• Journal of Digital Contents Society
• /
• v.17 no.4
• /
• pp.219-226
• /
• 2016

In our general life, what we recognize information with our human eyes and use it is diverse and massive. But even the current technologies improved by artificial intelligence are exorbitantly deficient comparing to human visual processing ability. Nevertheless, many researchers are trying to get information in everyday life, especially concentrate effort on recognizing information consisted of text. In the fields of recognizing text, to extract the text from the general document is used in some information processing fields, but to extract and recognize the text from real image is deficient too much yet. It is because the real images have many properties like color, size, orientation and something in common. In this paper, we applies an adaptive edge enhanced MSER(Maximally Stable Extremal Regions) to extract the text area in those diverse environments and the scene text, and show that the proposed method is a comparatively nice method with experiments.

• Journal of Digital Contents Society
• /
• v.19 no.9
• /
• pp.1787-1793
• /
• 2018

Shadow is a common phenomenon observed in natural scenes, but it has a negative influence on image analysis such as object recognition, feature detection and scene analysis. Therefore, the process of detecting and removing shadows included in digital images must be considered as a pre-processing process of image analysis. In this paper, the existing methods for acquiring 1D invariant images, one of the feature elements for detecting and removing shadows contained in a single natural image, are described, and a method for obtaining 1D invariant images based on linear regression has been proposed. The proposed method calculates the log of the band-ratio between each channel of the RGB color image, and obtains the grayscale image line by linear regression. The final 1D invariant images were obtained by projecting the log image of the band-ratio onto the estimated grayscale image line. Experimental results show that the proposed method has lower computational complexity than the existing projection method using entropy minimization, and shadow detection and removal based on 1D invariant images are performed effectively.

• The Journal of the Korea Contents Association
• /
• v.16 no.3
• /
• pp.72-80
• /
• 2016

There are various methods of developing latent fingerprints from evidence found at crime scenes. Crime scene investigators should choose appropriate techniques among them depending on the conditions of the evidences. In this study, we compared the three methods using forensic light sources to develop latent fingerprints on multi-colored surfaces. We selected the various samples according to color, shape and texture of the surfaces and developed the latent fingerprints using fluorescent powder, IR(Infrared) photography and Episcopic Co-axial Illumination. Fluorescent powder was highly effective on all surfaces. IR photography was also effective, but only on the not dark surfaces. Episcopic Co-axial Illumination was effective only on the flat and polished surfaces. Although fluorescent powder was fine regardless of the characteristics of the surfaces, IR photography was better on certain surfaces.

• Journal of Broadcast Engineering
• /
• v.16 no.3
• /
• pp.542-551
• /
• 2011

Recently an extension to DMB-AF (Digital Multimedia Broadcasting Application Format) standard was proposed in [1] without sufficient validation for industrial application due to incomplete implementation. The extended DMB-AF can include stereoscopic video and stereoscopic images for interactive service data, i.e., MPEG-4 BIFS data, in addition to the existing 2D video and 2D images for BIFS services. The contents in the extended DMB-AF can provide a temporal mixture of 2D/3D video presentations possibly with or without 2D/3D images for BIFS services. In this paper we developed DMB-AF player software that can play the extended DMB-AF files and authored several test files for its verification. As a result, we introduced a new method for indicating dependencies of 3D media tracks to improve the extension in [1] and validated the extended DMB-AF with the improvement.

• The Journal of the Korea Contents Association
• /
• v.15 no.12
• /
• pp.141-152
• /
• 2015

If we look into genre movie, we can see that almost similar forms are repeated in a movie. Such similar elements are largely divided into three units from a mass of story to a very small camera angle. Those can be explained as Formula, Convention, and Iconography. Among those three, convention means custom and it is a structure or an incident in which one story can be divided into second one. Convention is an incident visualized in individual genre, and a movie director tunes audiences through the incident. The director leads a familiar story but all of a sudden, he transforms the familiar scene to a new story. As a product established from the beginning of movie history, movie convention helps communication between audiences and a director. Audiences familiarize themselves with movie convention through repeated activities of watching movies, and the director utilizes it to provide audiences with familiarity. Director Bong Joon-ho not only tunes audiences through traditional convention but also creates a new art work through transformation of convention. A study is conducted on how he used traditional convention and transformation to get a new idea and to engage in his work through his work .

• The Journal of the Korea Contents Association
• /
• v.8 no.11
• /
• pp.33-40
• /
• 2008

The application of OCR moves from traditional formatted documents to the web document and natural scene images. It is usual that the new applications use not only standard fonts of Myungjo and Godic but also various fonts. The conventional databases which have mainly been constructed with standard fonts have limitations in applying to the new applications. In this paper, we generate 243 image samples for each of 2350 Hangul character classes which differs in font size, quality, and resolution. Additionally each sample was varied according to binarization threshold and rotational transformation. Through this process 2187 samples were generated for each character class. Totally 5,139,450 samples constitutes the printed Hangul character database called the PHD08. In addition, we present the characteristics and recognition performance by an commercial OCR software.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.89-90
• /
• 2014

This paper is the music director Miklos Rozsa participated crime To infer the narrative around two classic movie The study of musical functions. Two films are Double indemnity, 1946 and The Killers, 1948. The main theme was used in the movie Keywords that appear only after analyzing crime scenes film Possible inference of narrative musical expression around the room Examine the law. In the case of a crime movie theme music Indicate the start and development progress, planned steps and proceed only Through the proactive behavior of the system behavior and the final results after the acts To commit a criminal act represents lesson. Music maneu Can be inferred by the narrative of the crime and the crime film To progress in the music scene, and combine with effects The maximum tension over.

• The Journal of the Korea Contents Association
• /
• v.12 no.6
• /
• pp.9-20
• /
• 2012

In computer vision, it is very important to obtain reliable corresponding feature points. However, we know it is not easy to find the corresponding feature points exactly considering by scaling, lighting, viewpoints, etc. Lots of SIFT methods applies the invariant to image scale and rotation and change in illumination, which is due to the feature vector extracted from corners or edges of object. However, SIFT could not find feature points, if edges do not exist in the area when we extract feature points along edges. In this paper, we present a new placement method of marker to improve the performance of SIFT feature detection and matching between different view of an object or scene. The shape of the markers used in the proposed method is formed in a semicircle to detect dominant direction vector by SIFT algorithm depending on direction placement of marker. We applied De Bruijn sequence for the markers direction placement to improve the matching performance. The experimental results show that the proposed method is more accurate and effective comparing to the current method.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.1-9
• /
• 2008

In this paper, we proposed automatic face detection and tracking which is robustness in rotation. To detect a face image in complicated background and various illuminating conditions, we used face skin color detection. we used Harris corner detector for extract facial feature points. After that, we need to track these feature points. In traditional method, Lucas-Kanade feature tracker doesn't delete useless feature points by occlusion in current scene (face rotation or out of camera). So we proposed the estimation function, which delete useless feature points. The method of delete useless feature points is estimation value at each pyramidal level. When the face was occlusion, we deleted these feature points. This can be robustness to face rotation and out of camera. In experimental results, we assess that using estimation function is better than traditional feature tracker.

• The Journal of the Korea Contents Association
• /
• v.19 no.12
• /
• pp.527-534
• /
• 2019

Most of the prints left on the crime scene are latent prints. And, even after the latent prints have been developed, additional enhancement is required and forensic light sources are mainly used. Depending on the applied technique and the light source used, it is difficult to obtain the ideal enhancement effect when the reflected light cannot be cut off well. In this study, we improved the wavelength of the forensic light source by attaching a low-pass filter, resulting in better quality fingerprint images.