Papers - THI THI ZIN
-
A study on detection of precursor behaviors of estrus in cattle using video camera Reviewed
H. Hama, T. Hirata, T. Mizobuchi, Thi Thi Zin
2019 IEEE 1st Global Conference on Life Sciences and Technologies, LifeTech 2019 166 - 167 2019.3
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2019 IEEE 1st Global Conference on Life Sciences and Technologies, LifeTech 2019
Development of an estrus detection system by non-contact and non-invasive methods to improve productivity is a strong desire from livestock farmers with aging society. As one of the elemental technologies, we will focus on detecting precursor behaviors of estrus in cattle using video camera. First, we converted from two-dimensional motion on video image to three dimensional one. Next, some features which are well-known as estrus precursor behaviors, were selected, for example, walking speed, trajectory and relative positional relationship of two cattle. Through experimental results, we could confirm the effectiveness of our proposed algorism. As the result, although it is a small case, it was able to detect without any false positive and false negative.
-
A Hybrid Rolling Skew Histogram-Neural Network Approach to Dairy Cow Identification System Reviewed
Cho Nilar Phyo, Thi Thi Zin, H. Hama, I. Kobayashi
International Conference Image and Vision Computing New Zealand 2018-November 2019.2
Language：English Publishing type：Research paper (international conference proceedings) Publisher：International Conference Image and Vision Computing New Zealand
In this paper, we propose a hybrid method in which rolling skew histogram and neural network techniques are fused to recognize patterns and identify cows in the milking rotary parlor of dairy farms. Individual cow identification is very important for managing the welfare and health care of an individual cow and developing the body condition scoring system. Although there has some sensor-based cows' identification system, those systems require to attach the sensor devices on each cow which is costly and burden on the cows. Since the proposed method applies a single video camera which is a non-contact device for the identification of many different cow patterns, the proposed system is low cost and no burdens on the cow. In particular, the operation of the system takes place while the cows are in the milking process in rotary milking parlor where the monitoring of individual cow is more effective than some other time and places. The identification process is based on the black and white pattern on the cow's body while moving on the rotary milking parlor. For the detecting and cropping of cows' body region is carried out by using rolling the skew histogram and used for the training process of the deep convolutional neural network. The trained network is employed for the identification of individual cow in the testing process. The experiments are performed on the self-collected cow video dataset which includes around 60 different cow's body patterns that have been taken at the large-scale farm in Oita Prefecture, Japan. The experimental results show that the proposed system is promising with the overall accuracy of 96.3 % and it is very effective and practical for the real-time cow identification system needed for establishing a modern precision dairy farming.
-
Framework of Cow Calving Monitoring System Using a Single Depth Camera Reviewed
K. Sumi, Thi Thi Zin, I. Kobayashi, Y. Horii
International Conference Image and Vision Computing New Zealand 2018-November 2019.2
Language：English Publishing type：Research paper (international conference proceedings) Publisher：International Conference Image and Vision Computing New Zealand
Calving difficulty is the primary cause of the problem of increasing death loss in cow-calf. It also profoundly effects on the economic impact of farmers and producers because of calves' death, injury to cows and high veterinary cost. To help the calving difficult of cows in time, long time continuous monitoring is required for deciding when and how to assist the calving process of cows. On the other hand, the continuous monitoring of cows' welfare become the major burden task for labors especially in a large farm where has a large number of cows. Therefore, the demands of sophisticated technology for automatic monitoring of cows' welfare is more and more increasing every year. In recent years, some researcher develops the automatics monitoring and predicting the cows' calving behavior by using the sensors devices such as temperature sensors and acceleration sensors. However, the sensors based system has various problems such as spalling and malfunction of the sensors and even can cause the burden on the cow because sensors are needed to put inside or on the body of the cow. To overcome those problems, in this paper, we propose an automatic detection of cows' calving behavior by using the depth camera (3D camera) along with image processing and computer vision technology and coordinate system transformation concept. The proposed system by using 3D camera can reduce the burden of both labors and cows.
