• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1140-1151
• /
• 2003

This paper proposes a face recognition method based on modified Otsu's binarization and Hu moment. Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. As the proposed modified Otsu's binarization computes other thresholds from conventional Otsu's binarization, namely we create two binary images, we can extract higher dimensional feature vector. Here the feature vector has properties of robustness to brightness and contrast changes because the proposed method is based on Otsu's binarization. And our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. In the perspective of brightness, contrast, scale, rotation, and translation changes, experimental results with Olivetti Research Laboratory (ORL) database and the AR database showed that average recognition rates of conventional well-known principal component analysis (PCA) are 93.2% and 81.4%, respectively. Meanwhile, the proposed method for the same databases has superior performance of the average recognition rates of 93.2% and 81.4%, respectively.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.163-169
• /
• 2017

There are various algorithms evaluating a threshold for image segmentation. Among them, Otsu's algorithm sets a threshold based on the histogram. It finds the between-class variance for all over gray levels and then sets the largest one as Otsu's optimal threshold, so we can see that Otsu's algorithm requires a lot of the computation. In this paper, we improved the amount of computational needs by using estimated Otsu's threshold rather than computing for all the threshold candidates. The proposed algorithm is compared with the original one in computation amount and accuracy. we confirm that the proposed algorithm is about 29 times faster than conventional method on single processor and about 4 times faster than on parallel processing architecture machine.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2924-2932
• /
• 2015

Image binarization is a process to divide the image into objects and backgrounds, widely applied to the fields of image analysis and its recognition. In the existing method of binarization, there is some uncertainty when there is insufficient brightness gap between objects and backgrounds in setting threshold. The method of fuzzy binarization has improved the features of objects efficiently. However, since this method sets ${\alpha}$-cut value statically, there remain some problems that important features of objects can be lost during binarization. Therefore, in this paper, we propose a binarization method which does not set ${\alpha}$-cut value statically. The proposed method uses fuzzy membership functions calculated by thresholds of mean, iterative, and Otsu binarization. Experiment results show the proposed method binaries various images with less loss than the existing methods.

• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.9-17
• /
• 2009

License plate recognition is an active research area. but few comparative studies on license plate binarization have been conducted. Many related researchers have experienced similar trial and error for finding an effective binarization method. To reduce this trial and error, this study implemented some binarization methods and quantitatively compared the performance of the methods. The performance evaluation consists of a low level measure and a high level measure, so it can evaluate not only the quality of binarized image itself but also the usefulness of the result. The performance evaluation was separately performed with three groups of images so as to understand the properties of the binarization methods. Experimental results show that the quality of binarization is more dependent on the evenness of illumination than the intensity of illumination. The Otsu's method has acquired the most effective performance in the group of even illumination images and the Niblack's method with parameter correction has shown the best quality in the group of uneven illumination images.

• 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 ILASS-Korea
• /
• v.29 no.2
• /
• pp.91-97
• /
• 2024

When investigating the droplet, spray, and impact of liquid on a solid plate, backlight imaging has been widely used to understand these phenomena. However, some previous studies have suffered from poor image quality. In this study, various combinations of image processing algorithms, such as white image correction, histogram equalization, CLAHE, Otsu's binarization, and multi-Otsu's binarization, have been applied to flash boiling spray images to enhance image quality for qualitative observation and semi-quantitative spray angle evaluation. To acquire images with high contrast for qualitative observation, applying CLAHE was effective, making small droplets and detailed shapes of the jet noticeable. However, when images were averaged to determine spray angle or penetration length based on intensity, this method induced artifact unphysical patterns, thus requiring careful consideration. Based on the algorithm proposed in this study, the spray angle variation according to injection pressure and temperature has been calculated, showing a reasonable trend.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.123-127
• /
• 2008

본 논문에서는 2006년 11월 신 차량 번호판 등장 이후 꾸준히 증가하고 있는 흰색 번호판 차량에서 흰색 번호판 추출에 관한 연구를 수행한다. 먼저 입력된 차랑 영상을 그레이 레벨로 변환 후, 국부적으로 밝기 보정을 수행하고, Otsu 판별식을 이용해 이진화 한다. 이진화 된 차량 영상에서 번호판 특성을 이용하며 라인 구조요소에 의한 침식연산과 채움 연산을 적용한다. 이후, 수평 투영으로 명암 변화가 심한 후보 영역을 찾고, 다시 수직 투영을 하여 일정구간에서 흰색의 값이 가장 많이 나타나는 구간을 찾는다. 마지막으로 번호판의 형태학적 특징을 이용해 번호판을 추출한다. 제안한 알고리즘을 적용한 결과 번호판 크기가 일정하지 않거나 불규칙한 조명 상태에서도 번호판 추출이 가능하였다.

• 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 Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.845-852
• /
• 2017

In this paper, we propose a binarization algorithm using LVQ-Merge clustering method for fast and accurate extraction of cells from cell images. The proposed method clusters pixel data of a given image by using LVQ to remove noise and divides the result into two clusters by applying a hierarchical clustering algorithm to improve the accuracy of binarization. As a result, the execution speed is somewhat slower than that of the conventional LVQ or Otsu algorithm. However, the results of the binarization have very good quality and are almost identical to those judged by the human eye. Especially, the bigger and the more complex the image, the better the binarization quality. This suggests that the proposed method is a useful method for medical image processing field where high-resolution and huge medical images must be processed in real time. In addition, this method is possible to have many clusters instead of two cluster, so it can be used as a method to complement a hierarchical clustering algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.21-28
• /
• 2009

Color polarity classification is a process to determine whether the color of text is bright or dark and it is prerequisite task for text extraction. In this paper we propose a color polarity method to extract text region. Based on the observation for the text and background regions, the proposed method uses the ratios of sizes and standard deviations of bright and dark regions. At first, we employ Otsu's method for binarization for gray scale input region. The two largest segments among the bright and the dark regions are selected and the ratio of their sizes is defined as the first measure for color polarity classification. Again, we select the segments that have the smallest standard deviation of the distance from the center among two groups of regions and evaluate the ratio of their standard deviation as the second measure. We use these two ratio features to determine the text color polarity. The proposed method robustly classify color polarity of the text. which has shown by experimental result for the various font and size.