• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.167-170
• /
• 2004

We present a novel graph labeling problem called S-edge labeling. The constraint in this labeling is placed on the allowable edge label which is the difference between the labels of endvertices of an edge. Each edge label should be ${ a_n / a_n = 4 a_{n-l}+l,\;a_{n-1}=0}$. We show that every binomial tree is possible S-edge labeling by giving labeling schems to them. The labelings on the binomial trees are applied to their embedings into interconnection networks.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.731-734
• /
• 2000

We present a novel graph labeling problem called Fibonacci edge labeling. The constraint in this labeling is placed on the allowable edge label which is the difference between the labels of endvertices of an edge. Each edge label should be (3m+2)-th Fibonacci numbers. We show that every Fibonacci tree can be labeled Fibonacci edge labeling. The labelings on the Fibonacci trees are applied to their embeddings into Fibonacci Circulants.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.11C
• /
• pp.1171-1177
• /
• 2002

In this paper, we proposed a high speed IP(Internet Protocol) packet forwarding engine of ATM(Asynchronous Transfer Mode) based label edge routers for POS(Packet over SONET) interface. The forwarding engine uses TCAM(Ternary Content Addressable Memory) for high performance lookup processing of the packet received from POS interface. We have accomplished high speed IP packet forwarding in hardware by implementing the functions of high speed IP header Processing and lookup control into FPGA(Field Programmable Gate Array). The proposed forwarding engine has the functions of label edge routers as the lookup controller supports MPLS(Multiprotocol Label Switching) packet processing functionality.

• Proceedings of the IEEK Conference
• /
• 2003.07a
• /
• pp.386-389
• /
• 2003

This paper proposes the architecture of a multiple ring based optical network with single hop between edge nodes using either the concept of circuit switching or multi-wavelength label. The structure of the multi-wavelength label, be shown through the single wavelength-band and the multiple wavelength-band that can reduce number of ring. To avoid the collision of the optical packets at an outward port, we proposed the dynamic allocation scheme of the outward optical packets based on the fiber do]ay lines(FDLs).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.546-549
• /
• 2001

IPOW 기술은 파장이 갖는 특성으로 인하여 여러 가지 제약 사항을 갖고 있어 기존에 개발된 MPLS 기술을 효과적으로 적용하기 위해서는 WDM의 특성을 잘 분석하여 적용하여야 한다. 본 논문에서는 현재 IETF를 중심으로 연구중인 MPLamdaS 개념을 기초로 하여 광 인터넷의 진화를 고려한 구조적인 접근 방법을 연구한다 MPLS 도메인과 MPLambdaS 도메인간에 연동을 고려하여 전자적인 다수의 LSP를 광 LSP로 모으는 레이블 스택 개념을 이용한 Lambda LSP Tunneling 기술을 적용하여 전자적인 MPLS와 광 MPLambdas 간의 연동 방안을 제안하고 이를 지원하는 Edge Optical LSR의 구조를 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.7
• /
• pp.1257-1262
• /
• 2001

In recent years there has been a lot of interest in carrying IP over WDM networks in an efficient manner. The benefits here include larger bandwidth capacities, better network scalability, and more efficient operation. W based approach, termed "lambda-labeling" is presented for direct If over WDM integration. In this paper, we study on architecture approach method consider of optical Internet evolution that based on MPLamdaS conception of IETF. Label stack conception collect electronic LSP of optical LSP. This paper is proposed method of co-operation between MPLS domain and MPLambdaS domain. Additionally, proposed architecture of Edge Optical LSR.tical LSR.

• Proceedings of the IEEK Conference
• /
• 2000.11a
• /
• pp.37-40
• /
• 2000

Multi Protocol Label Switching (MPLS) is a high performance method for forwarding packets (frames) through a network. It enables routers at the edge of a network to apply simple labels to packets (frames). we use MPLS in the core network for internet. MPLS provide high speed switching and traffic engineering in MPLS domain but at the Label Edge Router(LER) there is frequently cell discarding via congestion and buffer management method. It is one of the most important reasons retransmission and congestion. In this paper we propose advanced LER scheme that provide less cell loss rate also efficient network infrastructure.

• International Journal of Contents
• /
• v.6 no.1
• /
• pp.6-11
• /
• 2010

Recently, there has been research to use portable digital camera to recognize objects in natural scene images, including labels or marks on a cylindrical surface. In many cases, text or logo in a label can be distorted by a structural movement of the object on which the label resides. Since the distortion in the label can degrade the performance of object recognition, the label should be rectified or restored from deformations. In this paper, a new method for label detection and restoration in digital images is presented. In the detection phase, the Hough transform is employed to detect two vertical boundaries of the label, and a horizontal edge profile is analyzed to detect upper-side and lower-side boundaries of the label. Then, the biquadratic transformation is used to restore the rectangular shape of the label. The proposed algorithm performs restoration of 3D objects in a 2D space, and it requires neither an auxiliary hardware such as 3D camera to construct 3D models nor a multi-camera to capture objects in different views. Experimental results demonstrate the effectiveness of the proposed method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.841-849
• /
• 2001

The pixel information of the object was obtained sequentially and pixels were clustered to a label by the line labeling method. Feature points were determined by finding the slope for edge pixels after selecting the fixed number of edge pixels. The slope was estimated by the least square method to reduce the detection error. Once a matching point was determined by comparing the feature information of the object and the pattern, the parameters for translation, scaling and rotation were obtained by selecting the longer line of the two which passed through the matching point from left and right sides. Finally, modified Hausdorff Distance has been used to identify the similarity between the object and the given pattern. The multi-label method was developed for recognizing the patterns with more than one label, which performs the modified Hausdorff Distance twice. Experiments have been performed to verify the performance of the proposed algorithm and method for simple target image, complex target image, simple pattern, and complex pattern as well as the partially hidden object. It was proved via experiments that the proposed image matching algorithm for recognizing the object had a good performance of matching.