• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.3
• /
• pp.217-226
• /
• 2003

A novel fingerprint ridge feature extraction using sequential labeling of thinned fingerprint image is proposed, which is invariant to position translation, scaling, and rotation. the proposed algorithm labels ridges of thinned fingerprint image sequentially using vertical line that goes through fingerprint core point. Then, we extract a feature from each labeled ridge and the extraction process is based on the type fo the ridge and a minutiae ridge angle in the ridge. The feature extracted through this process enables us to find out the kind of various minutiae and minutiae angle. As a result of the experiment using two thinned fingerprint images, we finally confirm that proposed algorithm is not related to position translation, scaling, and rotation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.196-199
• /
• 2010

The human eyes are important facial landmarks for image normalization due to their relatively constant interocular distance. This paper introduces a novel approach for the eye detection task using optimal segmentation method for eye representation. The method consists of three steps: (1)edge extraction method that can be used to accurately extract eye region from the gray-scale face image, (2)extraction of eye region using labeling method, (3)eye localization based on intensity information. Experimental results show that a correct eye detection rate of 98.9% can be achieved on 2408 FERET images with variations in lighting condition and facial expressions.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.4
• /
• pp.69-77
• /
• 2018

The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert's labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert's labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.338-340
• /
• 2019

Recently, the speed and size of data accumulation are increasing due to the development of networks. There are many difficulties in classifying these data. One of the difficulties is the difficulty of labeling. Labeling is usually done by people, but it is very difficult for everyone to understand the data in the same way and it is very difficult to label them on the same basis. In order to solve this problem, we implemented GAN to generate new image based on input image and to learn input data indirectly by using it for learning. This suggests that the accuracy of classification can be increased by increasing the number of learning data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10b
• /
• pp.822-825
• /
• 1988

In this paper, we present a system which enables a real-time measurement of the number and also the body length of the fry (baby fish) using a line image sensor. Here, we consider a situation that fry are transported from a pond to another, pond through a pipe. At one position of the pipe a transparent rectanglar channel is mounted. The images of the fry, which run through this rectanglar channel, are detected by a line image sensor. The image signals are digitized to binary ones and the contour of the fry are detected. After that, a real-time image analysis is executed with a digital signal processor. Labeling program analyses the connection of every pixel. The results are transfered to a personal computer and displayed on the online monitor graphically.

• Journal of Animal Environmental Science
• /
• v.5 no.3
• /
• pp.139-148
• /
• 1999

This study was conducted to develop an image processing system which can classify the pig's thermoregulatory behavior under the different environmental conditions. The 4 pigs of 25kg were housed in the environmentally controlled chamber(1.4m$\times$2.2m floor space). Postural behavior of the pigs was captured with an CCD color camera. The raw behavioral images were processed by thresholoding, reduction, separation of slightly contacted pigs, labeling, noise removal, computation of number of labels, and classification of the pig's behavior. The correct classification rate of the image processing system was 97.8%(88 out of 90 testing images). The results of this study showed that the image processing system could be used for a behavior-based automatic environmental controller.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.173-181
• /
• 2014

In this paper, the algorithm that can automatically segment the lung, the airway and the pulmonary vessels in a chest CT was proposed. The proposed method is progressed in three steps. In the first step, the lung and the airway are segmented by the region growing law through the optimal threshold and three-dimensional labeling. In the second, from the start point to the first carina of the airway is segmented by the deduction operation, and the next airway of the bifurcations are segmented by applying a variable threshold technique. In the third step, the left/right lungs are divided by the restoration process for the lung, and the outside of lungs for abnormal is checked by applying the advanced rolling ball algorithm, and if abnormal is found, that part is removed, and it is restored to the normal lungs by connecting the outside of the lung in the form of second-order polynomial. Finally, pulmonary vessels are segmented by applying the three-dimensional connected component labeling method and three-dimensional region growing method. As the results of simulation, it could be confirmed that the pulmonary vascular is accurately divided without loss of tissue around lung.

• The Korean Journal of Nuclear Medicine
• /
• v.28 no.2
• /
• pp.167-171
• /
• 1994

Ethylcystein dimer (ECD) was synthesized by dimerizatlon of L-thiazolidine-4-carboxylic acid in liquid ammania with sodium metal and successive esterification in ethanolic solution of hydrogen chlorde. The purified product was labeled with $^{99m}Tc$ in the presence of sodium glucarate(pH= 5.6) and stannous chloride. Best result was obtained from the preparation con sisting of 0.1mg ECD, $40{\mu}l$ of 0.4M sodium glucarate (pH=5.6), and $20{\mu}g$ of stannous chloride. The labeling efficiency was 90% with previous condition. The labeled $^{99m}Tc$-ECD was stable at least for 3 hours in PBS(pH=7.4) at room temperature. About 10mCi of $^{99m}Tc$-ECD was injected to normal volunteer, and SPECT image of brain was obtained by triple head camera 10 minutes after inection. The image showed similar distribution of radioactivity in brain with that of HMPAO image.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.309-316
• /
• 2014

In this paper, we propose an efficient detph map creation method using Graph Cut and Discrete Wavelet Transform. First, we have segmented the original image by using Graph Cut to process with its each areas. After that, the information which describes segmented areas of original image have been created by proposed labeling method for segmented areas. And then, we have created four subbands which contain the original image's frequency information. Finally, the depth map have been created by frequency map which made with HH, HL subbands and depth information calculation along the each segmented areas. The proposed method can perform efficient depth map creation process because of dynamic allocation using depth information. We also have tested the proposed method using PSNR(Peak Signal to Noise Ratio) method to evaluate ours.