• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.826-836
• /
• 2016

Mastering a musical instrument for an unskilled beginning learner is not an easy task. It requires playing every note correctly and maintaining the tempo accurately. Any music comes in two forms, a music score and it rendition into an audio music. The proposed method of assisting beginning music players in both aspects employs two popular pattern recognition methods for audio-visual analysis; they are support vector machine (SVM) for music score recognition and hidden Markov model (HMM) for audio music performance tracking. With proper synchronization of the two results, the proposed music learning assistant system can give useful feedback to self-training beginners.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1092-1099
• /
• 2017

This paper proposes a novel way of vehicle detection and classification based on image features. There are two main processes in the proposed system, which are database construction and vehicle classification processes. In the database construction, there is a tight censorship for choosing appropriate images of the training set under the rigorous standard. These images are trained using Haar features for vehicle detection and histogram of oriented gradients extraction for vehicle classification based on the support vector machine. Additionally, in the vehicle detection and classification processes, the region of interest is reset using a number plate to reduce complexity. In the experimental results, the proposed system had the accuracy of 0.9776 and the $F_1$ score of 0.9327 for vehicle classification.

• Journal of Multimedia Information System
• /
• v.1 no.2
• /
• pp.119-126
• /
• 2014

We propose a bicycle detection system riding on people based on modified projected local binary pattern(PLBP) for vision based intelligent vehicles. Projection method has robustness for rotation invariant and reducing dimensionality for original image. The features of Local binary pattern(LBP) are fast to compute and simple to implement for object recognition and texture classification area. Moreover, We use uniform pattern to remove the noise. This paper suggests that modified LBP method and projection vector having different weighting values according to the local shape and area in the image. Also our system maintains the simplicity of evaluation of traditional formulation while being more discriminative. Our experimental results show that a bicycle and motorcycle riding on people detection system based on proposed PLBP features achieve higher detection accuracy rate than traditional features.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.374-375
• /
• 2011

보행자 탐지를 위해 많은 알고리즘들이 제안되었고 그 중 HOG 알고리즘은 가장 좋은 성능을 보이는 알고리즘으로 알려져 있다. 하지만 HOG(Histogram of Oriented Gradients) 알고리즘은 연산량이 많아 계산 속도가 느려 실시간 시스템에 적용하기는 힘들다. 본 논문은 HOG 알고리즘으로 얻어진 특징 벡터를 이용해 보행자를 인식하는 방법의 속도 개선에 대하여 연구하였다. 기존 HOG 알고리즘에서 계산량이 많은 곳이 어느 부분인지 분석하고, 그 중 기울기와 방향을 계산하는 부분의 근사화를 통해 계산 속도를 높이는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.383-386
• /
• 2021

본 논문에서는 주행 중 운전자의 운전작업 중 전방 주의집중 여부를 모니터링하는 연구 방안들을 조사하고 최신 연구 동향을 분석하였으며, 자율주행자동차에서 운전자의 주의집중이 필요한 상황들에 대해 사전에 안내하는 방안을 제시하고자 한다. 연구 동향을 조사한 결과 대부분의 방법은 시각 자료 기반과 생체신호 기반으로 진행하고 있다. 연구분석 결과를 바탕으로 두 가지 방법 중 본 연구에서는 시각 자료 기반 연구 방법에 초점을 맞추어, 자동차에 설치된 카메라를 통해 수집된 영상에서 운전자의 운전작업 주의 여부를 식별하는 방법들에 대해서 분석을 진행하였다. 주행 영상에서 HoG(histogram of oriented gradients) 특징과 딥러닝 학습을 통해 운전자의 주의집중 여부를 모니터링하는 방법이 효과적임을 제시한다. 본 연구조사를 통해 분석된 운전자 모니터링 방안들을 자율주행 자동차에 적용하기 위한 운전자 주의 태만 경고시스템에 적용이 가능함을 제시한다.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1021-1028
• /
• 2013

Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.316-324
• /
• 2012

In this paper, a novel descreening method using HOG(histogram of gradient)-based adaptive smoothing filter is proposed. Conventional edge-oriented smoothing methods does not provide enough smoothing to the halftone image due to the edge-like characteristic of the halftone noise. Moreover, clustered-dot halftoning method, which is commonly used in printing tends to create Moire pattern because of the intereference in color channels. Therefore, the proposed method uses HOG to distinguish edges and the amount of smoothing to be performed on the halftone image is then calculated according to the magnitude of the HOG in the edge and edge normal orientation. The proposed method was tested on various scanned halftone materials, and the results show that it effectively removes halftone noises as well as Moire pattern while preserving image details.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3712-3729
• /
• 2020

Smoke detection is helpful for early fire detection. With its large coverage area and low cost, vision-based smoke detection technology is the main research direction of outdoor smoke detection. We propose a two-stage smoke detection method combined with block Deep Normalization and Convolutional Neural Network (DNCNN) and visual change image. In the first stage, each suspected smoke region is detected from each frame of the images by using block DNCNN. According to the physical characteristics of smoke diffusion, a concept of visual change image is put forward in this paper, which is constructed by the video motion change state of the suspected smoke regions, and can describe the physical diffusion characteristics of smoke in the time and space domains. In the second stage, the Support Vector Machine (SVM) classifier is used to classify the Histogram of Oriented Gradients (HOG) features of visual change images of the suspected smoke regions, in this way to reduce the false alarm caused by the smoke-like objects such as cloud and fog. Simulation experiments are carried out on two public datasets of smoke. Results show that the accuracy and recall rate of smoke detection are high, and the false alarm rate is much lower than that of other comparison methods.