-
A Study on Abnormal Behavior Detection of Infected Shrimp Reviewed
Takehiro Morimoto, Thi Thi Zin, Toshiaki Itami
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 818 - 819 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
A method of detecting infected shrimp has been developed. Though shrimp production is thriving in Japan, disease causes much damage. Because the cause is a virus infection, medical treatment is not currently possible. The infection route includes factors such as predation by environmental organisms and water-borne infection. However, no specific countermeasures have been developed. Therefore, early detection of infected shrimp is necessary to prevent secondary infection. When shrimp are infected, they exhibit the following abnormal behaviors: 1) not eating, 2) appearing in shallow water, or 3) making sudden movements. The developed method of detecting infected shrimp involves the use of image processing to determine when the shrimp are not eating.
-
Medication and Meal Intake Monitoring using Human-Object Interaction Reviewed
Pann Thinzar Seint, Thi Thi Zin, Mitsuhiro Yokota
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 145 - 146 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
Needs for end-of-life care are rising because of increasing age-related challenges. Among them, maintenance of nutrition and medication play an important role in healthcare of elderly people. In this situation, caregivers need to receive the daily record as a trending of usage which will lead to improvements in the quality of care. Our objective is to establish a video monitoring system for the act of taking medication and eating activity which is designed by using human-object interaction. For the evaluation of medication intake scenario, we propose the hierarchical classification system using hybrid PRNN-SVM model for action classification and activity interpretation. By the contribution of rulebased learning, our system also recognizes drinking/eating activity.
-
Automatic Postmortem Human Identification using Collarbone of X-ray and CT Scan Images Reviewed
Hanni Cho, Thi Thi Zin, N. Shinkawa, R. Nishii, H. Hama
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 369 - 370 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
Nowadays, human identification both before and after death is becoming one of the most important issues in various aspects. However, it is not easy to identify human by doctors or forensic experts manually because it consumes much time, especially in large scale victims. Therefore, an automatic human identification system becomes a vital need. For this purpose, we develop a computerized human identification system based on the collarbone of chest X-ray and CT scan images to identify an unknown person after death by using image processing technology.
-
An Automatic Estimation of Dairy Cow Body Condition Score Using Analytic Geometric Image Features Reviewed
Thi Thi Zin, Pyke Tin, I. Kobayashi, Y. Horii
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 190 - 191 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
In today modern precision dairy farms, among many dominant factors the Body Condition Score (BCS) has been considered a critical value to optimize milk production, analyzing health problems, insemination timing, and many others. Currently, the BCS is measured by human experts giving time- consuming and varying outcomes from one expert to another so that an automatic estimation system for body condition scoring is needed to be developed. Although there have been some researchers on the topics of the BCS by using image processing techniques, an efficient and satisfactory method has not been found yet. Therefore, in this paper, a new approach to an automatic estimation of dairy cow BCS using analytic geometry image features will be considered. Some experimental results are shown by using the BCS database.
-
A Study on Non-contact and Non-invasive Neonatal Jaundice Detection and Bilirubin Value Prediction Reviewed
Sojiro Kawano, Thi Thi Zin, Yuki Kodama
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 204 - 205 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
Neonatal jaundice is a yellowish discoloration of skin and eyes that commonly occurs in newborn babies. It is a physiological phenomenon in neonates and it occurs due to the overproduction of bilirubin, reduction of bilirubin treatment function. The quick and accurate treatment is required for neonatal jaundice because it can lead to nuclear jaundice, cerebral palsy, intellectual disturbance and various sequelae. The investigation methods for examining neonatal jaundice include examination using jaundice meter and blood sampling. However, these methods require continuous monitoring and can cause burden on newborn babies. In this paper, we propose the non-contact and non-invasive detection method for neonatal jaundice using image processing and computer vision technology. The experiments are performed on the data collected by University Hospital, University of Miyazaki. According to the experiments, we confirmed about the usefulness of proposed method which can work effectively for infants.
