• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.21-28
• /
• 2009

Color polarity classification is a process to determine whether the color of text is bright or dark and it is prerequisite task for text extraction. In this paper we propose a color polarity method to extract text region. Based on the observation for the text and background regions, the proposed method uses the ratios of sizes and standard deviations of bright and dark regions. At first, we employ Otsu's method for binarization for gray scale input region. The two largest segments among the bright and the dark regions are selected and the ratio of their sizes is defined as the first measure for color polarity classification. Again, we select the segments that have the smallest standard deviation of the distance from the center among two groups of regions and evaluate the ratio of their standard deviation as the second measure. We use these two ratio features to determine the text color polarity. The proposed method robustly classify color polarity of the text. which has shown by experimental result for the various font and size.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.764-767
• /
• 2021

While Generative Adversarial Networks (GANs) have seen huge success in image synthesis tasks, synthesizing high-quality images from text descriptions is a challenging problem in computer vision. This paper proposes a method named Text-to-Face Generation Using Multi-Scale Gradients for Conditional Generative Adversarial Networks (T2F-MSGGANs) that combines GANs and a natural language processing model to create human faces has features found in the input text. The proposed method addresses two problems of GANs: model collapse and training instability by investigating how gradients at multiple scales can be used to generate high-resolution images. We show that T2F-MSGGANs converge stably and generate good-quality images.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.545-558
• /
• 2020

The gaze-based input provides feedback to confirm that the typing is correct when the user types the text. Many studies have already demonstrated that feedback can increase the usability of gaze-based inputs. However, because the information of the typed text is revealed through feedback, it can be a target for shoulder-surfing attacks. Appropriate feedback needs to be used to improve security without compromising the usability of the gaze-based input using the original feedback. In this paper, we propose a new gaze-based input method, FFI(Fake Flickering Interface), to resist shoulder-surfing attacks. Through experiments and questionnaires, we evaluated the usability and security of the FFI compared to the gaze-based input using the original feedback.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.36-41
• /
• 2021

Text-based image retrieval is not only cumbersome as it requires the manual input of keywords by the user, but is also limited in the semantic approach of keywords. However, content-based image retrieval enables visual processing by a computer to solve the problems of text retrieval more fundamentally. Vision applications such as extraction and mapping of image characteristics, require the processing of a large amount of data in a mobile environment, rendering efficient power consumption difficult. Hence, an effective image retrieval method on mobile platforms is proposed herein. To provide the visual meaning of keywords to be inserted into images, the efficiency of image retrieval is improved by extracting keywords of exchangeable image file format metadata from images retrieved through a content-based similar image retrieval method and then adding automatic keywords to images captured on mobile devices. Additionally, users can manually add or modify keywords to the image metadata.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.2
• /
• pp.303-310
• /
• 2011

In this study, we employ CPM-GOMS analysis for explaining physical and cognitive processes and for quantitatively predicting when users are typing Korean text messages on mobile phones using both hands. First, we observe the behaviors of 10 subjects, when the subjects enter keypads with both hands. Then, basing upon MHP, we categorize the behaviors into perceptual, cognitive, motor operators, and then we analyze those operators. After that, we use the critical paths to model two task sentences. Also, we used Fitts' law method which was applied many times to predict text entering time on mobile phone to compare with the results of our CPM-GOMS model. We followed Lee's (2008) method that is well suited for text entry task using both hands and calculate total task time for each task sentences. For the sake of comparison between the actual data and the results predicted from our CPM-GOMS model, we empirically tested 10 subjects and concluded that there were no significant differences between the predicted values and the actual data. With the CPM-GOMS model, we can observe the human information processes composed on the physical and cognitive processes. Also we verified that the CPM-GOMS model can be well applied to predict the users' performance when they input text messages on mobile phones using both hands by comparing the predicted total task time with the real execution time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.740-753
• /
• 2023

Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.3
• /
• pp.560-574
• /
• 2011

In this paper, we propose a hybrid method of Machine Learning (ML) algorithm and a rule-based algorithm to implement a lightweight Named Entity (NE) extraction system for Korean SMS text. NE extraction from Korean SMS text is a challenging theme due to the resource limitation on a mobile phone, corruptions in input text, need for extension to include personal information stored in a mobile phone, and sparsity of training data. The proposed hybrid method retaining the advantages of statistical ML and rule-based algorithms provides fully-automated procedures for the combination of ML approaches and their correction rules using a threshold-based soft decision function. The proposed method is applied to Korean SMS texts to extract person's names as well as location names which are key information in personal appointment management system. Our proposed system achieved 80.53% in F-measure in this domain, superior to those of the conventional ML approaches.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1052-1070
• /
• 2017

For the autoencoder (AE) implemented as a construction component, this paper uses the method of greedy layer-by-layer pre-training without supervision to construct the stacked autoencoder (SAE) to extract the abstract features of the original input data, which is regarded as the input of the logistic regression (LR) model, after which the click-through rate (CTR) of the user to the advertisement under the contextual environment can be obtained. These experiments show that, compared with the usual logistic regression model and support vector regression model used in the field of predicting the advertising CTR in the industry, the SAE-LR model has a relatively large promotion in the AUC value. Based on the improvement of accuracy of advertising CTR prediction, the enterprises can accurately understand and have cognition for the needs of their customers, which promotes the multi-path development with high efficiency and low cost under the condition of internet finance.