• International Journal of Contents
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2011

In this paper, we propose a method to segment the bottle label in images taken by mobile phones using multi-gradient approaches. In order to segment the label region of interest-object, the saliency map method and Hough Transformation method are first applied to the original images to obtain the candidate region. The saliency map is used to detect the most salient area based on three kinds of features (color, orientation and illumination features). The Hough Transformation is a technique to isolated features of a particular shape within an image. Therefore, we utilize it to find the left and right border of the bottle. Next, we segment the label based on the gradient information obtained from the structure tensor method and edge method. The experimental results have shown that the proposed method is able to accurately segment the labels as the first step of product label recognition system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.5
• /
• pp.343-350
• /
• 2019

Map labels are the most recognizable map elements using the human visual system because they are essentially a natural language. In this study, an experiment was conducted using an eye-tracker to objectively record and analyze the response of subjects regarding visual attention to map labels. A primary building object was identified by analyzing visit counts, average visit duration, fixation counts, and the average fixation duration of a subject's gaze for an area of interest acquired using the eye-tracker. The unmarked rate of map labels in Google map, Naver map, and Daum map was calculated. As a result, this rate exceeded fifty-one percent, with the lowest rate recorded for Google map. It is expected that the results of this study will contribute to an increase in the diversity of research in terms of the spatial cognition approach for map labels, which is more helpful to users than the existing body of work on methods of expression for labels.

• Journal of Korea Multimedia Society
• /
• v.9 no.2
• /
• pp.139-150
• /
• 2006

A schematic map is a special purpose map which is generated to recognize it's objects easily and conveniently via simplifying and highlighting logical geometric information of a map. To manufacture the schematic map with road, label and icon, we must generate simplified route map and replace many geometric objects. Performing a give task, however, there are an amount of overlap areas between geometric objects whenever we process the replacement of geometry objects. Therefore we need replacing geometric objects without overlap. But this work requires much computational resources, because of the high complexity of the original geometry map. We propose the schematic map generation system whose map consists of icons and label. The proposed system has following steps: 1) eliminating kinks that are least relevant to the shape of polygonal curve using DCE(Discrete Curve Evolution) method. 2) making an evenly distributed route using CVT(Centroidal Voronoi Tessellation) and Grid snapping method. Therefore we can keep the structural information of the route map from CVT method. 3) replacing an icon and label information with collision avoidance algorithm. As a result, we can replace the vertices with a uniform distance and guarantee the available spaces for the replacement of icons and labels. We can also minimize the overlap between icons and labels and obtain more schematized map.

• International Journal of Contents
• /
• v.10 no.4
• /
• pp.1-10
• /
• 2014

In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.397-400
• /
• 2011

In this paper, we propose an approach to detect the product label for mobile phone images based on saliency map and the local structure tensor. The object boundary information can be better described by the local structure tensor than other edge detectors, and the saliency map methods can find out the most salient area and shorten the computational time by reducing the size of the orignal image. Therefore, these two methods are considered for our product label detection. The experimental results show an acceptable performance based on our proposed approach.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.3
• /
• pp.481-489
• /
• 2020

Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.23-32
• /
• 2021

Semantic image segmentation technology in the field of computer vision is a technology that classifies an image by dividing it into pixels. This technique is also rapidly improving performance using a machine learning method, and a high possibility of utilizing information in units of pixels is drawing attention. However, this technology has been raised from the early days until recently for 'lack of detailed segmentation' problem. Since this problem was caused by increasing the size of the label map, it was expected that the label map could be improved by using the edge map of the original image with detailed edge information. Therefore, in this paper, we propose a post-processing algorithm that maintains semantic image segmentation based on learning, but modifies the resulting label map based on the edge map of the original image. After applying the algorithm to the existing method, when comparing similar applications before and after, approximately 1.74% pixels and 1.35% IoU (Intersection of Union) were applied, and when analyzing the results, the precise targeting fine segmentation function was improved.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.687-694
• /
• 2022

In this paper, we proposed an autonomous vehicle platform that delivers goods to a designated destination based on the SLAM (Simultaneous Localization and Mapping) map generated indoors by applying the Visual SLAM technology. To generate a SLAM map indoors, a depth camera for SLAM map generation was installed on the top of a small autonomous vehicle platform, and a tracking camera was installed for accurate location estimation in the SLAM map. In addition, a convolutional neural network (CNN) was used to recognize the label of the destination, and the driving algorithm was applied to accurately arrive at the destination. A prototype of an indoor delivery autonomous vehicle was manufactured, and the accuracy of the SLAM map was verified and a destination label recognition experiment was performed through CNN. As a result, the suitability of the autonomous driving vehicle implemented by increasing the label recognition success rate for indoor delivery purposes was verified.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.67-70
• /
• 2022

NLP 분야에서 적극 활용되기 시작한 Transformer 모델을 Vision 분야에서 적용하기 시작하면서 object detection과 segmentation 등 각종 분야에서 기존 CNN 기반 모델의 정체된 성능을 극복하며 향상되고 있다. 또한, label 데이터 없이 이미지들로만 자기지도학습을 한 ViT(Vision Transformer) 모델을 통해 이미지에 포함된 여러 중요한 객체의 영역을 검출하는 saliency map을 추출할 수 있게 되었으며, 이로 인해 ViT의 자기지도학습을 통한 object detection과 semantic segmentation 연구가 활발히 진행되고 있다. 본 논문에서는 ViT 모델 뒤에 classifier를 붙인 모델에 일반 학습한 모델과 자기지도학습의 pretrained weight을 사용해서 전이학습한 모델의 시각화를 통해 각 saliency map들을 비교 분석하였다. 이를 통해, 클래스 분류 학습 기반 전이학습이 transformer의 saliency map에 미치는 영향을 확인할 수 있었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.596-599
• /
• 2003

본 논문에서는 아이콘과 레이블을 가진 도식화된 지도(Schematic map)를 생성차기 위한 아이콘과 레이블의 효과적인 배치 알고리즘을 제안한다. 이 알고리즘은 먼저 지리정보시스템(GIS)의 데이터베이스로부터 원시 정보를 파서로 분석한 후, 지형도 데이터에서 시각화에 필요한 부분만을 추출한 후 이들 선분에 대하여 선분 간략화 알고리즘을 적용하여 기도를 생성한다. 그리고 장식 및 정보의 표기를 목적으로 사용하는 아이콘 및 레이블 정보들의 특징을 반영하여 후보 영역을 생성한다. 마지막으로 생성된 후보영역 내에서 중첩이 발생하기 않으면서 아이콘을 설명하는데 적절한 최적화된 위치의 레이블을 배치하여 이들의 배치 값들 중 최적의 값을 얻은 후 이 최적의 위치에 아이콘과 레이블을 배치하도록 하였다.