Papers - THI THI ZIN
-
A study on detection of abnormal behavior by a surveillance camera image Reviewed
Hiroaki Tsushita, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 284 - 291 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
At present, an enormous amount of accidents and terrorisms has been occurred all over the world not only Japan. Due to the spread of security cameras, the number of occurrences of theft and robbery incidents has been decreasing more and more. Nonetheless, the arrest rate has not improved so much and improvement and rising of the arrest rate are required. The objective of this paper is detection of snatching that involves an event between two persons, and we made an effort to detect snatching in various kinds of situations by using some video scenarios. This video scenarios include the scene of snatching with a bicycle and the scene of non-snatching with normal pedestrian passing. Our proposed methods consist of several steps: background subtraction, pedestrian tracking, feature extraction, and snatch theft detection. We focused on the feature extraction process in details and used weighted decision fusion system based on these parameter, area feature, motion feature, and appearance feature in the paper [1]. We attempted to detect the snatching event from diverse features.
-
A study on violence behavior detection system between two persons Reviewed
Atsuki Kawano, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 302 - 311 2018.6
Authorship：Last author, Corresponding author Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
Lately, surveillance cameras have been widely used for security concerns to monitor human behavior analysis by using image processing technologies. In order to take into accounts for human rights, costs effectiveness, accuracy of performance the systems so that an automatic—human behavior analytic system shall be developed. –In particular, this paper focused on the action of two person violence and detecting two person fighting each other will be considered. Some experimental results are presented to confirm the proposed method by using ICPR 2010 Contest on Semantic Description of Human Activities (SDHA 2010) dataset.
-
A study on music retrieval system using image processing Reviewed
Emi Takaoka, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 346 - 354 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
The music retrieval system has made it possible to easily search music by simply listening to songs on machine with the spread of smartphone applications. However, it requires enormous data by voice information existing system. Therefore, we proposed new music retrieval system using images visualized by sound signal processing. In the experiment, we used 35 songs and made data for retrieval by extracting a part from them and using only melody information. As a result, the percentage of correct answers that appeared in the top 3 places was 89%, which proved that the proposed method is useful.
-
A study on detection of suspicious persons for intelligent monitoring system Reviewed
Tatsuya Ishikawa, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 292 - 301 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
Currently, surveillance cameras are proliferating for prevention of crimes worldwide and early detection of emergency situations, and they play a very important role in the field of crime prevention and verification against various crimes. With regard to crime recognition and crime arrest, the number of surveillance cameras has been on the rise since it became widespread, and this has also led to crime prevention. However, in most cases, it will be coped after the occurrence of crime, and as for ongoing surveillance for 24 h, the burden on the surveillance side is heavy and there are cases where suspicious people are overlooked. In this paper, by focusing on the action of “Loitering” performed by a criminal using various characteristics of a person, it is possible to automatically determine whether the target person is a “Normal Pedestrian” or “Suspicious Pedestrian”. We will develop algorithms to make it recognizable and confirm the usefulness in terms of crime prevention and crime verification. It is also expected that establishing detection technology will contribute to crime reduction as a deterrent against crime.
-
A survey on influence and information diffusion in twitter using big data analytics Reviewed
Radia El Bacha, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 39 - 47 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
By now, even if we are still geographically situated, we’re able to reach, connect and know about each other through social networks like never before. Among all popular Social Networks, Twitter is considered as the most open social media platform used by celebrities, politicians, journalists and recently attracted a lot of attention among researcher mainly because of its unique potential to reach this large number of diverse people and for its interesting fast-moving timeline where lots of latent information can be mined such as finding influencers or understanding influence diffusion process. This studies have a significant value to various applications, e.g., understanding customer behavior, predicting flu trends, event detection and more. The purpose of this paper is to investigate the most recent research methods related to this topic and to compare them to each other. Finally, we hope that this summarized literature gives directions to other researchers for future studies on this topic.
-
Behavior analysis for nursing home monitoring system Reviewed
Pann Thinzar Seint, Thi Thi Zin
Advances in Intelligent Systems and Computing 744 274 - 283 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
In this paper, we describe the nursing home monitoring system based on computer vision. This system is aimed for an effective and automatic take care of aged persons to monitor appropriate medication intake. Skin region detection for mouth and hand tracking and color label detection for water and medication bottles tracking are mainly performed for initialization. To differentiate the hand and face region, we use the regional properties of head with online learning. Tracking is done by the minimum Eigen values detection. The overlapping area ratios of desired object to body parts are simply used as feature vectors and Pattern Recognition Neural Network is proposed for the decision of simplest action. This paper presents the 7 types of simple actions recognition for medication intake and our experimental results give the promising results.
