• 방송공학회논문지
• /
• 제28권2호
• /
• pp.178-184
• /
• 2023

카메라로 촬영한 야외 일반 영상에서 텍스트 이미지를 찾아내고 그 내용을 인식하는 기술은 로봇 비전, 시각 보조 등의 기반으로 활용될 수 있는 매우 중요한 기술이다. 하지만 텍스트 이미지가 저해상도인 경우에는 텍스트 이미지에 포함된 노이즈나 블러 등의 열화가 더 두드러지기 때문에 텍스트 내용 인식 성능의 하락이 발생하게 된다. 본 논문에서는 일반 영상에서의 저해상도 한글 텍스트에 대한 이미지 초해상화를 통해서 텍스트 인식 정확도를 개선하였다. 트랜스포머에 기반한 모델로 한글 텍스트 이미지 초해상화를 수행 하였으며, 직접 구축한 고해상도-저해상도 한글 텍스트 이미지 데이터셋에 대하여 제안한 초해상화 방법을 적용했을 때 텍스트 인식 성능이 개선되는 것을 확인하였다.

• 디지털융복합연구
• /
• 제10권11호
• /
• pp.371-376
• /
• 2012

본 논문에서는 텍스트 영상에 대한 데이터 천이 최소화를 위한 새로운 데이터 코딩기법과 회로를 제안한다. 제안한 회로는 기존의 Modified LVDS(Low Voltage Differential Signaling)의 문제점인 입력되는 데이터간의 동기와 출력되는 데이터간의 동기 문제를 수정한 개선된 MLVDS 회로와 Text image에 대한 천이 최소화를 위한 추가적인 직렬 데이터 코딩 기법인 TMUX 알고리즘으로 한 클럭에 2비트의 신호를 동시에 전송하여 동작 주파수를 줄일 수 있으며, 전자파 장애와 전력 소비를 해결할 수 있다. 시뮬레이션 결과를 통해서 텍스트 영상 데이터 천이 최소화 향상과 입출력간의 동기문제를 보완되었음을 확인하였다.

• 디자인학연구
• /
• 제14권4호
• /
• pp.199-207
• /
• 2001

극의 공연은 희곡 텍스트를 무대라는 시각적 이미지로 바꾸어 표현하고 전달하는 것이 본질이다. 시각적 이미지는 두대라는 골간을 통해 형성된다. 무대는 시각적 이미지의 모태이다. 다시 말해서 극의 시각적 이미지는 결국 총체적인 공간이미지가 되는 것이다. 본 연구는 극텍스트의 공간이미지를 기호학적 관점에서 해석해 보고, 그것을 통하여 구현되는 공간의 구조와 체계를 파악해 보고자 하는 시도이다. 특히 본고에서 관심을 갖는 것은 이미지 속에 도입된 문자의 기호학이 아니라 텍스트의 언술내용 자체를 도입하는 공간의 이미지텍스트, 극공간의 구조와 의미작용을 파악하는 과정과 내용이며, 결국 이를 통하여 텍스트 그리고 실제 기념적·상징적 공간의 해석방법론으로서 기호학적 측면에서의 '공간 구현의 체계'를 제시하였다.

• Journal of information and communication convergence engineering
• /
• 제19권1호
• /
• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.359-362
• /
• 2002

In this paper, we propose a new feature-based text watermarking for the binary text image. The structure of specific characters from preprocessed text image are modified to embed watermark. Watermark message are embedded and detected by the following method; Hole line disconnect using the connectivity of the character containing a hole, Center line shift using the hole area and Differential encoding using difference of flippable score points. Experimental results show that the proposed method is robust to rotation and scaling distortion.

• 전기학회논문지
• /
• 제58권4호
• /
• pp.806-816
• /
• 2009

Character recognition system consists of four step; text localization, text segmentation, character segmentation, and recognition. The character segmentation is very important and difficult because of noise, illumination, and so on. For high recognition rates of the system, it is necessary to take good performance of character segmentation algorithm. Many algorithms for character segmentation have been developed up to now, and many people have been recently making researches in segmentation of touching or overlapping character. Most of algorithms cannot apply to the text regions of management number marked on the slab in steel image, because the text regions are irregular such as touching character by strong illumination and by trouble of nozzle in marking machine, and loss of character. It is difficult to gain high success rate in various cases. This paper describes a new algorithm of character segmentation to recognize slab management number marked on the slab in the steel image. It is very important that pre-processing step is to convert gray image to binary image without loss of character and touching character. In this binary image, non-touching characters are simply separated by using vertical projection profile. For separating touching characters, after we use combined profile to find candidate points of boundary, decide real character boundary by using method based on recognition. In recognition step, we remove noise of character images, then recognize respective character images. In this paper, the proposed algorithm is effective for character segmentation and recognition of various text regions on the slab in steel image.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.979-982
• /
• 2005

This paper is to be pre-processing that decides the text recognizability and quality contained in natural image. Differentiated with the existing studies, In this paper, it suggests the application of partially unified color models, Coiflet Wavelet and text extraction algorithm that uses the closed curve edge features of LoG (laplacian of gaussian)operator. The text image included in natural image such as signboard has the same hue, saturation and value, and there is a certain thickness as for their feature. Each color element is restructured into closed area by LoG operator, the 2nd differential operator. The text area is contracted by Hough Transform, logical AND-OR operator of each color model and Minimum-Distance classifier. This paper targets natural image into which text area is added regardless of the size and resolution of the image, and it is confirmed to have more excellent performance than other algorithms with many restrictions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1790-1806
• /
• 2016

Digital image encryption is widely used for image data security. JPEG standard compresses image with great performance on reducing file size. Thus, to encrypt an image in JPEG format we should keep the quality of original image and reduced size. This paper proposes a JPEG image encryption scheme based on quantized DC and non-zero AC coefficients inner category scrambling. Instead of coefficient value encryption, the address of coefficient is encrypted to get the address of cipher text. Then 8*8 blocks are shuffled. Chaotic iteration is employed to generate chaotic sequences for address scrambling and block shuffling. Analysis of simulation shows the proposed scheme is resistant to common attacks. Moreover, the proposed method keeps the file size of the encrypted image in an acceptable range compared with the plain text. To enlarge the cipher text possible space and improve the resistance to sophisticated attacks, several additional procedures are further developed. Contrast experiments verify these procedures can refine the proposed scheme and achieve significant improvements.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1437-1446
• /
• 2020

For the last few years, smart devices have begun to occupy an essential place in the life of children, by allowing them to access a variety of language activities and books. Various studies are being conducted on using smart devices for education. Our study extracts images and texts from kids' book with smart devices and matches the extracted images and texts to create new images that are not represented in these books. The proposed system will enable the use of smart devices as educational media for children. A deep convolutional generative adversarial network (DCGAN) is used for generating a new image. Three steps are involved in training DCGAN. Firstly, images with 11 titles and 1,164 images on ImageNet are learned. Secondly, Tesseract, an optical character recognition engine, is used to extract images and text from kids' book and classify the text using a morpheme analyzer. Thirdly, the classified word class is matched with the latent vector of the image. The learned DCGAN creates an image associated with the text.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• 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.