• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.626-643
• /
• 2023

As mobile forensics has emerged as an essential technique, the demand for technology development, education and training is increasing, wherein images are used. Academic societies in South Korea and national institutions in the US and the UK are leading the Mobile Forensic Image development. However, compared with disks, images developed in a mobile environment are few cases and have less active research, causing a waste of time, money, and manpower. Mobile Forensic Images are also difficult to trust owing to insufficient verification processes. Additionally, in South Korea, there are legal issues involving the Telecommunications Business Act and the Act on the Protection and Use of Location Information. Therefore, in this study, we requested a review of a standard model for the development of Mobile Forensic Image from experts and designed an 11-step development model. The steps of the model are as follows: a. setting of design directions, b. scenario design, c. selection of analysis techniques, d. review of legal issues, e. creation of virtual information, f. configuring system settings, g. performing imaging as per scenarios, h. Developing a checklist, i. internal verification, j. external verification, and k. confirmation of validity. Finally, we identified the differences between the mobile and disk environments and discussed the institutional efforts of South Korea. This study will also provide a guideline for the development of professional quality verification and proficiency tests as well as technology and talent-nurturing tools. We propose a method that can be used as a guide to secure pan-national trust in forensic examiners and tools. We expect this study to strengthen the mobile forensics capabilities of forensic examiners and researchers. This research will be used for the verification and evaluation of individuals and institutions, contributing to national security, eventually.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.121-122
• /
• 2002

The main principle of radiation therapy is to deliver optimum dose to tumor to increase tumor cure probability while minimizing dose to critical normal structure to reduce complications. RTP system is required for proper dose plan in radiation therapy treatment. The main goal of this research is to develop dose model for photon, electron, and brachytherapy, and to display dose distribution on patient images with optimum process. The main items developed in this research includes: (l) user requirements and quality control; analysis of user requirement in RTP, networking between RTP and relevant equipment, quality control using phantom for clinical application (2) dose model in RTP; photon, electron, brachytherapy, modifying dose model (3) image processing and 3D visualization; 2D image processing, auto contouring, image reconstruction, 3D visualization (4) object modeling and graphic user interface; development of total software structure, step-by-step planning procedure, window design and user-interface. Our final product show strong capability for routine and advance RTP planning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.80-80
• /
• 2022

Estimation of heading date of paddy rice is laborious and time consuming. Therefore, automatic estimation of heading date of paddy rice is highly essential. In this experiment, deep learning classification models were used to classify two difference categories of rice (vegetative and reproductive stage) based on the panicle initiation of paddy field. Specifically, the dataset includes 444 slanted view images belonging to two categories and was then expanded to include 1,497 images via IMGAUG data augmentation technique. We adopt two transfer learning strategies: (First, used transferring model weights already trained on ImageNet to six classification network models: VGGNet, ResNet, DenseNet, InceptionV3, Xception and MobileNet, Second, fine-tuned some layers of the network according to our dataset). After training the CNN model, we used several evaluation metrics commonly used for classification tasks, including Accuracy, Precision, Recall, and F1-score. In addition, GradCAM was used to generate visual explanations for each image patch. Experimental results showed that the InceptionV3 is the best performing model in terms of the accuracy, average recall, precision, and F1-score. The fine-tuned InceptionV3 model achieved an overall classification accuracy of 0.95 with a high F1-score of 0.95. Our CNN model also represented the change of rice heading date under different date of transplanting. This study demonstrated that image based deep learning model can reliably be used as an automatic monitoring system to detect the heading date of rice crops using CCTV camera.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.559-565
• /
• 2013

Spatial resolution of land covers from remotely sensed images can be increased using super-resolution mapping techniques for soft-classified land cover proportions. A further development of super-resolution mapping technique is downscaling the original remotely sensed image using super-resolution mapping techniques with a forward model. In this paper, the model for increasing spatial resolution of remote sensing multispectral image is tested with real SPOT 5 imagery at 10m spatial resolution for an area in Bac Giang Province, Vietnam in order to evaluate the feasibility of application of this model to the real imagery. The soft-classified land cover proportions obtained using a fuzzy c-means classification are then used as input data for a Hopfield neural network (HNN) to predict the multispectral images at sub-pixel spatial resolution. The 10m SPOT multispectral image was improved to 5m, 3,3m and 2.5m and compared with SPOT Panchromatic image at 2.5m resolution for assessment.Visually, the resulted image is compared with a SPOT 5 panchromatic image acquired at the same time with the multispectral data. The predicted image is apparently sharper than the original coarse spatial resolution image.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.

• Journal of Navigation and Port Research
• /
• v.35 no.4
• /
• pp.317-321
• /
• 2011

In this paper, a foggy-degraded image restoration technique with a physics-based degradation model is proposed for the measurement system. When the degradation model is used for the image restoration, its parameters and a distance from the spreader to the camera have to be previously known. In the proposed image restoration technique, the parameters are estimated from variances and averages of intensities on two foggy-degraded landmark images taken at different distances. Foggy-degraded images can be restored with the estimated parameters and the distance measured by the measurement system. On the basis of the experimental results, the performance of the proposed foggy-degraded image restoration technique was verified.

• 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.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.130-135
• /
• 2024

The Stable diffsuion AI tool is popular among designers because of its flexible and powerful image generation capabilities. However, due to the diversity of its AI models, it needs to spend a lot of time testing different AI models in the face of different design plans, so choosing a suitable general AI model has become a big problem at present. In this paper, by comparing the AI images generated by two different Stable diffsuion models, the advantages and disadvantages of each model are analyzed from the aspects of the matching degree of the AI image and the prompt, the color composition and light composition of the image, and the general AI model that the generated AI image has an aesthetic sense is analyzed, and the designer does not need to take cumbersome steps. A satisfactory AI image can be obtained. The results show that Playground V2.5 model can be used as a general AI model, which has both aesthetic and design sense in various style design requirements. As a result, content designers can focus more on creative content development, and expect more groundbreaking technologies to merge generative AI with content design.