• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1323-1331
• /
• 2017

Despite the fact that the copyright has grown into a large-scale business, there are many constant problems especially in image copyright. In this study, we propose an automatic object extraction and classification system for the scanned educational book image by combining document image processing and intelligent information technology like deep learning. First, the proposed technology removes noise component and then performs a visual attention assessment-based region separation. Then we carry out grouping operation based on extracted block areas and categorize each block as a picture or a character area. Finally, the caption area is extracted by searching around the classified picture area. As a result of the performance evaluation, it can be seen an average accuracy of 83% in the extraction of the image and caption area. For only image region detection, up-to 97% of accuracy is verified.

• Korean Journal of Remote Sensing
• /
• v.19 no.2
• /
• pp.170-179
• /
• 2003

In order to classify Land Use/Land Cover using multispectral images, we have to give consequence to defining proper classes and selecting training sample with higher class separability. The process of satellite hyperspectral image which has a lot of bands is difficult and time-consuming. Furthermore, classification result of hyperspectral image with noise is often worse than that of a multispectral image. When selecting training fields according to the signatures in the study area, it is difficult to calculate covariance matrix in some clusters with pixels less than the number of bands. Therefore in this paper we presented an overview of feature extraction methods for classification of Hyperion data and examined effectiveness of feature extraction through the accuracy assesment of classified image. Also we evaluated the classification accuracy of optimal meaningful features by class separation distance, which is also a method for band reduction. As a result, the classification accuracies of feature-extracted image and original image are similar regardless of classifiers. But the number of bands used and computing time were reduced. The classifiers such as MLC, SAM and ECHO were used.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.175-176
• /
• 2019

보안 시스템의 중요성이 늘어남에 따라 열악한 CCTV 영상 환경에서의 범죄 예방 및 검거의 중요성이 늘어나고 있다. 본 논문은 CCTV의 제약 환경에 맞는 데이터 취득, 근적외선 및 가시영역 혼합 영상의 분리 및 복원 방법을 제안한다. 데이터 취득 및 학습시킨 데이터의 성능은 PSNR 방법을 이용해 비교하였고, 저조도 영역의 근적외선과 가시영역의 분리 성능은 34dB 이상이 나왔다. 색 복원은 PSNR 측면에서는 22.5dB가 나왔고, 저조도 영역의 분리 성능과 비교하여 낮은 성능을 기록하다. 색복원의 평가 정도는 원본 영상과 주관적 평가방법을 사용하여 비교하였다.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2006.06a
• /
• pp.307-308
• /
• 2006

Recently, fire extinguishing systems based on water mists have been attracting public attentions in marine engineering. Performance of the fire extinguishing systems is influenced by the size and distribution of spayed water mists. Droplet analyzing method based on image processing technique for measuring droplet size and distribution has been developed. The morphological method based on partial curvature information of pre-processed images was adopted for recognition and separation of overlapped particles. Tested results show that the present method may be reliable for the analysis of the size and distribution of droplets produced by water mist spay flow.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.1
• /
• pp.67-73
• /
• 2007

Recently, fire extinguishing systems based on water mists have been attracting public attentions in marine engineering. Performance of fire extinguishing systems is very strongly influenced by the size and distribution of spayed water mists. Therefore, the present study has developed droplet analyzing method based on image processing. The morphological technique based on partial curvature information of pre-processed images with relaxation method was adopted for recognition and separation of overlapped particles. Tested results showed that the present method may be reliable for the analysis of the size and distribution of droplets in spray flow of fire extinguishing systems based water mists.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.3
• /
• pp.33-40
• /
• 2018

In this paper, we propose a method to effectively split the adjacent baggage that is moving on high speed conveyor of airport. The proposed method calculate the Angle Histogram(AH) that inspects background pixels within radius r based on the center point of the adjacent baggage. After that, the adjacent baggage is segmented by finding split angles at the AH. We also improved the split quality of adjoining baggage by repeatedly correcting the center point to correctly split adjacent baggage of asymmetric size. And the calculation time of AH is reduced about 1/3 by using the symmetry property of the circle. Experiments have shown that 93% of all adjacent baggage images are correctly segmented and the proposed method is effective.

• Journal of the Korean Society of Visualization
• /
• v.10 no.3
• /
• pp.37-41
• /
• 2012

Plate-fin heat exchanger is a kind of compact heat exchangers with a good performance in heat transfer. It is widely used in various engineering fields such as aerospace, chemical and biomedical industries. Quantitative and qualitative flow visualization study were performed using the water model of commercial plate-fin heat exchanger with header angles of $30^{\circ}$. The Reynolds number was 100. Conventional digital particle image velocimetry was used to measure the instantaneous velocity fields of the header region and the flow visualization using dye injection and hydrogen bubble method were applied to capture the qualitative flow characteristics. The results showed the existence of separation flow region at the junction area and the bottom wall of the exit region.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.304-306
• /
• 2007

Methods of Object recognition from camera image are to compare features of color. edge or pattern with model in a general way. SIFT(scale-invariant feature transform) has good performance but that has high complexity of computation. Using simple color histogram has low complexity. but low performance. In this paper we represent a model as a color cooccurrence histogram. and we improve performance using pyramid matching. The color cooccurrence histogram keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color cooccurrence histogram adds geometric information to the normal color histogram. We suggest object recognition by pyramid matching of color cooccurrence histogram.

• Journal of the Korean Society of Visualization
• /
• v.11 no.2
• /
• pp.27-33
• /
• 2013

The inlet flow of centrifugal blower were quantitatively visualized using particle image velocimetry. Because the centrifugal blower system is one of the key parts of EV battery cooling system, the quantitative information of flow field of centrifugal blower is important to design and optimize the cooling system. Two types of inlet parts were used in this study. One is the straight inlet and the other is a bended one. The results showed the flow asymmetry exists in the straight model due to the pressure difference in the blower. In case of the bended one, the separation bubble and the increase of head loss appeared compared with the straight model.

• Journal of Biosystems Engineering
• /
• v.42 no.3
• /
• pp.170-189
• /
• 2017

Purpose: This paper presents Raman chemical imaging technology for inspecting food and agricultural products. Methods The paper puts emphasis on introducing and demonstrating Raman imaging techniques for practical uses in food analysis. Results & Conclusions: The main topics include Raman scattering principles, Raman spectroscopy measurement techniques (e.g., backscattering Raman spectroscopy, transmission Raman spectroscopy, and spatially offset Raman spectroscopy), Raman image acquisition methods (i.e., point-scan, line-scan, and area-scan methods), Raman imaging instruments (e.g., excitation sources, wavelength separation devices, detectors, imaging systems, and calibration methods), and Raman image processing and analysis techniques (e.g., fluorescence correction, mixture analysis, target identification, spatial mapping, and quantitative analysis). Raman chemical imaging applications for food safety and quality evaluation are also reviewed.