• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.100-104
• /
• 2020

Over the past several years, deep learning has been widely used for feature extraction in image and video for various applications such as object classification and facial recognition. This paper introduces an implantation of embedded Linux system for embossed digits recognition using CNN based deep learning methods. For this purpose, we implemented a coin recognition system based on deep learning with the Keras open source library on Raspberry PI. The performance evaluation has been made with the success rate of coin classification using the images captured with ultra-wide angle camera on Raspberry PI. The simulation result shows 98% of the success rate on average.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.4
• /
• pp.1375-1384
• /
• 2014

Flashover of power transmission line insulators is a major threat to the reliable operation of power system. This paper deals with the flashover prediction of polymeric insulators used in power transmission line applications using the novel condition monitoring technique developed by PD signal time-frequency map and neural network technique. Laboratory experiments on polymeric insulators were carried out as per IEC 60507 under AC voltage, at different humidity and contamination levels using NaCl as a contaminant. Partial discharge signals were acquired using advanced ultra wide band detection system. Salient features from the Time-Frequency map and PRPD pattern at different pollution levels were extracted. The flashover prediction of polymeric insulators was automated using artificial neural network (ANN) with back propagation algorithm (BPA). From the results, it can be speculated that PD signal feature extraction along with back propagation classification is a well suited technique to predict flashover of polymeric insulators.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.645-647
• /
• 2003

In this work a new method for on-line scene segmentation is developed. In remote sensing a scene is represented by the pixel-oriented features. It is possible to reduce data redundancy by an unsupervised segment-feature extraction process, where the segment-features, rather than the pixelfeatures, are used for multispectral scene representation. The algorithm partitions the observation space into exhaustive set of disjoint segments. Then, pixels belonging to each segment are characterized by segment features. Illustrative examples are presented, and the performance of features is investigated. Results show an average compression more than 25, the classification performance is improved for all classes, and the CPU time required for classification is reduced by the same factor.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.02a
• /
• pp.64-72
• /
• 2004

Correction of shadow effects is critical step for image interpretation and feature extraction from aerial imagery. In this paper, an efficient algorithm to correct shadow effects from aerial color imagery is presented. The following steps have been performed to remove the shadow effect. First, the shadow regions are precisely located using the solar position and the height of ground objects derived from LIDAR (Light Detection and Ranging) data. Subsequently, segmentation of context regions is implemented for accurate correction with existing digital map. Next step, to calculate correction factor the comparison between the context region and the same non-shadowed context region is made. Finally, corrected image is generated by correcting the shadow effect. The result presented here helps to accurately extract and interpret geo-spatial information from aerial color imagery

• Annual Conference of KIPS
• /
• 2015.10a
• /
• pp.1345-1347
• /
• 2015

본 논문에서는 응급상황이 신고되는 상황에서 수보자에게 전달되는 신고자의 주변음향신호로부터 신고자의 주변상황을 추정하기 위하여 음향의 주파수적 특성 및 변화특성의 모델링 성능이 뛰어난 Gabor 필터뱅크 기반의 특징벡터 추출 기술 및 분류 성능이 뛰어난 심화신경망을 도입한다. 제안하는 Gabor 필터뱅크 기반의 특징벡터 추출 기법은 비음성 구간 검출기를 통하여 음성/비음성을 구분한 후에 비음성 구간에서 23차의 Mel-filter bank 계수를 추출한 후에 이로부터 Gabor 필터를 이용하여 주변상황 추정을 위한 특징벡터를 추출하고, 이로부터 학습된 심화신경망을 통하여 신고자의 장소적 정보를 추정한다. 제안된 기법은 여러 가지 시나리오 환경에서 평가되었으며, 우수한 분류성능을 보였다.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.65-70
• /
• 2020

CNN's technologies that represent emotional detection include primitive CNN algorithms, deployment normalization, and drop-off. We present the methods and data of the three experiments in this paper. The training database and the test database are set up differently. The first experiment is to extract emotions using Batch Normalization, which complemented the shortcomings of distribution. The second experiment is to extract emotions using Dropout, which is used for rapid computation. The third experiment uses CNN using convolution and maxpooling. All three results show a low detection rate, To supplement these problems, We will develop a deep learning algorithm using feature extraction method specialized in image processing field.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• Journal of Korea Multimedia Society
• /
• v.25 no.7
• /
• pp.903-911
• /
• 2022

A shrimp quality detection model using YOLOv4 deep learning algorithm is designed, which is superior in terms of network architecture, data processing and feature extraction. The shrimp images were taken and data expanded on their own, the LableImage platform was used for data annotation, and the network model was trained under the Darknet framework. Through comparison, the final performance of the model was all higher than other common target detection models, and its detection accuracy reached 93.7% with an average detection time of 47 ms, indicating that the method can effectively detect the quality of shrimp in the production process.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.347-350
• /
• 2011

This paper propose a statistical color model of background extraction base on Hue-Saturation-Value(HSV) color space, instead of the traditional RGB space, and shows that it provides a better use of the color information. HSV color space corresponds closely to the human perception of color and it has revealed more accuracy to distinguish shadows [3] [4]. The key feature of this segmentation method is based on processing hue component of color in HSV color space on image area. The HSV color model is used, its color components are efficiently analyzed and treated separately so that the proposed algorithm can adapt to different environmental illumination condition and shadows. Polar and linear statistical operations are used to calculate the background from the video frames. The experimental results show that the proposed background subtraction method can automatically segment video objects robustly and accurately in various illuminating and shadow environments.