• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.6
• /
• pp.486-491
• /
• 2013

This paper proposes a fast and efficient Haar-like feature selection algorithm for training classifier used in object detection. Many features selected by Haar-like feature selection algorithm and existing AdaBoost algorithm are either similar in shape or overlapping due to considering only feature's error rate. The proposed algorithm calculates similarity of features by their shape and distance between features. Fast and efficient feature selection is made possible by removing selected features and features with high similarity from feature set. FERET face database is used to compare performance of classifiers trained by previous algorithm and proposed algorithm. Experimental results show improved performance comparing classifier trained by proposed method to classifier trained by previous method. When classifier is trained to show same performance, proposed method shows 20% reduction of features used in classification.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.988-999
• /
• 2021

AOI (Automatic Optical Inspection) of PCB (Printed Circuit Board) is a very important step to guarantee the product performance. The process of registering components called teaching mode is first perform, and AOI is then carried out in a testing mode that checks defects, such as recognizing and comparing the component mounted on the PCB to the stored components. Since most of registration of the components on the PCB is done manually, it takes a lot of time and there are many problems caused by mistakes or misjudgement. In this paper, A components classifier is proposed using YOLO (You Only Look Once) v2's object detection model that can automatically register components in teaching modes to reduce dramatically time and mistakes. The network of YOLO is modified to classify small objects, and the number of anchor boxes was increased from 9 to 15 to classify various types and sizes. Experimental results show that the proposed method has a good performance with 99.86% accuracy.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1302-1312
• /
• 2015

Recent research has been devoted and focused on detecting pedestrian and vehicle in intelligent vehicles except for the vulnerable road user(VRUS). In this paper suggest a new projection method which has robustness for rotation invariant and reducing dimensionality for each cell from original image to detect two-wheeler. We applied new weighting values which are calculated by maximum curvature containing very important object shape features and uniform local binary pattern to remove the noise. This paper considered the Adaboost algorithm to make a strong classification from weak classification. Experiment results show that the new approach gives higher detection accuracy than of the conventional method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.145-153
• /
• 2009

Trajectory data are ubiquitous in the real world. Recent progress on satellite, sensor, RFID, video, and wireless technologies has made it possible to systematically track object movements and collect huge amounts of trajectory data. Accordingly, there is an ever-increasing interest in performing data analysis over trajectory data. In this paper, we develop a data mining tool for massive trajectory data. This mining tool supports three operations, clustering, classification, and outlier detection, which are the most widely used ones. Trajectory clustering discovers common movement patterns, trajectory classification predicts the class labels of moving objects based on their trajectories, and trajectory outlier detection finds trajectories that are grossly different from or inconsistent with the remaining set of trajectories. The primary advantage of the mining tool is to take advantage of the information of partial trajectories in the process of data mining. The effectiveness of the mining tool is shown using various real trajectory data sets. We believe that we have provided practical software for trajectory data mining which can be used in many real applications.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.5
• /
• pp.373-386
• /
• 2024

The aim of this study is to establish a system for the early detection of high-density harmful marine organisms. Considering its accuracy and processing speed, YOLOv8m (You Only Look Once version 8 medium) is selected as a suitable model for real-time underwater image-based object detection. Applying the detection algorithm allows one to detect numerous fish and the occasional occurrence of jellyfish. The average precision, recall rate, and mAP (mean Average Precision) of the trained model are 0.931, 0.881, and 0.948 for the validation data, respectively. Also, the mAP for each class is 0.97 for fish, 0.97 for jellyfish and 0.91 for salpa, all of which exceed 0.9 (90%) for classes demonstrating the excellent performance of the model. A scientific sonar system is used to address the object-detection range and validate the detection results. Additionally, integrating and grid averaging the echo strength allows the detection results to be smoothed in space and time. Mean-volume back-scattering strength values are obtained to reflect the detection variability within the analysis domain. Furthermore, an underwater image-based object (marine lives) detection algorithm, an image-correction technique based on the underwater environmental conditions (including nights), and quantified detection results based on a scientific sonar system are presented, which demonstrate the utility of the detection system in various applications.

• 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.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.61-66
• /
• 2022

Object classification is one of the main fields in neural networks and has attracted the interest of many researchers. Although there have been vast advancements in this area, still there are many challenges that are faced even in the current era due to its inefficiency in handling large data, linguistic and dimensional complexities. Powerful hardware and software approaches in Neural Networks such as Deep Neural Networks present efficient mechanisms and contribute a lot to the field of object recognition as well as to handle time series classification. Due to the high rate of accuracy in terms of prediction rate, a neural network is often preferred in applications that require identification, segmentation, and detection based on features. Neural networks self-learning ability has revolutionized computing power and has its application in numerous fields such as powering unmanned self-driving vehicles, speech recognition, etc. In this paper, the experiment is conducted to implement a neural approach to identify numbers in different formats without human intervention. Measures are taken to improve the efficiency of the machines to classify and identify numbers. Experimental results show the importance of having training sets to achieve better recognition accuracy.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.6
• /
• pp.504-511
• /
• 2013

This paper proposes improved detection schemes for concealed micro-electronic devices using clustering and classification of radio frequency harmonics in order to protect intellectual property rights. In general, if a radio wave with a specific fundamental frequency is propagated from the transmitter of a classifier to a concealed object, the second and the third harmonics will be returned as the radio wave is reflected. Using this principle, we exploit the fuzzy c-means clustering and the ${\kappa}$-nearest neighbor classification for detecting diverse concealed objects. Simulation results indicate that the proposed scheme can detect electronic devices and metal devices in various learning environments by efficient classification. Thus, the proposed schemes can be utilized as an effective detection method for concealed micro-electronic device to protect intellectual property rights.

• Korean Journal of Remote Sensing
• /
• v.27 no.3
• /
• pp.379-388
• /
• 2011

At present, GEOBIA (Geographic Object-based Image Analysis), heir of OBIA (Object-based Image Analysis), is regarded as an important methodology by object-oriented paradigm for remote sensing, dealing with geo-objects related to image segmentation and classification in the different view point of pixel-based processing. This also helps to directly link to GIS applications. Thus, GEOBIA software is on the booming. The main theme of this study is to look into the applicability of geo-spatial processing open source to GEOBIA. However, there is no few fully featured open source for GEOBIA which needs complicated schemes and algorithms, till It was carried out to implement a preliminary system for GEOBIA running an integrated and user-oriented environment. This work was performed by using various open sources such as OTB or PostgreSQL/PostGIS. Some points are different from the widely-used proprietary GEOBIA software. In this system, geo-objects are not file-based ones, but tightly linked with GIS layers in spatial database management system. The mean shift algorithm with parameters associated with spatial similarities or homogeneities is used for image segmentation. For classification process in this work, tree-based model of hierarchical network composing parent and child nodes is implemented by attribute join in the semi-automatic mode, unlike traditional image-based classification. Of course, this integrated GEOBIA system is on the progressing stage, and further works are necessary. It is expected that this approach helps to develop and to extend new applications such as urban mapping or change detection linked to GIS data sets using GEOBIA.