• 스마트미디어저널
• /
• 제4권3호
• /
• pp.44-49
• /
• 2015

Text line segmentation is a preprocessing step in OCR, which can significantly influence the accuracy of document analysis applications. This paper proposes a novel methodology for the text line segmentation of handwritten documents. First, the average width of the connected components is used to form a 1-D Gaussian kernel and a smoothing operation is then applied to the input binary image. The adaptive binarization of the smoothed image forms the final text lines. In this work, the segmentation method involves two stages: firstly, the large connected components are labelled as a unique text line using text line area mapping. Secondly, the final refinement of the segmentation is performed using the Euclidean distance between the text line and small connected components. The group of uniquely labelled text candidates achieves promising segmentation results. The proposed approach works well on Korean and English language handwritten documents captured using a camera.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.319-323
• /
• 2022

Handwritten text recognition is one of the active research areas nowadays. The progress in this field differs in every language. For example, the progress in Arabic handwritten text recognition is still insignificant and needs more attentions and efforts. One of the most important fields in this is Arabic handwritten manuscript text recognition which focuses in extracting text from historical manuscripts. For eons, ancients used manuscripts to write everything. Nowadays, there are millions of manuscripts all around the world. There are two main challenges in dealing with these manuscripts. The first one is that they are at the risk of damage since they are written in primitive materials, the second challenge is due to the difference in writing styles, hence most people are unable to read these manuscripts easily. Therefore, we discuss in this study different papers that are related to this important research field.

• International Journal of Contents
• /
• 제10권3호
• /
• pp.35-40
• /
• 2014

Text line segmentation is a critical task in handwritten document recognition. In this paper, we propose a novel text-line-segmentation method using baseline estimation and watershed. The baseline-detection algorithm estimates the baseline using Adaptive Head-Tail Connection (AHTC) on the document. Then, the watershed method segments the line region using the baseline-detection result. Finally, the text lines are separated by watershed result and a post-processing algorithm defines the lines more correctly. The scheme successfully segments text lines with 97% accuracy from the handwritten document images in the ICDAR database.

• 스마트미디어저널
• /
• 제5권3호
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.31-34
• /
• 2003

In this paper, we describe a method for separating text lines in handwritten Korean address images. The most remarkable feature of the proposed method is to use a modified projection technique. named a partial projection technique. A projection based text line separation method which projects the whole address image in horizontal direction to find split points for text line separation cannot avoid failing separation in case of images with a little skew or overlap between vertically neighboring text lines. To overcome this problem, we have introduced a partial projection technique which splits an address image into a few partial address images to be equal width and then project them each horizontally. The experiment done with 989 handwritten Korean address images extracted from live mails shows the superiority of the proposed method. The correct text-line separation rate fir the testing images was about 91.5％.

• International Journal of Contents
• /
• 제13권3호
• /
• pp.38-42
• /
• 2017

Documents of the last few decades typically include more than one kind of language, so linguistic classification of each word is essential, especially in terms of English and Korean in handwritten documents. Traditional methods mostly use conventional features of structural or stroke features, but sometimes they fail to identify many characteristics of words because of complexity introduced by handwriting. Therefore, traditional methods lead to a considerably more-complicated task and naturally lead to possibly poor results. In this study, convolutional neural network (CNN) is used for classification of English and Korean handwritten words in text documents. Experimental results reveal that the proposed method works effectively compared to previous methods.

• 대한전자공학회논문지
• /
• 제26권3호
• /
• pp.85-94
• /
• 1989

글자의 간격과 크기가 일정하지 않으므로 전처리 과정에서 각 글자를 분리하기 어려운 필기체 한글 문서로 부터 자모들을 인식하는 방법을 제안한다. 본 방법은 세선화된 필기체 한글문서의 영상 내에 있는 모든 글자들을 스트로크들로 변환시키고, 이들 사이의 배열관계를 나타내는 속성을 추출한 다음, 이들 스트로크와 속성들에 대해 속성문법을 적용하여 자모들을 인식한다.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.59-71
• /
• 2012

Since mobile phones are used as common communication devices, their applications are increasingly important to human's life. Using smart-phones camera to collect daily life environment's information is one of targets for many applications such as text recognition, object recognition or context awareness. Studies have been conducted to provide important information through the recognition of texts, which are artificially or naturally included in images and movies acquired from mobile phones. In this study, a character segmentation method that improves character-recognition accuracy in images obtained from mobile phone cameras is proposed. The proposed method first classifies texts in a given image to printed letters and handwritten letters since segmentation approaches for them are different. For printed letters, rough segmentation process is conducted, then the segmented regions are integrated, deleted, and re-segmented. Segmentation for the handwritten letters is performed after skews are corrected and the characters are classified by integrating them. The experimental result shows our method achieves a successful performance for both printed and handwritten letters as 95.9% and 84.7%, respectively.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.893-913
• /
• 2017

The handwriting based person identification systems use their designer's perceived structural properties of handwriting as features. In this paper, we present a system that uses those structural properties as features that graphologists and expert handwriting analyzers use for determining the writer's personality traits and for making other assessments. The advantage of these features is that their definition is based on sound historical knowledge (i.e., the knowledge discovered by graphologists, psychiatrists, forensic experts, and experts of other domains in analyzing the relationships between handwritten stroke characteristics and the phenomena that imbeds individuality in stroke). Hence, each stroke characteristic reflects a personality trait. We have measured the effectiveness of these features on a subset of handwritten Devnagari and Latin script datasets from the Center for Pattern Analysis and Recognition (CPAR-2012), which were written by 100 people where each person wrote three samples of the Devnagari and Latin text that we have designed for our experiments. The experiment yielded 100% correct identification on the training set. However, we observed an 88% and 89% correct identification rate when we experimented with 200 training samples and 100 test samples on handwritten Devnagari and Latin text. By introducing the majority voting based rejection criteria, the identification accuracy increased to 97% on both script sets.

• 한국산업정보학회논문지
• /
• 제29권3호
• /
• pp.13-22
• /
• 2024

현재 디지털 기기의 확산과 함께 일상에서 손으로 쓰는 글씨의 비중은 점점 줄어들고 있다. 키보드와 터치스크린의 활용도 증가에 따라 한글 필기체의 품질 저하는 어린 학생부터 성인까지 넓은 범위의 한글 문서에서 관찰되고 있다. 그러나 한글 필기체는 여전히 개인적인 고유한 특징을 포함하면서 가독성을 제공하는 많은 문서 작성에 필요하다. 이를 위해 본 논문에서는 손으로 쓴 한글 필기체의 품질을 개선하고, 교정하기 위한 목적의 어플 구현을 목적으로 한다. 제안된 어플은 CRAFT(Character-Region Awareness For Text Detection) 모델을 사용하여 필기체 영역을 검출하고, 딥러닝으로서 VGG-Feature-Extraction 모델을 사용하여 필기체의 특징을 학습한다. 이때 사용자가 작성한 한글 필기체의 음절 단위로 신뢰도를 인식률로 제시하고, 또한, 후보 폰트들중에서 가장 유사한 글자체를 추천하도록 구현한다. 다양한 실험을 통해 제안한 어플은 기존의 상용화된 문자 인식 소프트웨어와 비교할만한 우수한 인식률을 제공함을 확인할 수 있다.