Yeni Bir Dilimleme Yöntemi Kullanılarak El Yazısı Rakamlarının Tanınması ve Performans Değerlendirmesi
Year 2023,
Volume: 1 Issue: 1, 38 - 47, 10.08.2023
Sultan Murat Yılmaz
,
Serap Çakar
Abstract
Makine öğrenmesi ve bilgisayar görmesi uygulamaları son zamanlar oldukça trend olmaya ve biyometrik tanıma, hastalık teşhisi ve karakter analizi gibi uygulamalar başta olmak üzere birçok uygulama ve alanda kullanılmaya başlanmıştır. Bu çalışma kapsamında okullarda yapılan yazılı veya test sınav notlarının daha kolay okunup sistem üzerine entegre edilmesi için bir uygulama geliştirilmiş ve uygulamada kullanılan sınıflandırıcıların performansları değerlendirilmiştir. Sınav kağıtları üzerine elle yazılan başarı notlarının görüntü işleme yöntemleri kullanılarak tanımlanması yapılmıştır. Başarı notlarının tanınması aşamasında görüntü üzerinde ön işleme, dilimleme ve sınıflandırma işlemleri yapılarak kullanılan veri seti üzerinde sınıflandırma işlemleri gerçekleştirilmiştir. Sistemi eğitmek ve test etmek için akademik çalışmalarda sıklıkla tercih edilen MNIST veri seti kullanılmıştır. Bu veri setinde 0-9 arasındaki rakamların 250 farklı kişiden alınan 60.000 el yazısı örneği bulunmaktadır. Görüntü işleme aşamasında karakterlerin dilimleme işlemleri için yeni bir teknik kullanılarak tüm durumlar için uygun karakter ayrımı gerçekleştirilmiştir. Uygun dilimleme işlemi gerçekleştirildikten sonra verileri sınıflandırmak için Yapay Sinir Ağları (YSA), Evrişimsel Sinir Ağları (CNN) ve K-En Yakın Komşu (K-NN) algoritmaları kullanılmış ve performans değerleri sırasıyla %98, %98.4, %86 olarak elde edilmiştir.
References
- [1] Makkar T., Kumar Y., Dubey A.K., Rocha Á., Goyal A., Analogizing time complexity of KNN and CNN in recognizing handwritten digits, 2017 Fourth International Conference on Image Information Processing (ICIIP), (2017) 1-6.
- [2] Ghadekar P., Ingole S., Sonone D., Handwritten Digit and Letter Recognition Using Hybrid DWT-DCT with KNN and SVM Classifier, 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), (2018) 1-6.
- [3] E. Lejeune, Mechanical MNIST: A benchmark dataset for mechanical metamodels, Extreme Mechanics Letters, 36 (2020) (100659) 1-7.
- [4] Kaziha O., Bonny T., A Comparison of Quantized Convolutional and LSTM Recurrent Neural Network Models Using MNIST, 2019 International Conference on Electrical and Computing Technologies and Applications (ICECTA), (2019) 1-5.
- [5] Palvanov A, Cho Y.I. Comparisons of Deep Learning Algorithms for MNIST in Real-Time Environment, IJFIS, 18 (2018) 126-134.
- [6] Alvear-Sandoval R.F., Sancho-Gómez J.L., Figueiras-Vidal A.R., On improving CNNs performance: The case of MNIST, Information Fusion, 52 (2019)106-109.
- [7] Gati E.S., Nimo B.D., Asiamah E.K., Kannada-Mnist Classification Using Skip CNN, 16th International Computer Conference on Wavelet Active Media Technology and Information Processing, (2019( 245-248.
- [8] Beohar D., Rasool A., Handwritten Digit Recognition of MNIST dataset using Deep Learning state-of-the-art Artificial Neural Network (ANN) and Convolutional Neural Network (CNN), 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), (2021) 542-548.
- [9] Zhang K., Su H., Dou Y., Shen S., Evaluation of the Influences of Hyper-Parameters and L2-Norm Regularization on ANN Model for MNIST Recognition, 2019 International Conference on Intelligent Computing Automation and Systems (ICICAS), (2019) 379-386.
- [10] Garin A., Tauzin G., A Topological "Reading" Lesson: Classification of MNIST using TDA, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), (2019) 1551-1556.
- [11] Ge D.-y., Yao X.-f., Xiang W.-j., Wen X-j., Liu E.-c., Design of High Accuracy Detector for MNIST Handwritten Digit Recognition Based on Convolutional Neural Network, 2019 12th International Conference on Intelligent Computation Technology and Automation (ICICTA), (2019) 658-662.
