"Automatic Tongue Segmentation and Its Movement Analysis in Video" NRCT, Research Quality Achievement Award in the field of Information Technology and Communication Art, The National Research Council of Thailand (NRCT)
"Cattle AutoID: Biometric for Cattle Identification" NRCT, Research Quality Achievement Award in the field of Information Technology and Communication Art, The National Research Council of Thailand (NRCT)
นำโดย รศ.ดร.วรพันธ์ คู่สกุลนิรันดร์
และคณะประกอบด้วย
นายกิตติคุณ ทองกัญชร
รศ.ดร.น.สพ. อนุวัตน์ วิรัชสุดากุล
นายกันต์ธร พงษ์ลือเลิศ
นายชนาธิป ศิริแสงไพรวัลย์
นางสาวโอซ นารายณ์นา
การแยกส่วนและการวัดการเคลื่อนไหวของลิ้นในภาพวิดีโอโดยอัตโนมัติ (Automatic Tongue Segmentation and Its Movement Analysis in Video)
The research project has an ultimate goal to develop a computer program based on advanced knowledge of image and video processing, to help in the oral physiotherapy and treatment. This work focuses on an analysis part of tongue movement. Therefore, the project is separated into 3 main tasks including 1) tongue segmentation in an image/video, 2) tongue’s movement detection in an image/video, and 3) UI/UX design and development for a friendly user experience.
The convolutional neural network (CNN) based approaches were developed to address the tongue segmentation. While, the optical flow and morphological operations are applied on the segmented tongues for the motion analysis. The developed models for tong segmentation and motion analysis are then plugged in the web application-based platform for an easy use of target users.
The statistical information including lengths and degrees of tongue’s movement is plotted in a format of graph for a further interpretation by medical experts. The segmentation results are promising with the accuracy over 92 % in an average, while average root mean square error (RSME) of less than 1.0.
* Deep Upscale U-Net for Automatic Tongue Segmentation, Worapan Kusakunniran, Thanandon Imaromkul, Sophon Mongkolluksamee, Kittikhun Thongkanchorn, Panrasee Ritthipravat, Pimchanok Tuakta, Paitoon Benjapornlert, Medical & Biological Engineering & Computing (MBEC), 62(6):1751-1762, Online Published: 19 February 2024, Issue: June 2024 https://doi.org/10.1007/s11517-024-03051-w
* Automated Tongue Segmentation using Deep Encoder-Decoder Model, W. Kusakunniran, P. Borwarnginn, T. Imaromkul, K. Aukkapinyo, K. Thongkanchorn, D. Wattanadhirach, S. Mongkolluksamee, R. Thammasudjarit, P. Ritthipravat, P. Tuakta, P. Benjapornlert, Multimedia Tools and Applications (MTAP), 82:37661-37686, 20 March 2023 https://doi.org/10.1007/s11042-023-15061-1
* Encoder-Decoder Network with RMP for Tongue Segmentation, W. Kusakunniran, P. Borwarnginn, S. Karnjanapreechakorn, K. Thongkanchorn, P. Ritthipravat, P. Tuakta, P. Benjapornlert, Medical & Biological Engineering & Computing (MBEC), 61(5):1193-1207, January 2023 https://doi.org/10.1007/s11517-022-02761-3
* Measurement of Tongue Motion Using Optical Flows on Segmented Areas, W. Kusakunniran, K. Aukkapinyo, P. Borwarnginn, T. Imaromkul, K. Thongkanchorn, D. Wattanadhirach, S. Mongkolluksamee, R. Thammasudjarit, P. Ritthipravat, P. Tuakta, P. Benjapornlert, Thailand, January 2022, International Conference on Knowledge and Smart Technology (KST) https://doi.org/10.1109/KST53302.2022.9729063
Existing solutions of animal identification (i.e., cattle in this research project) are based on RFID, ear tag, and microchip. However, they are facing with difficulties of high cost, dislodged and lost, and harm to human operators and animals. Therefore, this paper proposes a biometric based solution of cattle identification using cattle’s face images. The proposed method is developed using a convolutional neural network (CNN) for both main steps of face localization and face recognition.
The face localization model is trained using a Single-Shot Detector (SSD) architecture, where the face recognition model is trained based on FaceNet. The proposed method is validated using our dataset containing 2,432 cattle images from 152 different cattle. It achieves 94.74% and 83.45% for subject-based and image-based accuracies respectively.
* Analysing Muzzle Pattern Images as a Biometric for Cattle Identification, W. Kusakunniran, A. Wiratsudakul, U. Chuachan, T. Imaromkul, S. Kanchanapreechakorn, N. Suksriupatham, K. Thongkanchorn, International Journal of Biometrics (IJBM), 13(4):367-384, June 2021 https://doi.org/10.1504/IJBM.2021.117852
* Biometric for Cattle Identification using Muzzle Patterns, W. Kusakunniran, A. Wiratsudakul, U. Chuachan, S. Kanchanapreechakorn, T. Imaromkul, N. Suksriupatham, K. Thongkanchorn, International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), 34(12):2056007-1 to 2056007-21, November 2020 https://doi.org/10.1142/S0218001420560078
* Cattle AutoID: Biometric for Cattle Identification, Worapan Kusakunniran, Kunthorn Phongluelert, Chanathip Sirisangpaival, Osh Narayan, Kittikhun Thongkanchorn, Anuwat Wiratsudakul, Indonesia, October 2023, International Conference on Sustainable Information Engineering and Technology (SIET 2023) https://doi.org/10.1145/3626641.3627215
* Automatic Cattle Identification based on Multi-Channel LBP on Muzzle Images, W. Kusakunniran, T. Chaiviroonjaroen, Indonesia, November 2018, International Conference on Sustainable Information Engineering and Technology (SIET2018) https://doi.org/10.1109/SIET.2018.8693161
* BuffScan: Light to the new era of animal biometric identification in Thailand, A. Wiratsudakul, U. Chuachan, W. Kusakunniran, S. Kanchanapreechakorn, T. Imaromkul, Argentina, September 2018, International Congress on Tropical Veterinary Medicine http://isvee.net/scientific-information/poster-presentation/
* Automatic Cattle Identification based on Fusion of Texture Features Extracted from Muzzle Images, W. Kusakunniran, A. Wiratsudakul, U. Chuachan, S. Kanchanapreechakorn, T. Imaromkul, France, February 2018, IEEE International Conference on Industrial Technology (ICIT) https://doi.org/10.1109/ICIT.2018.8352400