-
A study on estrus detection of cattle combining video image and sensor information Reviewed
Tetsuya Hirata, Thi Thi Zin, Ikuo Kobayashi, Hiromitsu Hama
Advances in Intelligent Systems and Computing 744 267 - 273 2018.6
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Advances in Intelligent Systems and Computing
In Japan, the detection rate of estrus behavior of cattle has declined from 70% to 55% in about 20 years. Causes include the burden of the monitoring system due to the aging of livestock farmers and oversight of detection of estrus behavior by multiple rearing. Because the time period during which estrus behavior appears conspicuously is nearly the same at day and night, it is necessary to monitor on a 24-h system. In the method proposed in this paper, region extraction of black cattle is performed by combining frame difference and MHI (Motion History Image), then feature detection of count formula is performed using the characteristic and features of the riding behaviors. In addition, as a consideration of the model experiment, a method of detecting the riding behavior by combining the vanishing point of the camera and the height from the foot of the cattle was proposed. The effectiveness of both methods were confirmed through experimental results.
-
Behavior Analysis for Nursing Home Monitoring System Reviewed
Pann Thinzar Seint, Thi Thi Zin
Big Data Analysis and Deep Learning Applications. ICBDL 2018. Advances in Intelligent Systems and Computing 744 274 - 283 2018.6
Language：English Publishing type：Research paper (international conference proceedings)
In this paper, we describe the nursing home monitoring system based on computer vision. This system is aimed for an effective and automatic take care of aged persons to monitor appropriate medication intake. Skin region detection for mouth and hand tracking and color label detection for water and medication bottles tracking are mainly performed for initialization. To differentiate the hand and face region, we use the regional properties of head with online learning. Tracking is done by the minimum Eigen values detection. The overlapping area ratios of desired object to body parts are simply used as feature vectors and Pattern Recognition Neural Network is proposed for the decision of simplest action. This paper presents the 7 types of simple actions recognition for medication intake and our experimental results give the promising results.
-
Image technology based students' feedbacks analyzing system using deep learning Reviewed
Cho Nilar Phyo, Thi Thi Zin, Hiroshi Kamada, Takashi Toriu
Lecture Notes in Engineering and Computer Science 1 330 - 333 2018.3
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Lecture Notes in Engineering and Computer Science
In these days, the integration of technology in teaching-learning process has become a central role in order to redesign a quality education system especially for the development of interactive education. In this concern, technology based analysis on the interaction between students and teacher and the feedback of the students play key roles. Thus, in this paper, we proposed the automatic students' feedbacks analyzing system for the purpose of speeding up the communication between students and teacher in the classroom by using the image processing and deep learning technology. In the proposed system, the students can use the five kind of color cards for answering the questions or for describing their feedbacks. Then the automatic students' feedback analyzing system will analyze the color cards objects by using the camera and describe the analyzed result to the teacher. In this way, the interaction between students and teacher can be faster and can give a lot of benefit for the education system. In order to implement this system, firstly, the color objects segmentation is performed over the input image using the predefined color thresholds. Then, the noise objects are removed by using the predefined maximum size and minimum size thresholds. Finally, the Deep Convolutional Neural Network (DCNN) is applied in order to classify the five color cards objects and non-card color objects. The experiments are performed on the image that have been taken in the large classroom under the different illumination condition. According to the experimental results, the proposed system can robustly analyze the color cards objects with the accuracy of 97.02% on the training data and 94.38% for the testing data. The proposed system can give the ubiquitous (anytime, anywhere) analyzing of the students' feedback in the classroom.
-
Image Technology based Cow Identification System Using Deep Learning Reviewed
Thi Thi Zin, Cho Nilar Phyo, Pyke Tin, Hiromitsu Hama, Ikuo Kobayashi
Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists 2018 320 - 323 2018.3
Language：English Publishing type：Research paper (international conference proceedings)
Today worldwide trending in precision dairy farming is becoming more focus on an individual cow welfare and health rather than group management by using modern technologies including image processing techniques. In such cases, individual cow identification is one of the fundamental ingredients for the success of modern dairy farming. Thus, in this paper we shall explore and examine how image processing technologies can be utilized in analyzing and identifying individual cows along with deep learning techniques. This system is mainly focus on the identification of individual cow based on the black and white pattern of the cow’s body. In our system, firstly we detect the cow’s body which have been placed on the Rotary Milking Parlour by using the inter-frame differencing and horizontal histogram based approach. Then, we crop the cow’s body region by using the predefined distance value. Finally, the cropped images are used as input data for training the deep convolutional neural network for the identification of individual cow’s pattern. The experiments are performed on the self-collected cow video dataset which have been taken at the large-scale ranch in Oita Prefecture, Japan. According the experimental result, our system got the accuracy of 86.8% for automatic cropping of cow’s body region and 97.01% for cow’s pattern identification. The result shows that our system can automatically recognize each individual cow’s pattern very well.
