• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.76-83
• /
• 2007

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.681-683
• /
• 2023

폐암은 전 세계적으로 사망률이 가장 높은 암 질환으로, 조기 발견 및 신속한 치료를 위해서는 흉부 X-ray 영상 내 악성 결절을 놓치지 않는 것이 중요하다. 그러나 흉부 X-ray 영상은 정밀도의 한계로 진단 결과에 대한 신뢰도가 낮아, 이를 보조하는 도구의 개발이 요구된다. 기존의 폐암 진단 보조 도구는 학습 기반의 기법으로, 진단 결과에 대한 설명성(explainability)이 없다는 위험성을 갖는다. 이에 본 논문에서는 통계 분석에 기반한 결절의 석회화 여부 진단 기법을 제안한다. 제안하는 기법은 결절과 해부학적 구조물의 밝기 차 분포로부터 석회화 여부를 판단하며, 그 결과 민감도 65.22%, 특이도 88.48%, 정확도 83.41%의 성능을 보였다.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.778-787
• /
• 2003

Intrusion detection systems based on rules are not efficient for mutated attacks, because they need additional rules for the variations. In this paper, we propose an intrusion detection system using the time delay neural network. Packets on the network can be considered as gray images of which pixels represent bytes of them. Using this continuous packet images, we construct a neural network classifier that discriminates between normal and abnormal packet flows. The system deals well with various mutated attacks, as well as well known attacks.

• Journal of the Korean Society of Systems Engineering
• /
• v.1 no.2
• /
• pp.26-33
• /
• 2005

In this paper, an algorithm is presented to recognize road based on unpaved test courses image. The road images obtained by a video camera undergoes a pre-processing that includes filtering, gray level slicing, masking and identification of unpaved test courses. After this pre-processing, a part of image is grouped into 27 sub-windows and fed into a three-layer feed-forward neural network. The neural network is trained to indicate the road direction. The proposed algorithm has been tested with the images different from the training images, and demonstrated its efficacy for recognizing unpaved road. Based on the test results, it can be said that the algorithm successfully combines the traditional image processing and the neural network principles towards a simpler and more efficient driver warning or assistance system.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.8-15
• /
• 2003

In Korea, quality evaluation of dried oak mushrooms are done first by classifying them into more than 10 different categories based on the state of opening of the cap, surface pattern, and colors. And mushrooms of each category are further classified into 3 or 4 groups based on its shape and size, resulting into total 30 to 40 different grades. Quality evaluation and sorting based on the external visual features are usually done manually. Since visual features of mushroom affecting quality grades are distributed over the entire surface of the mushroom, both front (cap) and back (stem and gill) surfaces should be inspected thoroughly. In fact, it is almost impossible for human to inspect every mushroom, especially when they are fed continuously via conveyor. In this paper, considering real time on-line system implementation, image processing algorithms utilizing artificial neural network have been developed for the quality grading of a mushroom. The neural network based image processing utilized the raw gray value image of fed mushrooms captured by the camera without any complex image processing such as feature enhancement and extraction to identify the feeding state and to grade the quality of a mushroom. Developed algorithms were implemented to the prototype on-line grading and sorting system. The prototype was developed to simplify the system requirement and the overall mechanism. The system was composed of automatic devices for mushroom feeding and handling, a set of computer vision system with lighting chamber, one chip microprocessor based controller, and pneumatic actuators. The proposed grading scheme was tested using the prototype. Network training for the feeding state recognition and grading was done using static images. 200 samples (20 grade levels and 10 per each grade) were used for training. 300 samples (20 grade levels and 15 per each grade) were used to validate the trained network. By changing orientation of each sample, 600 data sets were made for the test and the trained network showed around 91 % of the grading accuracy. Though image processing itself required approximately less than 0.3 second depending on a mushroom, because of the actuating device and control response, average 0.6 to 0.7 second was required for grading and sorting of a mushroom resulting into the processing capability of 5,000/hr to 6,000/hr.

• Korean Journal of Radiology
• /
• v.24 no.3
• /
• pp.247-258
• /
• 2023

Objective: To localize the neuroanatomical substrate of rapid eye movement sleep behavior disorder (RBD) and to investigate the neuroanatomical locational relationship between RBD and α-synucleinopathy neurodegenerative diseases. Materials and Methods: Using a systematic PubMed search, we identified 19 patients with lesions in different brain regions that caused RBD. First, lesion network mapping was applied to confirm whether the lesion locations causing RBD corresponded to a common brain network. Second, the literature-based RBD lesion network map was validated using neuroimaging findings and locations of brain pathologies at post-mortem in patients with idiopathic RBD (iRBD) who were identified by independent systematic literature search using PubMed. Finally, we assessed the locational relationship between the sites of pathological alterations at the preclinical stage in α-synucleinopathy neurodegenerative diseases and the brain network for RBD. Results: The lesion network mapping showed lesions causing RBD to be localized to a common brain network defined by connectivity to the pons (including the locus coeruleus, dorsal raphe nucleus, central superior nucleus, and ventrolateral periaqueductal gray), regardless of the lesion location. The positive regions in the pons were replicated by the neuroimaging findings in an independent group of patients with iRBD and it coincided with the reported pathological alterations at post-mortem in patients with iRBD. Furthermore, all brain pathological sites at preclinical stages (Braak stages 1-2) in Parkinson's disease (PD) and at brainstem Lewy body disease in dementia with Lewy bodies (DLB) were involved in the brain network identified for RBD. Conclusion: The brain network defined by connectivity to positive pons regions might be the regulatory network loop inducing RBD in humans. In addition, our results suggested that the underlying cause of high phenoconversion rate from iRBD to neurodegenerative α-synucleinopathy might be pathological changes in the preclinical stage of α-synucleinopathy located at the regulatory network loop of RBD.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.703-715
• /
• 2017

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and gray-level co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2644-2657
• /
• 2018

To utilize the energy of sensor nodes efficiently and extend the network lifetime maximally is one of the primary goals in wireless sensor networks (WSNs). Thus, designing an energy-efficient protocol to optimize the determination of cluster heads (CHs) in WSNs has become increasingly important. In this paper, we propose a novel energy-efficient protocol based on an improved Grey Wolf Optimizer (GWO), which we refer to as Fitness value based Improved GWO (FIGWO). It considers a fitness value to improve the finding of the optimal solution in GWO, which ensures a better distribution of CHs and a more balanced cluster structure. According to the distance to the CHs and the BS, sensor nodes' transmission distance are recalculated to reduce the energy consumption. Simulation results demonstrate that the proposed approach can prolong the stability period of the network in comparison to other algorithms, namely by 31.5% in comparison to SEP, and even by 57.8% when compared with LEACH protocol. The results also show that the proposed protocol performs well over the above comparative protocols in terms of energy consumption and network throughput.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.549-555
• /
• 2006

An edge detection is an very important area in image processing and computer vision, General edge detection methods (Robert mask, Sobel mask, Kirsh mask etc) are a good performance to detect step edge in a image but are no good performance to detect step edge in a noses image. We suggested a step edge detection method based on image information measure and neutral network. Using these essential properties of step edges, which are directional and structural and whose gray level distribution in neighborhood, as a input vector to the BP neutral network we get the good result of proposed algorithm. And also we get the satisfactory experimental result using rose image and cell images an experimental and analysing image.