• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.405-408
• /
• 2003

This paper proposes a new algorithm for cloudy area detection using K-Means and GHA (Generalized Hebbian Algorithm). K-Means is one of simple classification algorithm, and GHA is unsupervised neural network for data compression and pattern classification. Proposed algorithm is based on block based image processing that size is l6$\times$l6. Experimental results shows good performance of cloudy area detection except blur cloudy areas.

• Korean Journal of Remote Sensing
• /
• v.7 no.1
• /
• pp.69-86
• /
• 1991

An unsupervised region based image segmentation algorithm implemented with a pyramid structure has been developed. Rather than depending on thraditional local splitting and merging of regions with a similarity test of region statistics, the algorithm identifies the homogenous and boundary regions at each level of pyramid, then the global parameters of esch class are estimated and updated with values of the homogenous regions represented at the level of the pyramid using the mixture distribution estimation. The image is then classified through the pyramid structure. Classification results obtained for both simulated and SPOT imagery are presented.

• Korean Journal of Remote Sensing
• /
• v.21 no.1
• /
• pp.83-89
• /
• 2005

This study utilized a spatial region growing segmentation and a classification using fuzzy membership vectors to detect the changes in the images observed at different dates. Consider two co-registered images of the same scene, and one image is supposed to have the class map of the scene at the observation time. The method performs the unsupervised segmentation and the fuzzy classification for the other image, and then detects the changes in the scene by examining the changes in the fuzzy membership vectors of the segmented regions in the classification procedure. The algorithm was evaluated with simulated images and then applied to a real scene of the Korean Peninsula using the KOMPSAT-l EOC images. In the expertments, the proposed method showed a great performance for detecting changes in land-cover.

• Korean Journal of Remote Sensing
• /
• v.19 no.5
• /
• pp.381-392
• /
• 2003

Multi-temporal approaches using sequential data acquired over multiple years are essential for satisfactory discrimination between many land-cover classes whose signatures exhibit seasonal trends. At any particular time, the response of several classes may be indistinguishable. A harmonic model that can represent seasonal variability is characterized by four components: mean level, frequency, phase and amplitude. The trigonometric components of the harmonic function inherently contain temporal information about changes in land-cover characteristics. Using the estimates which are obtained from sequential images through spectral analysis, seasonal periodicity can be incorporates into multi-temporal classification. The Normalized Difference Vegetation Index (NDVI) was computed for one week composites of the Advanced Very High Resolution Radiometer (AVHRR) imagery over the Korean peninsula for 1996 ～ 2000 using a dynamic technique. Land-cover types were then classified both with the estimated harmonic components using an unsupervised classification approach based on a hierarchical clustering algorithm. The results of the classification using the harmonic components show that the new approach is potentially very effective for identifying land-cover types by the analysis of its multi-temporal behavior.

• Journal of Korea Multimedia Society
• /
• v.21 no.7
• /
• pp.779-786
• /
• 2018

In this paper, we are applied a nerve network to allow for the reflection of data learning methods in their overall forms by using cluster data rather than data learning by the stages and then selected a nerve network model and analyzed its variables through learning by the cluster. The CkLR algorithm was proposed to analyze the reaction variables of clustering outcomes through an approach to the initialization of K-means clustering and build a model to assess the prediction rate of clustering and the accuracy rate of prediction in case of new data inputs. The performance evaluation results show that the accuracy rate of test data by the class was over 92%, which was the mean accuracy rate of the entire test data, thus confirming the advantages of a specialized structure found in the proposed learning nerve network by the class.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.11
• /
• pp.852-858
• /
• 1991

