• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.561-566
• /
• 2023

With the development of deep learning, it is possible to solve various computer non-specialized problems such as image processing. However, most image processing methods use only the visual information of the image to process the image. Text data such as descriptions and annotations related to images may provide additional tactile and visual information that is difficult to obtain from the image itself. In this paper, we intend to improve image classification accuracy through a deep learning model that analyzes images and texts using image-text pairs. The proposed model showed an approximately 11% classification accuracy improvement over the deep learning model using only image information.

• The Korean Journal of Physiology and Pharmacology
• /
• v.7 no.6
• /
• pp.317-323
• /
• 2003

Interneuron diversity is one of the key factors to hinder understanding the mechanism of cortical neural network functions even with their important roles. We characterized inhibitory interneurons in layer II/III of the rat primary visual cortex, using patch-clamp recording and confocal reconstruction, and classified inhibitory interneurons into fast spiking (FS), late spiking (LS), burst spiking (BS), and regular spiking non-pyramidal (RSNP) neurons according to their electrophysiological characteristics. Global parameters to identify inhibitory interneurons were resting membrane potential (＞-70 mV) and action potential (AP) width (＜0.9 msec at half amplitude). FS could be differentiated from LS, based on smaller amplitude of the AP (＜∼50 mV) and shorter peak-to-trough time (P-T time) of the afterhyperpolarization (＜4 msec). In addition to the shorter AP width, RSNP had the higher input resistance (＞200 $M{Omega}$) and the shorter P-T time (＜20 msec) than those of regular spiking pyramidal neurons. Confocal reconstruction of recorded cells revealed characteristic morphology of each subtype of inhibitory interneurons. Thus, our results provide at least four subtypes of inhibitory interneurons in layer II/III of the rat primary visual cortex and a classification scheme of inhibitory interneurons.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.79-82
• /
• 2015

Bag of visual words(BoVW) is one of the image classification and retrieval methods, using feature point that automatical sorting and searching system by image feature vector of data base. The existing method using feature point shall search or classify the image that user unwanted. To solve this weakness, when comprise the words, include not only feature point but color information that express overall mood of image or texture information that express repeated pattern. It makes various searching possible. At the test, you could see the result compared between classified image using the words that have only feature point and another image that added color and texture information. New method leads to accuracy of 80~90%.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.358-363
• /
• 1992

The tire manufacturing process demands classification of tire types when the tires are transferred between the inner processes. Though most processes are being well automated, the classification relies greatly upon the visual inspection of humen. This has been an obstacle to the factory automation of tire manufacturing companies. This paper proposes an effective vision systems which can be usefully applied to the tire classification process in real time. The system adopts a parallel architecture using multiple transputers and contains the algorithms of preprocesssing for character recognition. The system can be easily expandable to manipulate the large data that can be processed seperately.

• The Journal of Korea Robotics Society
• /
• v.5 no.4
• /
• pp.339-348
• /
• 2010

One of the requirements for autonomous vehicles on off-road is to move stably in unstructured environments. Such capacity of autonomous vehicles is one of the most important abilities in consideration of mobility. So, many researchers use contact and/or non-contact methods to determine a terrain whether the vehicle can move on or not. In this paper we introduce an algorithm to classify terrains using visual information(one of the non-contacting methods). As a pre-processing, a contrast enhancement technique is introduced to improve classification of terrain. Also, for conducting classification algorithm, training images are grouped according to materials of the surface, and then Bayesian classification are applied to new images to determine membership to each group. In addition to the classification, we can build Traversability map specified by friction coefficients on which autonomous vehicles can decide to go or not. Experiments are made with Load-Cell to determine real friction coefficients of various terrains.

• Journal of Environmental Science International
• /
• v.23 no.1
• /
• pp.143-152
• /
• 2014

The results which are from naturalness assessment and visual assessment was examined to accomplish a classification, a conclusion, a comparison and an analysis. Also statistical test was examined to identify applicability of the survey to other rivers according to the result of visual assessment. As a result of naturalness assessment and visual assessment, evaluation rate of Geumho river is the highest rank of the grade as 2.5. Also t-test was examined to apply items of visual assessment at other rivers through differences in means of river naturalness rates from which visual assessment results. Most of differences in means of river naturalness rates are significant. Thus assessment criteria can be applied to other rivers to find out unique characteristics because each item has independent characteristics.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2003.11a
• /
• pp.277-282
• /
• 2003

The purpose of this study is to investigate the architectural visual identity, and scheme of conceptional extent of architectural visual identity through literature research and sample analysis by design factors for apartment design. Korea National Housing Corporation's Mapo apartment put first caterer which is continued about 30 years to solve shortage of houses by beginning and the impact of IMF and the price decontrol on second half in the 1990s have changed the housing status to commercial goods. Construction companies have introduced brand concept to satisfy consumer's appetite in production of house goods including apartment under market situation. Importance of visual identity in apartment design occupies has risen in heftily. However most companies are in condition of stay on two-dimensional application that uses symbol, logotype, and character assistance. Several high position construction companies are trying architectural visual identity, but those are applied in partial element and those are not going forward to systematic classification and synthetic visual identity plan within peculiarity of apartment complex. This study is to grasp plan and design tendency to acquire identity of design element of construction field and goods through design examination. In conclusion visual identity in apartment design is architectural visual identity on all of 2 dimensions and 3 dimension for application. Architectural visual identity is a language of form that prescribe identity about external appearance in combination with brand image.

• Journal of Korean Public Health Nursing
• /
• v.35 no.1
• /
• pp.149-164
• /
• 2021

Purpose: To identify the factors associated with poor self-rated health in individuals with acquired visual impairment through classification of such individuals into severe and mild visual impairment groups. Methods: This descriptive, cross-sectional, survey-based study analyzed data from 563 individuals with visual impairment due to acquired causes who had been recruited in the 2017 Korean National Survey on Persons with Disabilities. Results: Individuals with severe visual impairment reported poorer self-rated health. Mild depression (p=.003), and low smartphone use (p=.045) were associated with poorer self-rated health in those with severe visual impairment. The factors associated with poor self-rated health in those with mild visual impairment were comorbidities, low smartphone use (p=.006), needed health information (p=.020), unbalanced diet (p<.001), low weight (p=.024), and lack of health checkups (p=.001). Conclusion: Depression was found to be a predictor of poor self-rated health in individuals with severe visual impairment, which highlights the need for nursing and related healthcare intervention to lower depression in this specific population. Further, promoting social network building and providing health information using smartphones may serve to encourage appropriate health behavior in people with severe visual impairment who have reduced mobility and health literacy.