A Development of Information Retrieval System of Indigo Fabric Pattern with Deep Learning Techniques

Authors

  • Charinee Chaichana Program in Business Computer, Business Administration, Faculty of Industry and Technology, Rajamangala University of Technology Isan Sakonakhon Campus, Thailand
  • Seetala Wongkalasin Program in Business Computer, Business Administration, Faculty of Industry and Technology, Rajamangala University of Technology Isan Sakonakhon Campus, Thailand
  • Chatchai Jiamram Computer Center of Nakhonratchasima Rajabhat University, Thailand

Keywords:

Deep Learning, Image Processing, Indigo Fabric Pattern, Convolutional Neural Network

Abstract

This research is an application of image processing technology with deep learning techniques to classify the indigo fabric pattern of natural indigo dye processing groups that have been registered to use the symbolizing geographical indication. In Sakon Nakhon province, there were 42 groups, with a collection of 216 images of fabric patterns.  The model is developed using the architecture of the convolutional neural network (CNN) which uses the RestNet50 model.  The model accuracy assessment was 93% with a lower loss of 0.09%. Then the model was used in the information retrieval system of indigo fabric pattern with deep learning techniques. As a result, the accuracy on 10 samples of indigo fabric pattern was more than 80%. In addition, the system can support the identity and basic information of the indigo pattern, which is a part of public relations for community tourism called “The Indigo Way”. As a result, the community income has increased and the community also has stability and sustainability.

References

อนุรัตน์ สายทอง, อังคณา เทียนกลุ่ม, สุดกลม ลาโสภา. ครามและผลิตภัณฑ์คราม. สกลนคร: มหาวิทยาลัยราชภัฏสกลนคร; 2554.

กระทรวงวิทยาศาสตร์และเทคโนโลยี ร่วมกับมหาวิทยาลัยเทคโนโลยีราชมงคลอีสาน วิทยาเขตสกลนคร. การพัฒนาผลิตภัณฑ์ผ้าสกลนคร; 2555.

สำนักงานเกษตรจังหวัดสกลนคร กรมส่งเสริมการเกษตร กระทรวงเกษตรและสหกรณ์. แผนพัฒนาการเกษตรจังหวัดสกลนครปี 2563-2564; 2562.

นพรุจ พัฒนาสาร, ณัฐวุฒิ ศรีวิบูลย์. การประมวลผลภาพสำหรับจำแนกคุณภาพมะม่วงพันธ์โชคอนันต์ โดยการจำลองการมองเห็นของมนุษย์ด้วยวิธีการเรียนรู้เชิงลึก. Journal of Information Science and Technology. 2563;10(1):24-29.

Shamrat FJM, Mahmud I, Rahman AS, et al. A smart automated system model for vehicles detection to maintain traffic by image processing. International Journal of Scientific & Technology Research. 2020; 9(02):2921-2928.

Rahouma KH, Mahfouz AZ. Design and implementation of a face recognition system based on API mobile vision and normalized features of still images. Journal of Procedia Computer Science. 2021;194:32-44.

Rahmatov N, Paul A, Saeed F, et al. Machine learning–based automated image processing for quality management in industrial Internet of Things. International Journal of Distributed Sensor Networks. 2019;15(10):1-11.

Schlett T, Rathgeb C, Busch C. Deep learning-based single image face depth data enhancement. Computer Vision and Image Understanding Journal. 2021;210:1-15.

Gjoreski M, Gradišek A, Budna B, et al. Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds. IEEE Access. 2020;8:20313-20324.

Han C, Lei S, Mingming W, et al. Innovative design of traditional calligraphy costume patterns based on deep learning. In Journal of Physics: Conference Series. 2021;1790(1):1-6.

LeCun Y, Bottou L, Bengio Y, et al. Gradient based learning applied to document recognition. In: Proceedings of the IEEE. 1998;86(11):2278–2324.

Wang D, Wang J, Li W, et al. T-CNN: Trilinear convolutional neural networks model for visual detection of plant diseases. Computers and Electronics in Agriculture Expert Systems with Applications Journal. 2021;190:1-10.

Giuseppe CA. ResNet-50-based Convolutional neural network model for language ID identification from speech recordings. Proceedings of the Third Workshop on Computational Typology and Multilingual NLP; 2021 June. Association for Computational Linguistics. 2021:136-144.

Zhang H, Jiang L, Li C. Cs-resnet: cost-sensitive residual convolutional neural network for PCB cosmetic defect detection. Expert Systems with Applications Journal. 2021;185:1-10.

Yamane T. Statistics: An introduction analysis. New York: Harper & Row; 1973.

Bruckhaus T. The business impact of predictive analytics. In Knowledge discovery and data mining: Challenges and realities. USA: Igi Global; 2007.

Downloads

Published

2022-06-16

How to Cite

[1]
C. Chaichana, S. Wongkalasin, and C. Jiamram, “A Development of Information Retrieval System of Indigo Fabric Pattern with Deep Learning Techniques”, UTK RESEARCH JOURNAL, vol. 16, no. 1, pp. 68–83, Jun. 2022.

Issue

Section

Research Articles