• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.3
• /
• pp.464-469
• /
• 2002

In this research, nonvisibility and robustness of image watermarking mixed Key and Logo method were evaluated. The role of the Key was performed by a personal ID of a copyrighter and the logo images were used as the watermark. The standard image of Lena was used for experimental image and binary images of `Park'with size 32${\times}$32 and 64${\times}$64 were used for the watermark, respectively In order to evaluate nonvisibility of the proposed watermarking scheme, PSNR(Peak Signal to Noise Ratio) of the watermarked image was obtained and for robustness reconstructive rates of the reconstructed watermark were obtained from the watermarked image with image transformation of JPEG lossy compression. The experimental results show that nonvisibility is excellent as PSNR of the watermarked image is 93.75dB and the reconstructive rates of the case of 322${\times}$32 watermark was better than the case of the 64${\times}$64 watermark; average 5.9%, 13.9%, 6.5%, and 4.2% in the case of scale-down rates, rotational rates, impulse noise power density, and JPEG lossy compression rates, respectively.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.179-188
• /
• 2008

In this paper, knowledge based text to facial sequence image system for interaction of lecturer and learner in cyber universities is studied. The system is defined by the synthesis of facial sequence image which is synchronized the lip according to the text information based on grammatical characteristic of hangul. For the implementation of the system, the transformation method that the text information is transformed into the phoneme code, the deformation rules of mouse shape which can be changed according to the code of phonemes, and the synthesis method of facial sequence image by using deformation rules of mouse shape are proposed. In the proposed method, all syllables of hangul are represented 10 principal mouse shape and 78 compound mouse shape according to the pronunciation characteristics of the basic consonants and vowels, and the characteristics of the articulation rules, respectively. To synthesize the real time facial sequence image able to realize the PC, the 88 mouth shape stored data base are used without the synthesis of mouse shape in each frame. To verify the validity of the proposed method the various synthesis of facial sequence image transformed from the text information is accomplished, and the system that can be applied the PC is implemented using the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.1
• /
• pp.9-18
• /
• 2018

Recently, the use of image stitching technology has been increasing as the number of contents based on virtual reality increases. Image Stitching is a method for matching multiple images to produce a high resolution image and a wide field of view image. The image stitching is used in various fields beyond the limitation of images generated from one camera. Image Stitching detects feature points and corresponding points to match multiple images, and calculates the homography among images using the RANSAC algorithm. Generally, corresponding points are needed for calculating conversion relation. However, the corresponding points include various types of noise that can be caused by false assumptions or errors about the conversion relationship. This noise is an obstacle to accurately predict the conversion relation. Therefore, RANSAC algorithm is used to construct an accurate conversion relationship from the outliers that interfere with the prediction of the model parameters because matching methods can usually occur incorrect correspondence points. In this paper, we propose an algorithm that extracts more accurate inliers and computes accurate transformation relations by using correspondence point relation information used in RANSAC algorithm. The correspondence point relation information uses distance ratio between corresponding points used in image matching. This paper aims to reduce the processing time while maintaining the same performance as RANSAC.

• Journal of Korean Society for Geospatial Information Science
• /
• v.6 no.2 s.12
• /
• pp.105-117
• /
• 1998

The main object of this study was to prove the effectiveness of satellite Image data for extraction of the pine needle gall midge damaged area in the part of Kangwon-do area, and to present the detailed procedure of a digital image processing for extraction of those damaged area. The effectiveness of extraction of damaged area was improved by using the BRCT(Backwards Radiance Correction Transformation) with DEM for the normalization of topographic effects. The topographic surface analysis of the extracted damaged area revealed that the general damaged area was at south-west and south-east aspect with the slope of 31 to 38 degrees, the temperature of 21 to 25, and 23% to 39% of the highest altitude mountains. The new damaged area in which expanded area was at 27 to 30 degree of slope, the aspect of 46 to 180 degrees, the temperature of $11^{\circ}C\;to\;12^{\circ}C$ and 27% to 39% of the highest altitude mountains. The NDI(New Damaged Index) was developed using the environment factor and simple vegetation index.

