臺灣博碩士論文加值系統

隨著人工智慧(Artificial Intelligence , AI)技術的進步，加上各國推動自動化政策下，除了凸顯出降低人事成本、提高效率等等優勢外，也是現代科技研究主流方向之一，例如透過數字的判斷來協助進行圖片辨識。

在本論文中，我們將將圖片大小從400×400縮小至64×64大小，並利用中值濾波(Median Filter)技術作為圖片前置處理，以濾除圖片之脈衝雜訊(Impulse Noise)，最後在電腦上進行機器訓練(Maching Learing)產生手勢識別模型。為了減少成本和延遲問題，採用Raspberry Pi 4和Arduino Uno Rev3作為圖片擷取分析之平台，透過Arduino Uno Rev3來讀取Raspberry Pi 4所傳遞之數位訊號，舒緩延遲問題。

As the progress of artificial intelligence (AI) technology, and the policy of automation, it reveals the advantages of reduced the labor costs and improved efficiency. It is also one of the main developed directions of scientific and technological research. For example, the symbol of digits can be used to assist the recognition of pictures.

In this paper, we resize the image size from 400×400 to 64×64, and use Median Filter technology to make image pre-processing for filtering out the impulse noise ( Impulse Noise). Finally, we perform machine learning on the computer to generate a recognition model of fingers. In order to reduce cost and delay problems, Raspberry Pi 4 and Arduino Uno Rev3 are used to make image capture and analysis. Arduino Uno Rev3 is used to read the digital signal by Raspberry Pi 4, this moderate the delay issue.

摘 要 X
ABSTRACT XI
致謝 XII
目錄 XIII
表目錄 VIII
第一章 緒論 1
1.1 前言 1
1.2 論文貢獻 4
1.3 論文架構 5
第二章 微控制器探討 6
2.1 微控制器之介紹 6
2.2 微控制器之介紹 7
2.2.1 Arduino Uno Rev3開發平台[4] 7
2.2.2 Raspberry Pi 4開發平台[5] 8
2.2.3 開發平台之評估 9
第三章 基於濾波技術與灰階亮度值之辨識系統 11
3.1 濾除影像雜訊之方法 11
3.1.1 濾除圖片雜訊之技術介紹[43] 12
3.1.2 濾除圖片雜訊之技術比較[44] 14
3.2 提升圖片灰階亮度值之方法 16
3.2.1 提升灰階亮度值之方法介紹[45] 17
3.2.2 提升灰階亮度值之方法比較[45] 18
3.3 系統方塊圖 19
3.4 結合濾除雜訊之卷積架構 20
3.4.1 採用基礎卷積技術之圖片辨識介紹[25] 22
3.4.2 本論文所使用之卷積圖形辨識方法[25] 24
3.4.3 丟棄層與批量標準化層探討與比較[46-50] 28
3.4.4 結合濾除雜訊和提升灰階亮度值訓練結果比較 30
第四章 模型實體應用與比較 32
4.1 測試平台硬體設備介紹 32
4.1.1 鏡頭模組介紹 32
4.1.2 馬達介紹 33
4.1.3 USB-UART介紹 33
4.1.4 總測試平台硬體架構 34
4.2 測試平台軟體設計 35
4.2.1 鏡頭模組啟動設定流程 35
4.2.2 結合卷積模型與Raspberry Pi 4設定流程 36
4.2.3 總測試平台軟體設計流程 37
4.3 測試平台驗證與結果 39
4.3.1 測試平台驗證規劃 39
4.3.2 測試平台驗證結果 40
4.4 本論文之做法與相關文獻比較與分析 42
4.4.1 相關文獻探討[21-24] 42
4.4.2 結果比較與分析[21-24] 45
第五章 結論與未來研究方向 48
5.1 結論 48
5.2 未來研究方向 48
參考文獻 49

[1]K. Shafique, B. A. Khawaja, F. Sabir, S. Qazi and M. Mustaqim, "Internet of Things (IoT) for Next-Generation Smart Systems: A Review of Current Challenges, Future Trends and Prospects for Emerging 5G-IoT Scenarios," IEEE Access, vol. 8, pp.23022-23040, 2020
[2]協調推動產業創新計劃
[Online]Available:https://www.ndc.gov.tw/Content_List.aspx?n=9D024A4424DC36B9
[3]R. Sanchez-Iborra and A. F. Skarmeta, "TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities," IEEE Circuits and Systems Magazine, vol. 20, no. 3, pp. 4-18, 2020
[4]Arduino Uno Rev3
[Online] Available: https://store.arduino.cc/products/arduino-uno-rev3
[5]Raspberry Pi 4 Model B
[Online] Available: https://www.raspberrypi.com/products/raspberry-pi-4-model-b/
[6]HOLTEK ESK-303
[Online]Available: https://www.holtek.com.tw/esk-303
[7]MediaTek LinkIt 7697
[Online] Available: https://labs.mediatek.com/en/platform/linkit-7697
