• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1170-1178
• /
• 2021

This paper proposed a versatile algorithm based on a dual-tree complex wavelet transform for intensifying the visual aspect of medical images. First, the decomposition of the input image into a high sub-band and low-sub-band image is done. Further, to improve the resolution of the resulting image, the high sub-band image is interpolated using Lanczos interpolation. Also, contrast enhancement is performed by singular value decomposition (SVD). Finally, the image reconstruction is achieved by using an inverse wavelet transform. Then, the Gaussian filter will improve the visual quality of the image. We have collected images from the hospital and the internet for quantitative and qualitative analysis. These images act as a reference image for comparing the effectiveness of the proposed algorithm with the existing state-of-the-art. We have divided the proposed algorithm into several stages: preprocessing, contrast enhancement, resolution enhancement, and visual quality enhancement. Both analyses show the proposed algorithm's effectiveness compared to existing methods.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.56-63
• /
• 2024

Despite the rapid strides in content-based image retrieval, a notable disparity persists between the visual features of images and the semantic features discerned by humans. Hence, image retrieval based on the association of semantic similarities recognized by humans with visual similarities is a difficult task for most image-retrieval systems. Our study endeavors to bridge this gap by refining image semantics, aligning them more closely with human perception. Deep learning techniques are used to semantically classify images and retrieve those that are semantically similar to personalized images. Moreover, we introduce a keyword-based image retrieval, enabling automatic labeling of images in mobile environments. The proposed approach can improve the performance of a mobile device with limited resources and bandwidth by performing retrieval based on the visual features and keywords of the image on the mobile device.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.2
• /
• pp.88-92
• /
• 2011

This paper looks at the development of the visual system of robots, and the development of image processing algorism to measure the size of an object and the distance from robot to an object for the visual system. Robots usually get the visual systems with a camera for measuring the size of an object and the distance to an object. The visual systems are accurately impossible the size and distance in case of that the locations of the systems is changed and the objects are not on the ground. Thus, in this paper, we developed robot's visual system to measure the size of an object and the distance to an object using two cameras and two-degree robot mechanism. And, we developed the image processing algorism to measure the size of an object and the distance from robot to an object for the visual system, and finally, carried out the characteristics test of the developed visual system. As a result, it is thought that the developed system could accurately measure the size of an object and the distance to an object.

• Journal of Fashion Business
• /
• v.12 no.4
• /
• pp.143-157
• /
• 2008

The purpose of this study was to evaluate the visual effects and images according to changes in the silhouettes and length of miniskirt. The silhouettes of the miniskirt were classified into two different categories according to side line, H-line and A-line. We altered the length of the miniskirt in five categories with changes in 25cm, 27.5cm, 30cm, 32.5cm, and 35cm. For the visual evaluation, 10 stimuli were placed in mannequins, and were estimated by the experts in the fashion design. For the visual evaluation according to changes in the silhouettes and length of the miniskirt, we used 13 pairs of items to find the visual effects, and 23 pairs of adjectives to measure the visual images. The stimuli and adjectives were randomly given to the evaluators and were evaluated by the 7-Point Likert Type Scale. The data have analyzed by frequency, t-test, factor analysis, anova, scheffe's test and the MCA method. According to the factor analysis of the visual effects of the miniskirt, the result was classified into 3 factors: the thickness of the lower body, the length of the lower body, and the shape of the lower body. According to factor analysis of the visual image of the miniskirt, the result was classified into 4 factor: personality, attraction, elegance, and activity. The silhouettes of miniskirt had more positive visual effects and images in A-Line than in H-Line. Among the visual effects of miniskirts, the length affected the thickness and length of the lower body more than the silhouette did and, the silhouette had more effects on the shape of the lower body than the length did. And shorter the skirts, stronger the image of personality. However, 32.5cm and 35cm miniskirts are estimated to be more attractive than excessively short skirts. There are many differences in the image of personality and activity according to the changes in the length of miniskirts.

• Archives of design research
• /
• v.16 no.4
• /
• pp.207-214
• /
• 2003

The reason why rhetoric is important to a moving image is that a moving image communicates through non-verbal communication language. At first, rhetoric in a moving image functions to be persuasive in the story of a moving image. Second, rhetoric works to enhance an aesthetic value for a moving image. Thus we feel good when we are watching a moving image with well embeded rhetoric. On the other hand, we see extened rhetoric to enhance an imaginary because of a hollywood movie with visual effect and a digital movie. Visual images now formed using more signigier compared to signified for signification. Also we see that every signifier structured metaphorically to function as a sign. In this paper, 1 am going to explain the principles of rhetoric applied to a moving image so that we can better understand a signification on visual image.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.12
• /
• pp.2498-2504
• /
• 2009

