• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.166-171
• /
• 2023

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.87-96
• /
• 2014

In this paper, we propose a directionally adaptive aliasing and noise removal using dictionary learning based on space-frequency analysis. The proposed aliasing and noise removal algorithm consists of two modules; i) aliasing and noise detection using dictionary learning and analysis of frequency characteristics from the combined wavelet-Fourier transform and ii) aliasing removal with suppressing noise based on the directional shrinkage in the detected regions. The proposed method can preserve the high-frequency details because aliasing and noise region is detected. Experimental results show that the proposed algorithm can efficiently reduce aliasing and noise while minimizing losses of high-frequency details and generation of artifacts comparing with the conventional methods. The proposed algorithm is suitable for various applications such as image resampling, super-resolution image, and robot vision.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.205-211
• /
• 2012

By using an adaptive threshold and weight based on the wavelet transform and Haar transform, a novel image enhancement algorithm is proposed. First, a medical image was decomposed with wavelet transform and all high-frequency sub-images were decomposed with Haar transform. Secondly, noise in the frequency domain was reduced by the proposed soft-threshold method. Thirdly, high-frequency coefficients were enhanced by the proposed weight values in different sub-images. Then, the enhanced image was obtained through the inverse Haar transform and wavelet transform. But the pixel range of the enhanced image is narrower than a normal image. Lastly, the image's histogram was stretched by nonlinear histogram equalization. Experiments showed that the proposed method can be not only enhance an image's details but can also preserve its edge features effectively.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.415-425
• /
• 2019

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super-resolution, and compression artifact reduction. By fully exploiting its characteristics, state-of-the-art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN-training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non-negligible degradation of the objective image quality, including peak signal-to-noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression-artifact reduction and super-resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.

• Journal of Fashion Business
• /
• v.8 no.1
• /
• pp.91-106
• /
• 2004

This study focuses on the sportism expressed in the modern fashion. Many factors attribute to the advent of sportism such as rapid development and cultural changes toward sports, increase in leisure time, new fashion materials resulting from new technologies, youth culture and postmodernism. Designers gazing into the future are inspired by the details and functionality of clothing for snow boarding, skiing, rock-climbing and fitness. While the sportswear is the term whith stemmed from the need for functionally in sports, the Sportism is the style inspired by the formative elements, that is, the details, the silhouette, and the colors of the sportswear. New technologies for sports, the powerful influence of youthful culture, and the celebritizations of the sports stars made the sports look more popular. It can be categorized into three aesthetic values, i.e., the functional sportism, the street sportism, and the futuristic sportism. The functional sportism is expressed with the details of function, simplicity, and no useless ornament, the street sportism with fun, androgynous and unisex mode and the image of hip-hop look and traditional look, the futuristic sportism with new high tech fabrics and cyber style. The characters of these are a sence of unisex, sensualness, ostentation, renovation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.19 no.4
• /
• pp.17-27
• /
• 2017

This study analyzes the trends of photo image components and forms of expression in global fashion advertising photos. First, photo image components are classified into seven categories: location (indoor-outdoor), the model's movement, pose, facial expression, gender, race and number of models. The forms of expression are classified into six categories: direct expression, sensual expression, symbolic expression, storytelling expression, dramatic expression, and sexual expression. With the aforementioned classifications, the trends were studied for three years from 2013 to 2015. The analysis result indicates the following: for the details of photo image components, the portion of indoor photos, static poses and conscious facial expressions was over 60% of the total for every season of the 3 years, while there was a slight increase in the number of models and the diversity of races. For the forms of expression, the sensual expression showed the largest portion accounting for over 50% of the total, followed by direct expression and storytelling expression. The findings from this study show that the trends of photo image components and forms of expression in global fashion advertisements are changing. Therefore, domestic companies will need to develop photo image components and forms of expression in line with the changing global fashion advertisement trends.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.156-158
• /
• 2003

Analysis of high-resolution satellite image becomes important for cartography, surveillance, and remote sensing. However, there are lots of problems to be solved for automatic analysis of high-resolution satellite image especially in urban area. The problems are originated from the increased complexity due to the unnecessary details and shadows, and time-varying illuminations. Because of such obstacles, it seems impossible to make automatic analysis. This paper proposes a way of change detection of buildings in urban area by using digital vector map. The proposed way makes the buildings on the vector map parameterized, and searches them in the preprocessed high-resolution image by using generalized Hough transform. The searched building objects are overlaid on the satellite image. The overlaid image can help to detect the change of building rapidly.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.4
• /
• pp.1441-1456
• /
• 2015

The bidimensional empirical mode decomposition (BEMD) algorithm with high adaptability is more suitable to process multiple image fusion than traditional image fusion. However, the advantages of this algorithm are limited by the end effects problem, multiscale integration problem and number difference of intrinsic mode functions in multiple images decomposition. This study proposes the multiscale self-coordination BEMD algorithm to solve this problem. This algorithm outside extending the feather information with the support vector machine which has a high degree of generalization, then it also overcomes the BEMD end effects problem with conventional mirror extension methods of data processing,. The coordination of the extreme value point of the source image helps solve the problem of multiscale information fusion. Results show that the proposed method is better than the wavelet and NSCT method in retaining the characteristics of the source image information and the details of the mutation information inherited from the source image and in significantly improving the signal-to-noise ratio.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1188-1202
• /
• 2012

In this paper, we propose a new multi-scale connected coherence tree algorithm (MCCTA) by improving the connected coherence tree algorithm (CCTA). In contrast to many multi-scale image processing algorithms, MCCTA works on multiple scales space of an image and can adaptively change the parameters to capture the coarse and fine level details. Furthermore, we design a Multi-scale Connected Coherence Tree algorithm plus Spectral graph partitioning (MCCTSGP) by combining MCCTA and Spectral graph partitioning in to a new framework. Specifically, the graph nodes are the regions produced by CCTA and the image pixels, and the weights are the affinities between nodes. Then we run a spectral graph partitioning algorithm to partition on the graph which can consider the information both from pixels and regions to improve the quality of segments for providing image segmentation. The experimental results on Berkeley image database demonstrate the accuracy of our algorithm as compared to existing popular methods.