An adaptive hierarchical classifier(AHCL) for Korean character recognition using a neural net is designed. This classifier has two neural nets: USACL (Unsupervised Adaptive Classifier) and SACL (Supervised Adaptive Classifier). USACL has the input layer and the output layer. The input layer and the output layer are fully connected. The nodes in the output layer are generated by the unsupervised and nearest neighbor learning rule during learning. SACL has the input layer, the hidden layer and the output layer. The input layer and the hidden layer arefully connected, and the hidden layer and the output layer are partially connected. The nodes in the SACL are generated by the supervised and nearest neighbor learning rule during learning. USACL has pre-attentive effect, which perform partial search instead of full search during SACL classification to enhance processing speed. The input of USACL and SACL is a directional edge feature with a directional receptive field. In order to test the performance of the AHCL, various multi-font printed Hangul characters are used in learning and testing, and its processing its speed and and classification rate are compared with the conventional LVQ(Learning Vector Quantizer) which has the nearest neighbor learning rule.

• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.218-227
• /
• 2022

This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.65-76
• /
• 2004

Today, most documents are electronically produced and their paleography is digitalized by imaging, resulting in a tremendous number of electronic documents in the shape of images. Therefore, to process these document images, many methods of document structure analysis and recognition have already been proposed, including font classification. Accordingly, the current paper proposes a font classification method for document images that uses non-negative matrix factorization (NMF), which is able to learn part-based representations of objects. In the proposed method, spatially total features of font images are automatically extracted using NMF, then the appropriateness of the features specifying each font is investigated. The proposed method is expected to improve the performance of optical character recognition (OCR), document indexing, and retrieval systems, when such systems adopt a font classifier as a preprocessor.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.4 no.2
• /
• pp.36-44
• /
• 2001

The main purpose of this study was to classify forest vegetation effectively using Landsat Thematic Mapper data(June, 1994) in mountainous region. The research area was the Mt. Wolak Experimental Forest of Chungbuk National University, near Chungju and Jecheon city, Chungcheongbuk-do. To classify forest vegetation effectively, Normalized Difference Vegetation Index(NDVI) was used to reduce topographic effects. This NDVI was modified and transformed to the value of 0 to 255, and then the modified values were combined with other Landsat Thematic Mapper bands. To classify forest and land cover types, unsupervised classification method was used. The results of this study are summarized as follows. 1. Combinations of band "3, 5, NDVI" in Landsat Thematic Mapper data showed a good separation with high accuracy. The expected classification accuracy was 95.1% in Landsat Thematic Mapper data. 2. The Land Cover types were classified into six groups : coniferous forest, deciduous forest, mixed forest, paddy and grass, non-forest, and other undetectable areas. As these classified results were compared with the reconnaissance survey and aerial black and white infrared photographs, the overall classification accuracy was 76.5% in Landsat Thematic Mapper data. 3. The portion of non-forest in Mt. Wolak area was 1.9%. The percentages of coniferous, deciduous and mixed forests were 30.9%, 35.7% and 26.4%, respectively. 4. As these classified results were compared with other reference data, the percentages of coniferous, deciduous and mixed forests increased, but the portion of non-forest was exceedingly diminished. These differences are thought to be from the different research method and the different season of received Landsat Thematic Mapper data.

• Korean Journal of Remote Sensing
• /
• v.15 no.3
• /
• pp.217-225
• /
• 1999

Through the ISODATA method of unsupervised classification, the micro-landform of Julpo-Bay tidal flat was classified into mudflat, mixedflat, and sandflat using Landsat TM image. Each showed an apparent differences in its topographical characteristics and grain size composition. Mudflat occupied innermost part of the tidal flat, sandflat located closest to the entrance of the bay and mixed flat in the center is. For example, mudlflats are formed with flat faces and tidal channel. Topographically, mudflat consist of tidal channels and flat intermediate surface. Its average relief of them is about 2 meter. Meanwhile, sandflat comprised very flat landform with well-developed ripple marks of less than 10cm average relief. And Mixed flat stood in between. In addition, Out of 7 bands of Landsat TM images, band 5 and 7 provided the highest power level for discrimination between micro-landforms of the tidal flat. Band 4 showed a clear boundary between the land and tidal flat, and band 3 did its share by showing well a boundary between the sea surface and the tidal flat.