The fundamental research for the mobile robot navigation using the numerical optimization method is presented. We propose an image-based visual servo navigation algorithm for a wheeled mobile robot utilizing a ceiling mounted camera. For the image-based visual servoing, we define the composite image Jacobian which represents the relationship between the speed of wheels of a mobile robot and the robot's overall speed in the image plane. The rotational speed of wheels of a mobile robot can be directly related to the overall speed of a mobile robot in the image plane using the composite image Jacobian. We define the mobile robot navigation problem as an unconstrained optimization problem to minimize the cost function with the image error between the goal position and the position of a mobile robot. In order to avoid the obstacle, the modified cost function is proposed which is composed of the image error between the position of a mobile robot and the goal position and the distance between the position of a mobile robot and the position of the obstacle. The performance was evaluated using the simulation.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.18 no.5
• /
• pp.646-660
• /
• 1994

The purpose of this study was to investigate the difference of the visual evaluation about Clothing form and the surface image of detail. This study consists of pre-experiment for selecting the method of expression among detail which shows difference of the image and main experiment for identifying the clothing image as clothing form and the suface image of detial. Main experiment is made of factorial design for three variables-clothing form (H-line, A-line, V-line, X-line), detail (frill, tape), direction (width, length). Questionaire consists of 24 semantic differential scale expressing clothing form and detail. The subjects were 100 female students majoring in clothing and textile.7he data were analyzed by Frequencey, Factor analysis, Anova, scheffe's test and MCA method. The major findings were; 1) The image of clothing form and the surface image of detail were composed of 5 factors; attractiveness, prettiness, attention, modern, young. 2) For the visual evaluation of clothing form as the surface image of detail, there were significant differences in prettiness and attention factors. For the pretty and attentive image, we should express by the image of frill. 3) For the visual evaluation of the image of detail as clothing forms variation, there were significant difference in prettiness by A-line and X-line. 4) For the effect of clothing form and the surface image of detail, main effect was significant in attractiveness, prettiness, attention, modern factor. For the pretty image of clothing, it will be expressed by the image of frill and A-line, X-line. For the attentive image of clothing, it will be expressed by the image of frill and V-line. For the modern image of clothing, it will be expressed by the image of tape and V-line.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2862-2878
• /
• 2020

Data Security is the most challenging area in Internet communication, where most of the secret sharing schemes are proposed for binary images. But still it lacks in providing security for data communication, especially in image transmission. Traditional visual cryptography scheme generate meaningless diwies and the reconstruction phase leads to quality degradation over the secret image. In this work, an intelligent two dimensional secret share construction scheme is proposed. A secret image is expanded into n diwies with the choice of scheme selection. By Stacking all the qualified diwies to revert the secret image without content loss and less than s^* - 1 shares could not reveal any information about the secret image. The experimental results emphasize that the proposed secret share scheme is highly secured for image transmission.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.21 no.8
• /
• pp.1297-1306
• /
• 1997

The purpose of this study was to investigate the difference of visual evaluation about combination of contrary clothing image, Elegance-Casual, Ethnic-Modern. The data were collected using 23 semantic differential hi-polar scale questionnaires from 50 female students majoring in clothing and textile and analyzed by Factor analysis, ANOVA, Discriminant analysis and MDS. The results obtained were summarized as follows; 1. As a result of factor analysis, 4 factors -Attractiveness, Casualness, Moderateness, Modernness-were found out as constructing factors of contrary clothing image. 2. For the visual evaluation of contrary clothing image combined with top and bottom, there were significant differences in all factors. 3. As a result of discriminant analysis, discrimination among images was more closely related to renovated image by combination of contrary clothing image. 4. As a result of MDS, evaluative dimensions of contrary clothing image were identified, and relationship between clothing images and special qualities of design was shown on positioning map.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.67-77
• /
• 2020

Image captioning has received significant interest in recent years, and notable results have been achieved. Most previous approaches have focused on generating visual descriptions from images, whereas a few approaches have exploited visual descriptions for image classification. This study demonstrates that a good performance can be achieved for both description generation and image classification through an end-to-end joint learning approach with a loss function, which encourages each task to reach a consensus. When given images and visual descriptions, the proposed model learns a multimodal intermediate embedding, which can represent both the textual and visual characteristics of an object. The performance can be improved for both tasks by sharing the multimodal embedding. Through a novel loss function based on class activation mapping, which localizes the discriminative image region of a model, we achieve a higher score when the captioning and classification model reaches a consensus on the key parts of the object. Using the proposed model, we established a substantially improved performance for each task on the UCSD Birds and Oxford Flowers datasets.