• Journal of Information Technology and Architecture
• /
• v.10 no.1
• /
• pp.79-91
• /
• 2013

This paper proposes a systematic methodology that could be used to decide which one shows the best performance among space filling curves (SFCs) in applying lower-dimensional transformations to histogram sequences. A histogram sequence represents a time-series converted from an image by the given SFC. Due to the high-dimensionality nature, histogram sequences are very difficult to be stored and searched in their original form. To solve this problem, we generally use lower-dimensional transformations, which produce lower bounds among high dimensional sequences, but the tightness of those lower-bounds is highly affected by the types of SFC. In this paper, we attack a challenging problem of evaluating which SFC shows the better performance when we apply the lower-dimensional transformation to histogram sequences. For this, we first present a concept of spatial locality, which comes from an intuition of "if the entries are adjacent in a histogram sequence, their corresponding cells should also be adjacent in its original image." We also propose spatial locality preservation metric (slpm in short) that quantitatively evaluates spatial locality and present its formal computation method. We then evaluate five SFCs from the perspective of slpm and verify that this evaluation result concurs with the performance evaluation of lower-dimensional transformations in real image matching. Finally, we perform k-NN (k-nearest neighbors) search based on lower-dimensional transformations and validate accuracy of the proposed slpm by providing that the Hilbert-order with the highest slpm also shows the best performance in k-NN search.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3D
• /
• pp.419-431
• /
• 2009

The core of this study is finding out the efficient band selection or extraction method discovering the optimal spectral bands when applying canonical correlation classifier (CCC) to hyperspectral data. The optimal efficient bands grounded on each separability decision technique are selected using Multispec$^{(C)}$ software developed by Purdue university of USA. Total 6 separability decision techniques are used, which are Divergence, Transformed Divergence, Bhattacharyya, Mean Bhattacharyya, Covariance Bhattacharyya, Noncovariance Bhattacharyya. For feature extraction, PCA transformation and MNF transformation are accomplished by ERDAS Imagine and ENVI software. For the comparison and assessment on the effect of feature selection and feature extraction, land cover classification is performed by CCC. The overall accuracy of CCC using the firstly selected 60 bands is 71.8%, the highest classification accuracy acquired by CCC is 79.0% as the case that executes CCC after appling Noncovariance Bhattacharyya. In conclusion, as a matter of fact, only Noncovariance Bhattacharyya separability decision method was valuable as feature selection algorithm for hyperspectral image classification depended on CCC. The lassification accuracy using other feature selection and extraction algorithms except Divergence rather declined in CCC.

• The Research Journal of the Costume Culture
• /
• v.22 no.1
• /
• pp.167-182
• /
• 2014

This study researched the symbolic meaning of the costume colors in the independent film . The purpose of the study is to shed light on the relation between a film and the clothing color by exploring the symbolic meaning of costume colors as based on place images and as reflected in characters' internal psychological states and situations. The conclusions of this study are as follows. First, the colors primarily presented were neutral shades of black and white or dark, almost-black tones, representing the negative narrative structure and depicting the image of a human being. Second, a series of bright blue shades were presented to reflect the positive narrative structure of a human being returning successfully to reality. Third, the application of color, involving both the psychological aspect as well as the symbolism of color, was effectively delivered to the audience. Fourth, the emphasis on color in the smallest details of costumes was analyzed, and it was found that symbolic color effectively communicated the whole image of transformation as the story progressed, clearly delivered delicate emotional messages, and contained symbolism relating to particular places and situations.

• Journal of the Korean Home Economics Association
• /
• v.40 no.11
• /
• pp.157-170
• /
• 2002

This study is an attempt to establish an aesthetic and fashion sense of the heroine's image and fashion according to the social environment which is related to fashion transformation. Also, this study modem society's need for specific social occupational roles through fashion and clothing in cinema. first, individual people are estimating their social position and ability by his/her fashion style. Modem fashion styles are changing into various, complicated, gorgeous and attractive styles; however, the needs of professional women's clothing styles are fairly conservative. Second, classical, closed, and unobtrusive fashion styles are appearing in modem cinema's clothing depending on professional women's expertise in fashion styles. Third, changes of styles are varied by their colors and clothing design. Colors had not changed very much during the last 30 years; however, in the 1980's, white and grey colors, in the 1990's black and achromatic colors, and in the beginning of this century dark green and brown and also diverse colors have been used. But the brightness is so light and expressed by a quiet and cold style. Furthermore, the inner images are judged by their forms which is determined by how people choose their clothing styles. Consequently, women's clothing styles easily appear as a result of their preconceived ideas formed by their professional knowledge and ability.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.6
• /
• pp.621-626
• /
• 2010

For geometric correction of high-resolution images, the authors matched corresponding objects between a large-scale digital map and a QuickBird image to obtain the coefficients of the first order polynomial. Proximity corrections were performed, using the Boolean operation, to perform automated matching accurately. The modified iterative closest point (ICP) algorithm was used between the point data of the surface linear objects and the point data of the edge objects of the image to determine accurate transformation coefficients. As a result of the automated geometric correction for the study site, an accuracy of 1.207 root mean square error (RMSE) per pixel was obtained.