Other Link： http://www.iaeng.org/publication/IMECS2018/
-
A Study on Disease Diagnosis by Tremor Analysis Reviewed
Yuichi Mitsui, Nobuyuki Ishii, Hitoshi Mochizuki, Thi Thi Zin
Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists 2018 1 2018.3
Language：English Publishing type：Research paper (international conference proceedings)
Tremor is a symptom in which a part of the body (hands, feet, head, etc.) trembles involuntarily. Essential tremor and cerebellar disorders are examples of diseases with tremor, but it is sometime difficult to accurately diagnose these diseases by only physical examination, and there is no indicator to quantitatively evaluate the tremor. In this study, we analyzed the Finger-Nose-Finger (FNF) test, which is a physical examination for detecting patients’ tremor, using image processing technology, and proposed an index to discriminate between essential tremor and cerebellar disorders.
Other Link： http://www.iaeng.org/publication/IMECS2018/
-
Markov Chain Techniques for Cow Behavior Analysis in Video-based Monitoring System Reviewed
Thi Thi Zin, Pyke Tin, Hiromitsu Hama, Ikuo Kobayashi
Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists 2018 1 339 - 342 2018.3
Language：English Publishing type：Research paper (international conference proceedings)
In this paper, we shall explore and examine how Markov Chain techniques of stochastic processes can be utilized to analyze cow behaviors in video-based monitoring systems. In this aspect due to shortage of human experts for monitoring the video-based monitoring system has become a powerful technique to replace for human experts. Moreover the image processing methods will play major roles in analyzing visual behaviors such as cow identification, estrus detection, prediction of calving time and body condition scoring etc. Since cow behaviors are changing with respect to times and related to immediate past, Markov Chain models will be very useful enforce the image processing techniques. Although there has been a tremendous amount of methods for detecting estrus, still it needs to improve for achieving a more accurate and practical. Thus in this paper, cow behaviors are to be analyzed by using Gamma Type Markov Chain Models. In particular, image processing methods will be performed to detect cow activities such as standing, lying and walking in association with time, space and frequencies. Then collected data are to be modeled by using Markov Chain for decision making process. As an illustration, we provide some simulation results based on gamma random number generated data.
Other Link： http://www.iaeng.org/publication/IMECS2018/
-
Color and Shape based Method for Detecting and Classifying Card Images Reviewed
Cho Nilar Phyo, Thi Thi Zin, Hiroshi Kamada, Takashi Toriu
Journal of Robotics, Networking and Artificial Life 4 ( 4 ) 287 - 290 2018.3
Language：English Publishing type：Research paper (scientific journal)
This paper proposes an effective method for detecting and classifying card images by using color and shape features. We extract the card color area using color information and remove low possibility regions based on shape feature. Then, we classify the image by taking classroom size and camera distance. In order to confirm the proposed method, we conduct the experiments with our own videos. According to experimental results the proposed method achieves the overall accuracy of 93.93% in various classroom type (small and large).
-
An Innovative Approach to Video Based Monitoring System for Independent Living Elderly People Reviewed
Thi Thi Zin, Pyke Tin, Hiromitsu Hama
Transactions on Engineering Technologies of International MultiConference of Engineers and Computer Scientists (IMECS 2017) 253 - 264 2018.2
Language：English Publishing type：Research paper (scientific journal)
In these days the population of elderly people grows faster and faster and most of them are rather preferred independent living at their homes. Thus a new and better approaches are necessary for improving the life quality of the elderly with the help of modern technology. In this chapter we shall propose a video based monitoring system to analyze the daily activities of elderly people with independent living at their homes. This approach combines data provided by the video cameras with data provided by the multiple environmental data based on the type of activity. Only normal activity or behavior data are used to train the stochastic model. Then decisions are made based on the variations from the model results to detect the abnormal behaviors. Some experimental results are shown to confirm the validity of proposed method in this paper.
