• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.8-16
• /
• 2024

Communication with the deaf has always been crucial. Deaf and hard-of-hearing persons can now express their thoughts and opinions to teachers through sign language, which has become a universal language and a very effective tool. This helps to improve their education. This facilitates and simplifies the referral procedure between them and the teachers. There are various bodily movements used in sign language, including those of arms, legs, and face. Pure expressiveness, proximity, and shared interests are examples of nonverbal physical communication that is distinct from gestures that convey a particular message. The meanings of gestures vary depending on your social or cultural background and are quite unique. Sign language prediction recognition is a highly popular and Research is ongoing in this area, and the SVM has shown value. Research in a number of fields where SVMs struggle has encouraged the development of numerous applications, such as SVM for enormous data sets, SVM for multi-classification, and SVM for unbalanced data sets.Without a precise diagnosis of the signs, right control measures cannot be applied when they are needed. One of the methods that is frequently utilized for the identification and categorization of sign languages is image processing. African Buffalo Optimization using Support Vector Machine (ABO+SVM) classification technology is used in this work to help identify and categorize peoples' sign languages. Segmentation by K-means clustering is used to first identify the sign region, after which color and texture features are extracted. The accuracy, sensitivity, Precision, specificity, and F1-score of the proposed system African Buffalo Optimization using Support Vector Machine (ABOSVM) are validated against the existing classifiers SVM, CNN, and PSO+ANN.

• Journal of KIISE:Software and Applications
• /
• v.27 no.6
• /
• pp.632-641
• /
• 2000

Conventional character extraction methods extract character regions using methods such as color reduction, region split and merge and texture analysis from the whole image. Because these methods use many heuristic variables and thresholding values derived from a priori knowledge, it is difficult to generalize them algorithmically. In this paper, we propose a method that can extract character regions using a topographical feature extraction method and a point-line-region extension method. The proposed method can also solve the problems of conventional methods by reducing heuristic variables and generalizing thresholding values. We see that character regions can be extracted by generalized variables and thresolding values without using a priori knowledge of character region. Experimental results show that the candidate region extraction rate is 100%, and the character region extraction rate is over 98%.

• Culinary science and hospitality research
• /
• v.24 no.3
• /
• pp.104-112
• /
• 2018

The purpose of this study was to examine the quality characteristics of white pan bread according to the different types of water (tap water (still water), purified water, still water, light water, classical water, and bold water). Pan breads were statistically analyzed using texture profile analysis, fermentation, texture, suitability, image analysis, color, moisture content, and statistical analysis. This result will contribute to the commercialization of pan bread using various kinds of water. Ultimately, we analyzed the quality characteristics of various kinds of water, depending on the carbonic acid content on the dough and the pan bread, and to derive the optimum kinds and ratios of the water to be applied to the pan bread. As a result of the study, the best findings were obtained with water containing carbonic acid content more than the classical water according to overall characteristics, durability (Width of Tail and Integral), foot efficiency, softness, volume and preference check. Therefore, when white pan bread is produced by using water containing a carbonic acid content (5~7.5 mg/L) or more of the classical water, it affects the quality characteristics and a good obtains positive response to from consumers. In this study, the quality characteristics of pan bread based different kinds of water which were not available in the past, and the quality characteristics of pan bread, which can be used as the basic data for future research, were well analyzed.

• Journal of the Korea Computer Graphics Society
• /
• v.12 no.4
• /
• pp.7-15
• /
• 2006

The ultimate objective of painterly rendering is to express an inputted image as if it is hand drawn. The factors to express this painterly effect are thickness of the brush, direction, texture and the establishment of criteria judging if the produced brush will be drawn on to the canvas. In this paper, the algorithm using density of the edges in determining the criteria whether the brush will be drawn onto the canvas is proposed. Density of edges refers to the quantity of edge in the specific area. And uses the method of finding the location of the brush to be drawn as a unit of dynamic grid as well as expressing consistent directional through direction interpolation. Also, the texture is expressed using various textured brushes. Considering density of edges,We can express detailed area and abstract area. And it result in more human effect of oil painting.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.737-744
• /
• 2009

This paper is to study and implement 3D Virtual Face Aesthetic Surgery System which provides more satisfaction by comparing the before-and-after plastic face surgery using 3D face model. For this study, we implemented 3D Face Model Generating System which resembles 2D image of the user based on 3D Korean standard face model and user's 2D pictures. The proposed 3D Virtual Face Aesthetic Surgery System in this paper consists of 3D Face Model Generating System, 3D Skin Texture Mapping System, and Detailed Adjustment System for reflecting the detailed description of face. The proposed system provides more satisfaction to the medical uses and stability in the surgery in compare with other existing systems.

• Journal of Broadcast Engineering
• /
• v.10 no.4 s.29
• /
• pp.632-642
• /
• 2005

This paper presents a new vertex selection scheme for the polygon-based contour approximation. In the proposed method, the entire contour is partitioned into partial segments and they are approximated adaptively with variable accuracy. The approximation accuracy of each segment is controlled based on its relative significance. By computing the relative significance with the texture degradation in the approximation error region, the visual quality enhancement in the reconstructed frames can be achieved under the same amount of the contour data. For this purpose, a decision rule for $d_{max}$ is derived based on inter-region contrasts. In addition, an adaptive vertex selection method using the derived rule is proposed. Experimental results are presented to show the superiority of the proposed method over conventional methods.

• Journal of Advanced Navigation Technology
• /
• v.15 no.1
• /
• pp.140-146
• /
• 2011

In this paper, we propose a fast object classification method based on texture and color information for video surveillance. We take the advantage of local patches by extracting SURF and color histogram from images. SURF gives intensity content information and color information strengthens distinctiveness by providing links to patch content. We achieve the advantages of fast computation of SURF as well as color cues of objects. We use Bag of Word models to generate global descriptors of a region of interest (ROI) or an image using the local features, and Na$\ddot{i}$ve Bayes model for classifying the global descriptor. In this paper, we also investigate discriminative descriptor named Scale Invariant Feature Transform (SIFT). Our experiment result for 4 classes of the objects shows 95.75% of classification rate.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.321-328
• /
• 2017

We have implemented a technique to correct the brightness, saturation, and contrast of an image according to the degree of light, and further compensate the backlight. Backlight compensation can be done automatically or manually. For manual backlight compensation, we have to select the region of interest (ROI). ROI can be selected by connecting the outline of the desired object. We make users select the region delicately with the new magnetic lasso tool. The previous lasso tool has a disadvantage that the start point and the end point must be connected. However, the proposed lasso tool has the advantage of selecting the region of interest without connecting the start point and the end point. We can automatically obtain various results of backlight compensation by adjusting the number of k-means clusters for texture extraction and the threshold value for binarization.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.75-85
• /
• 2013

To acquire depth information using stereo vision, it is required to find correspondence points between stereo image pair. Conventional stereo vision systems usually use two cameras to get disparity data. Therefore, conventional stereo matching methods cannot resolve the tradeoff problem between accuracy and precision with respect to the length of baseline. Besides, belief propagation method, which is being used recently, has a problem that matching performance is dependent on the fixed weight parameter ${\lambda}$. In this paper, we propose a modified belief propagation stereo matching technique based on multi-baseline stereo vision to solve the tradeoff problem. The proposed method calculates EMAD(extended mean of absolute differences) as local evidence. And proposed method decides weight parameter ${\lambda}$ adaptively to local texture information. The proposed method shows higher initial matching performance than conventional methods and reached optimum solution in less iteration. The matching performance is increased about 4.85 dB in PSNR.