[8]L. -W. Chen and H. -M. Chen, "Driver Behavior Monitoring and Warning With Dangerous Driving Detection Based on the Internet of Vehicles," IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 11, pp. 7232-7241, Nov. 2021
[9]L. -D. Liao et al., "Design and Validation of a Multifunctional Android-Based Smart Home Control and Monitoring System," IEEE Access, vol. 7, pp. 163313-163322, 2019
[10]J. W. M. Lim et al., "Automated Integrated Robotic Systems for Diagnostics and Test of Electric and Micropropulsion Thrusters," IEEE Transactions on Plasma Science, vol. 46, no. 2, pp. 345-353, Feb. 2018
[11]O. D. Jimoh, L. A. Ajao, O. O. Adeleke and S. S. Kolo, "A Vehicle Tracking System Using Greedy Forwarding Algorithms for Public Transportation in Urban Arterial," IEEE Access, vol. 8, pp. 191706-191725, 2020
[12]S. Ponnada, S. Yarramalle and M. R. T. V., "A Hybrid Approach for Identification of Manhole and Staircase to Assist Visually Challenged," IEEE Access, vol. 6, pp. 41013-41022, 2018
[13]S. Dhingra, R. B. Madda, A. H. Gandomi, R. Patan and M. Daneshmand, "Internet of Things Mobile–Air Pollution Monitoring System (IoT-Mobair)," IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5577-5584, June 2019
[14]M. Shahroz, M. F. Mushtaq, M. Ahmad, S. Ullah, A. Mehmood and G. S. Choi, "IoT-Based Smart Shopping Cart Using Radio Frequency Identification," IEEE Access, vol. 8, pp. 68426-68438, 2020
[15]TensorFlow [Online] Available: https://www.tensorflow.org/?hl=zh-tw
[16]I. Ahmed, G. Jeon and F. Piccialli, "From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where," IEEE Transactions on Industrial Informatics, vol. 18, no. 8, pp. 5031-5042, Aug. 2022
[17]Tesla Vision [Online] Available: https://www.tesla.com/support/transitioning-tesla-vision
[18]AccuPick 3D [Online] Available: https://www.solomon-3d.com/tw/accupick-3d-%e6%99%ba%e8%83%bd%e5%8f%96%e6%94%be%e7%b3%bb%e7%b5%b1
[19]EagleEye [Online] Available: https://www.advantech.tw/products/6a1d8397-ce30-4e86-a2b6-cd80ec5db4c6/eagleeye/mod_5b94a2c5-894a-4d6a-98bf-525fff2957e3
[20]工業4.0加速機器視覺成長 2025年產值達144億美元
[Online] Available: https://www.solomon.com.tw/%e5%b7%a5%e6%a5%ad4-0%e5%8a%a0%e9%80%9f%e6%a9%9f%e5%99%a8%e8%a6%96%e8%a6%ba%e6%88%90%e9%95%b7-2025%e5%b9%b4%e7%94%a2%e5%80%bc%e9%81%94144%e5%84%84%e7%be%8e%e5%85%83
[21]J. Barreyro, L. R. Yoshioka and C. L. Marte, "A non-intrusive category identification method based on the binary image of profile vehicles and CNN classification algorithm," in 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 1803-1808, 2021
[22]W. Yu, D. Lai, H. Liu and Z. Li, "Research on CNN Algorithm for Monochromatic Fabric Defect Detection," in 2021 6th International Conference on Image, Vision and Computing (ICIVC), pp. 20-25, 2021
[23]A. Momeni Pour, H. Seyedarabi, S. H. Abbasi Jahromi and A. Javadzadeh, "Automatic Detection and Monitoring of Diabetic Retinopathy Using Efficient Convolutional Neural Networks and Contrast Limited Adaptive Histogram Equalization," IEEE Access, vol. 8, pp. 136668-136673, 2020
[24]Y. -S. Su, C. -H. Chou, Y. -L. Chu and Z. -Y. Yang, "A Finger-Worn Device for Exploring Chinese Printed Text With Using CNN Algorithm on a Micro IoT Processor," IEEE Access, vol. 7, pp. 116529-116541, 2019