-
Use of Computed Tomography and Radiography Imaging in Person Identification Reviewed
Thi Thi Zin, Ryudo Ishigami, Norihiro Shinkawa, Ryuichi Nishii
Transactions on Engineering Technologies of International MultiConference of Engineers and Computer Scientists (IMECS 2017) 311 - 323 2018.2
Language：English Publishing type：Research paper (scientific journal)
After a large scale of a natural or manmade disaster or fatal accident is hit all victims have to be immediately and accurately identified for the sake of relatives or for judicial aspects. Also it is not ethical for human being to lose their identities after death. Therefore, the identification of a person after or before death is a big issue in any society. In most commonly used methods for person identification includes utilization of different biometric modalities such as Finger-print, Iris, Hand-Veins, Dental biometrics etc. to identify humans. However only a little has been known the chest X-Ray biometric which was very powerful method for identification especially during the mass disasters in which most of other biometrics are unidentifiable. Therefore, in this paper, we propose an identification method which utilizes a fusion of computed tomography and radiography imaging processes to identify human body after death based on chest radiograph database taken prior to death. To confirm the validity of the proposed approach we exhibit some experimental results by using real life dataset. The outcomes are more promising than most of existing methods.
-
A study on disease diagnosis by tremor analysis Reviewed
Y. Mitsui, N. Ishii, H. Mochizuki, Thi Thi Zin
Lecture Notes in Engineering and Computer Science 2233 348 - 351 2018
Language：English Publishing type：Research paper (international conference proceedings) Publisher：Lecture Notes in Engineering and Computer Science
Tremor is a symptom in which a part of the body (hands, feet, head, etc.) trembles involuntarily. Essential tremor and cerebellar disorders are examples of diseases with tremor, but it is sometime difficult to accurately diagnose these diseases by only physical examination, and there is no indicator to quantitatively evaluate the tremor. In this study, we analyzed the Finger-Nose-Finger (FNF) test, which is a physical examination for detecting patients' tremor, using image processing technology, and proposed an index to discriminate between essential tremor and cerebellar disorders.
-
A Markov Chain Approach to big data ranking systems Reviewed
Radia El Bacha, Thi Thi Zin
2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017 2017-January 1 - 2 2017.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
In this paper, we propose a Markov Chain Approach to big data ranking systems. In doing so first, we create a transition matrix which will store a calculated score between every applicable pair of nodes on a large scale network. We then compute the stationary distribution of the Markov Chain with the transition matrix and rank the outcomes of this matrix to get the most influential users on the network. We have implemented our algorithm on the neo4j platform and tested it with some sample datasets. The experimental results show that the proposed method is promising for mining influential nodes in big social networks.
-
A study on automatic display system of the archery score for the visually impaired Reviewed
Kazuhisa Shiiya, Thi Thi Zin, Misaki Jomoto, Hitoshi Watanabe
2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017 2017-January 1 - 2 2017.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
In this paper we propose a robust method of displaying the archery score in real time by using image processing techniques to aid for the development of an automated scoring system after archers shoot arrows. Some experimental results are shown by using video sequences taken in an indoor environment.
-
A study on cow monitoring system for calving process Reviewed
Kosuke Sumi, Thi Thi Zin, Ikuo Kobayashi, Yoichiro Horii
2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017 2017-January 1 - 2 2017.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
Calving is a key dairy farming event and the goal is to have deliver a live, healthy calf and mother cow. Thus knowing when a cow is going to calve is very important for a dairy farm since the necessary assistance can be provided in case of difficult calving during and after birth. Thus in this paper we propose an image technology based method for detecting calving process by analyzing the motion features or monitored video sequences. In particular we utilize the motion features of tail up, increasing movement, licking the calf, repeating standing and sitting, stretching the legs. To confirm the proposed method, some experimental results are shown by using video sequences taken in a large dairy farm.
-
Skeleton motion history based human action recognition using deep learning Reviewed
Cho Nilar Phyo, Thi Thi Zin, Pyke Tin
2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017 2017-January 1 - 2 2017.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
Nowadays, deep learning is very popular in a variety of research field due to its outperformance over the existing machine learning methods and its high generality over raw inputs. According to recent surveys, deep learning can give high performance in visual object recognition system. Human Action Recognition (HAR) is a promising research area over the computer vision research field due to its enormous applicability. Most of the conventional HAR need to extract the handcrafted features in advance before classifying the actions and the environments are fixed. Those limitations make HAR to depend too much on the problem. In real-world, it is difficult to choose the suitable feature depending on the problem and difficult to fix the environment. In this paper, we applied the deep learning technology over the Skeleton Motion History Image (Skl MHI) of human actions to implement HAR that can work independently on the problem domain. According to the experimental results, the proposed system achieves the high recognition accuracy with low computational cost under the various environments.