect cracks. Considering that the images of sewers in South Korea have very low resolution, this study selected low resolution images to be investigated. An automatic crack detection technique was studied using digital image processing technology for low resolution images of sewage pipelines. The authors developed a program to automatically detect cracks as 6 steps based on the MATLAB functions. In this study, the second step covers an algorithm developed to find the optimal threshold value, and the fifth step deals with an algorithm to determine cracks. In step 2, Otsu's threshold for images with a white caption was higher than that for an image without caption. Therefore, the optimal threshold was found by decreasing the Otsu threshold by 0.01 from the beginning. Step 5 presents an algorithm that detects cracks by judging that the length is 10 mm (40 pixels) or more and the width is 1 mm (4 pixels) or more. As a result, the crack detection performance was good despite the very low-resolution images.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.252-259
• /
• 2022

Artificial intelligence is used in fusion with image processing techniques using cameras. Image processing technology is a technology that processes objects in an image received from a camera in real time, and is used in various fields such as security monitoring and medical image analysis. If such image processing reduces the accuracy of recognition, providing incorrect information to medical image analysis, security monitoring, etc. may cause serious problems. Therefore, this paper uses a mixture of YOLOv4-tiny model and image processing algorithm and uses the COCO dataset for learning. The image processing algorithm performs five image processing methods such as normalization, Gaussian distribution, Otsu algorithm, equalization, and gradient operation. For RGB images, three image processing methods are performed: equalization, Gaussian blur, and gamma correction proceed. Among the nine algorithms applied in this paper, the Equalization and Gaussian Blur model showed the highest object detection accuracy of 96%, and the gamma correction (RGB environment) model showed the highest object detection rate of 89% outdoors (daytime). The image binarization model showed the highest object detection rate at 89% outdoors (night).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.5
• /
• pp.1064-1069
• /
• 2013

In this paper, we propose a Musical Score Recognition with SOM and Enhanced ART-1 Algorithm. First, we apply Hough transform and Otsu's binarization to the original BMP format image and extract notes from separated passages by histogram analysis with removing staff lines. Then extracted musical notes are normalized to same size by SOM algorithm and ART-1 algorithm plays the learning and recognition role. The experiment verifies that the proposed method is quite effective on printed musical score recognition.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.49-54
• /
• 2016

Medical image processing is a compulsory process to diagnose many kinds of disease. Therefore, an automatic algorithm for this task is highly demanded as an important part to construct a computer-aided diagnosis system. In this paper, we introduce an automatic method to segment the liver region from 3D abdominal CT images using Otsu method. First, we choose a 2D slice which has most liver information from the whole 3D image. Secondly, on the chosen slice, we enhanced the image based on its intensity using Otsu method with multiple thresholds and use the threshold to enhance the whole 3D image. Then, we apply a liver mask to mark the candidate liver region. After that, we execute the Otsu method again to segment the liver region from the chosen slice and propagate the result to the whole 3D image. Finally, we apply preprocessing on the frontal side of 3D images to crop only the liver region from the image.

• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.195-202
• /
• 2009

In this paper, we propose the regions segmentation method of the white matter and the gray matter for brain MR image by using the ant colony optimization algorithm. Ant Colony Optimization (ACO) is a new meta heuristics algorithm to solve hard combinatorial optimization problem. This algorithm finds the expected pixel for image as the real ant finds the food from nest to food source. Then ants deposit pheromone on the pixels, and the pheromone will affect the motion of next ants. At each iteration step, ants will change their positions in the image according to the transition rule. Finally, we can obtain the segmentation results through analyzing the pheromone distribution in the image. We compared the proposed method with other threshold methods, viz. the Otsu' method, the genetic algorithm, the fuzzy method, and the original ant colony optimization algorithm. From comparison results, the proposed method is more exact than other threshold methods for the segmentation of specific region structures in MR brain image.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.15-23
• /
• 2016

This paper proposes an effective algorithm of Korean license plate recognition. By applying Haar-like feature and Canny edge detection on a captured vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are classified using neural networks trained by backpropagation algorithm to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.431-436
• /
• 2014

Cell segmentation which extracts cell objects from background is one of basic works in bio-imaging which analyze cell images acquired from live cells in cell culture. In the case of clear images, they have a bi-modal histogram distribution and segmentation of them can easily be performed by global threshold algorithm such as Otsu algorithm. But In the case of degraded images, it is difficult to get exact segmentation results. In this paper, we developed a cell segmentation system that it classify input images by the type of their histogram distribution and then apply a proper segmentation algorithm. If it has a bi-modal distribution, a global threshold algorithm is applied for segmentation. Otherwise it has a uni-modal distribution, our algorithm is performed. By experimentation, our system gave exact segmentation results for uni-modal cell images as well as bi-modal cell images.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.975-988
• /
• 2020

Change detection is the process of identifying changes by observing the multi-temporal images at different times, and it is an important technique in remote sensing using satellite images. Among the change detection methods, the unsupervised change detection technique has the advantage of extracting rapidly the change area as a binary image. However, it is difficult to understand the changing pattern of land cover in binary images. This study used grid points generated from seamless digital map to evaluate the satellite image change detection results. The land cover change results were extracted using multi-temporal KOMPSAT-3A (K3A) data taken by Gimje Free Trade Zone and change detection algorithm used Spectral Angle Mapper (SAM). Change detection results were presented as binary images using the methods Otsu, Kittler, Kapur, and Tsai among the automated threshold selection algorithms. To consider the seasonal change of vegetation in the change detection process, we used the threshold of Differenced Normalized Difference Vegetation Index (dNDVI) through the probability density function. The experimental results showed the accuracy of the Otsu and Kapur was the highest at 58.16%, and the accuracy improved to 85.47% when the seasonal effects were removed through dNDVI. The algorithm generated based on this research is considered to be an effective method for accuracy assessment and identifying changes pattern when applied to unsupervised change detection.