[25]施威名研究室著. (2020, Feb 18). tf.keras 技術者們必讀！深度學習攻略手冊. 旗標科技股份有限公司.
[Online] Available: https://www.books.com.tw/products/0010847908
[26]D. S. Breland, A. Dayal, A. Jha, P. K. Yalavarthy, O. J. Pandey and L. R. Cenkeramaddi, "Robust Hand Gestures Recognition Using a Deep CNN and Thermal Images," IEEE Sensors Journal, vol. 21, no. 23, pp. 26602-26614, 1 Dec.1, 2021
[27]M. Tufail, J. Iqbal, M. I. Tiwana, M. S. Alam, Z. A. Khan and M. T. Khan, "Identification of Tobacco Crop Based on Machine Learning for a Precision Agricultural Sprayer," IEEE Access, vol. 9, pp. 23814-23825, 2021
[28]W. Chang, L. Chen, C. Hsu, C. Lin and T. Yang, "A Deep Learning-Based Intelligent Medicine Recognition System for Chronic Patients," IEEE Access, vol. 7, pp. 44441-44458, 2019
[29]W. C. -C. Chu, C. Shih, W. -Y. Chou, S. I. Ahamed and P. -A. Hsiung, "Artificial Intelligence of Things in Sports Science: Weight Training as an Example," Computer, vol. 52, no. 11, pp. 52-61, Nov. 2019
[30]R. Bannatyne and G. Viot, "Introduction to microcontrollers," in WESCON/97 Conference Proceedings, pp. 564-574,1997
[31]R. Bannatyne and G. Viot, "Introduction to microcontrollers. II," in Wescon/98. Conference Proceedings (Cat. No.98CH36265), pp. 362-366, 1998
[32]水頭一壽,米澤遼,藤田浴士著. (2014, Jan 01). CPU自製入門. 人民郵電出版社 [Online] Available: https://www.books.com.tw/products/CN11075117
[33]B. Balon, J. Đurić and M. Simić, "Arduino Platform as Learning Tool in High School and College Education," in 2021 44th International Convention on Information, Communication and Electronic Technology (MIPRO), pp. 688-693, 2021
[34]C. -J. Chen, Y. -Y. Huang, Y. -S. Li, C. -Y. Chang and Y. -M. Huang, "An AIoT Based Smart Agricultural System for Pests Detection," IEEE Access, vol. 8, pp. 180750-180761, 2020
[35]R. Kamath, M. Balachandra and S. Prabhu, "Raspberry Pi as Visual Sensor Nodes in Precision Agriculture: A Study," IEEE Access, vol. 7, pp. 45110-45122, 2019
[36]N. C. A. Sallang, M. T. Islam, M. S. Islam and H. Arshad, "A CNN-Based Smart Waste Management System Using TensorFlow Lite and LoRa-GPS Shield in Internet of Things Environment," IEEE Access, vol. 9, pp. 153560-153574, 2021
[37]Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998
[38]A. Howard et al., "Searching for MobileNetV3," in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1314-1324, 2019
[39]K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016
[40]Y. Zhou and Z. Gao, "Intelligent Recognition of Medical Motion Image Combining Convolutional Neural Network With Internet of Things," IEEE Access, vol. 7, pp. 145462-145476, 2019
[41]G. Lou and H. Shi, "Face image recognition based on convolutional neural network," China Communications, vol. 17, no. 2, pp. 117-124, Feb. 2020
[42]A. Kumar and Y. Zhou, "Human Identification Using Finger Images," IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 2228-2244, April 2012
[43]R. C. Gonzalez and R. E. Woods, Digital image processing, 4th edition, Pearson Publishers, Inc. 2018.