-
Tsubasa Mizobuchi, Thi Thi Zin, Ikuo Kobayashi, Hiromitsu Hama
2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018 815 - 817 2018.12
Language：English Publishing type：Research paper (international conference proceedings) Publisher：2018 IEEE 7th Global Conference on Consumer Electronics, GCCE 2018
Nowadays, the methodology of cattle production has been transferred from natural mating to artificial insemination. Therefore, estrous detection for cattle is very important to determine the time period that farmers conduct artificial insemination. However, the observation of estrous behavior by human's eyes through the whole day become as a burden task when the number of cattle is large. Therefore, most farmers are missing to notice estrous behavior. In this paper, we proposed the method for automated detection of cattle's estrous behavior, which is mounting and standing, by using laser range sensor and image processing technology. Some experiments are carried out at the Sumiyoshi field, Faculty of Agriculture, University of Miyazaki. Through experimental results, the effectiveness of our proposed method was confirmed.
-
Post-Mortem Human Identification Using Chest X-Ray and CT Scan Images Reviewed
Hanni Cho, Thi Thi ZIN, Norihiro SHINKAWA, and Ryuichi NISHII
International Journal of Biomedical Soft Computing and Human Sciences 23 ( 2 ) 51 - 57 2018.12
Language：English Publishing type：Research paper (scientific journal)
In this paper, we develop a computerized human post-mortem identification system by using chest biometrics feature. The main purpose is to identify an unknown person after death. An unknown death body is identified by comparing the chest CT image after death with the X-ray images before death stored in a database to find the highest similarity. The proposed system consists of four main processes: pre-processing, boundary extraction, feature extraction, and similarity calculation and ranking results. All the images are firstly enhanced using Contrast Limited Adaptive Histogram Equalization (CLAHE), and then ribs boundaries are extracted using morphological erosion. After that, the features are extracted using Discrete Fourier Transform (DFT). We use the Euclidean distance to calculate similarity between those features, and then ranking is performed based on the resulted distances. Finally, the system retrieves the ante-mortem X-ray images that are similar to the query image of post-mortem CT image of a death person. Experiments are conducted on dataset collected from the Faculty of Medicine, University of Miyazaki, and our experimental results are compared with the best result of the existing system under the same conditions. From the comparison, our proposed system performs best and gives the accuracy of 74.07%.
DOI： https://doi.org/10.24466/ijbschs.23.2_51
Other Link： https://www.jstage.jst.go.jp/article/ijbschs/23/2/23_51/_pdf/-char/ja
-
Ranking of Influential users based on User-Tweet bipartite graph Reviewed
Radia EL BACHA, Thi Thi Zin
Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018 97 - 101 2018.10
Authorship：Corresponding author Language：English Publishing type：Research paper (international conference proceedings) Publisher：Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018
Today, even if we are still geographically situated, but real-time news and trends are able to reach us no matter how far we are or how huge is the time difference. This is due to Social Networks Services and the strong involvement of people to them through posting, sharing and interacting online with information. Therefore, we propose a study on patterns of information diffusion on Twitter during global scale events. We also introduce a method for identifying influencers and quantify popularity of Tweets on the Network based on a user-tweet bipartite graph.
-
Classification of Shape Images Using K-mean Clustering and Deep Learning Reviewed
Swe Zar Maw, Thi Thi Zin, Mitsuhiro Yokota, Ei Phyo Min
ICIC Express Letter 12 ( 10 ) 1023 - 1023 2018.10
Language：English Publishing type：Research paper (scientific journal)
In this day and age, deep learning becomes attractive method for learning multilevel features and representation of data. In this work, we propose the new preprocessing method using K-mean clustering and the shape image classification using deep learning. Firstly, we handle K-means clustering for image preprocessing because there are many variation in input images. Image preprocessing using K-mean clustering can upgrade the achievement of the accuracy. We apply two dimensional deep convolutional neural network in order to classify 10000 shape images in the BabyAIImageAndQuestion Datasets into three different classes. We trained 10000 shape images that can properly classify near 100% and tested 5000 images that can deliver outstanding performance. The goal of our research is to develop the visual ability of children which includes visual acuity, tracking, color perception, depth perception, and object recognition by effectively applying the deep learning algorithm. We also hope that our proposed method is useful for real world application.
-
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.