[44]A. Horé and D. Ziou, "Image Quality Metrics: PSNR vs. SSIM," in 2010 20th International Conference on Pattern Recognition, pp. 2366-2369, 2010
[45]Solem. Jan Erik , Programming Computer Vision with Python, O’Reilly Media Publishers, Inc. 2012.
[46]J. Lambert, O. Sener and S. Savarese, "Deep Learning Under Privileged Information Using Heteroscedastic Dropout," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
[47]J. Liang and R. Liu, "Stacked denoising autoencoder and dropout together to prevent overfitting in deep neural network," in 2015 8th International Congress on Image and Signal Processing (CISP), pp. 697-701, 2015
[48]Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky. Ilya Sutskever, and Ruslan Salakhutdinov, "Dropout: A Simple Way to Prevent Neural Networks from Overfitting", Department of Computer Science University of Toronto, Toronto, Ontario, Canada, 2014
[49]Sergey Ioffe, and Christian Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift”, Google, Amphitheatre Pkwy, Mountain View, USA, Feb, 2015
[50]V. Thakkar, S. Tewary and C. Chakraborty, "Batch Normalization in Convolutional Neural Networks — A comparative study with CIFAR-10 data,” in 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), pp. 1-5, 2018
[51]T. Sorwar, S. B. Azad, S. R. Hussain and A. I. Mahmood, "Real-time Vehicle monitoring for traffic surveillance and adaptive change detection using Raspberry Pi camera module," in 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), pp. 481-484, 2017
[52]Raspberry Pi Camera Module 2
[Online] Available:https://www.raspberrypi.com/products/camera-module-v2/
[53]P. Garg, A. Kamboj, A. shankar and A. Kumar, "Mechanization of G, C and D Chord playing system using servomotors for Acoustic Guitar," in 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA), pp. 1-5, 2019
[54]TOWER PRO MG995
[Online] Available: https://www.towerpro.com.tw/product/mg995/
[55]TOWER PRO MG996R
[Online] Available: https://www.towerpro.com.tw/product/mg996r/
[56]M. Sharma, N. Agarwal and S. R. N. Reddy, "Design and development of daughter board for USB-UART communication between Raspberry Pi and PC," in International Conference on Computing, Communication & Automation, pp. 944-948, 2015
[57]FT232BL-UART [Online] Available: https://www.taiwansensor.com.tw/product/ft232bl-rl-usb-%E8%BD%89-ttl-%E4%B8%B2%E5%8F%A3%E6%A8%A1%E7%B5%84/
[58]K. J. Millman and M. Aivazis, "Python for Scientists and Engineers," Computing in Science & Engineering, vol. 13, no. 2, pp. 9-12, March-April 2011
[59]OpenCV [Online]Available: https://opencv.org/