- [12] Gope B., Pande S., Karale N., Dharmale S., Umekar P., Handwritten Digits Identification Using Mnist Database Via Machine Learning Models, IOP Conference Series: Materials Science and Engineering, 1022 (2021) 1-11.
- [13] KARAKAYA K., Handwriting Recognation Using Machine Learning, Master Thesis, Sakarya Üniversitesi, Institute of Natural Sciences, 2020.
- [14] GitHub, Mahanteshambi/Clustering-MNIST page, 2020, NOS. Available at: https://github.com/Mahanteshambi/Clustering-MNIST, Retrieved August 8, 2023.
- [15] Pythonawesome, A 1D analogue of the MNIST dataset for measuring spatial biases page, NOS. Available at: https://pythonawesome.com/a-1d-analogue-of-the-mnist-dataset-for-measuring-spatial-biases. Retrieved August 8, 2023.
- [16] Hochuli A.G., Oliveira L.S., Britto Jr A.S., Sabourin R., Handwritten Digit Segmentation: Is it Still Necessary?, Pattern Recognition, 78 (2018) 1-11.
- [17] Gattal A., Chibani Y., Hadjadji B., Segmentation and Recognition System for Unknown-length Handwritten Digit Strings, Pattern Analysis and Applications, 20 (2017) 307-323.
- [18] Elkhayati M., Elkettani Y., Mourchid M., Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations, Pattern Recognition, 122 (2022) (108288) 1-15.
- [19] Renton G., Soullard Y., Chatelain C., Adam S., Kermorvant C., Paquet T., S Fully Convolutional Network With Dilated Convolutions for Handwritten Text Line Segmentation, International Journal on Document Analysis and Recognition (IJDAR), 21 (2018) 177-186.
- [20] Sharma M. K., Dhaka V. S., Segmentation of Handwritten Words Using Structured Support Vector Machine, Pattern Analysis and Applications, 23 (2020) 1355-1367.
- [21] P. Jindal, B. Jindal, Line and Word Segmentation of Handwritten Text Documents Written in Gurmukhi Script Using Mid Point Detection Technique, 2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences (RAECS), (2015) 1-6.
Year 2023,
Volume: 1 Issue: 1, 38 - 47, 10.08.2023
Sultan Murat Yılmaz
,
Serap Çakar
References
- [1] Makkar T., Kumar Y., Dubey A.K., Rocha Á., Goyal A., Analogizing time complexity of KNN and CNN in recognizing handwritten digits, 2017 Fourth International Conference on Image Information Processing (ICIIP), (2017) 1-6.
- [2] Ghadekar P., Ingole S., Sonone D., Handwritten Digit and Letter Recognition Using Hybrid DWT-DCT with KNN and SVM Classifier, 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), (2018) 1-6.
- [3] E. Lejeune, Mechanical MNIST: A benchmark dataset for mechanical metamodels, Extreme Mechanics Letters, 36 (2020) (100659) 1-7.
- [4] Kaziha O., Bonny T., A Comparison of Quantized Convolutional and LSTM Recurrent Neural Network Models Using MNIST, 2019 International Conference on Electrical and Computing Technologies and Applications (ICECTA), (2019) 1-5.
- [5] Palvanov A, Cho Y.I. Comparisons of Deep Learning Algorithms for MNIST in Real-Time Environment, IJFIS, 18 (2018) 126-134.
- [6] Alvear-Sandoval R.F., Sancho-Gómez J.L., Figueiras-Vidal A.R., On improving CNNs performance: The case of MNIST, Information Fusion, 52 (2019)106-109.
- [7] Gati E.S., Nimo B.D., Asiamah E.K., Kannada-Mnist Classification Using Skip CNN, 16th International Computer Conference on Wavelet Active Media Technology and Information Processing, (2019( 245-248.
- [8] Beohar D., Rasool A., Handwritten Digit Recognition of MNIST dataset using Deep Learning state-of-the-art Artificial Neural Network (ANN) and Convolutional Neural Network (CNN), 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), (2021) 542-548.
- [9] Zhang K., Su H., Dou Y., Shen S., Evaluation of the Influences of Hyper-Parameters and L2-Norm Regularization on ANN Model for MNIST Recognition, 2019 International Conference on Intelligent Computing Automation and Systems (ICICAS), (2019) 379-386.
- [10] Garin A., Tauzin G., A Topological "Reading" Lesson: Classification of MNIST using TDA, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), (2019) 1551-1556.
- [11] Ge D.-y., Yao X.-f., Xiang W.-j., Wen X-j., Liu E.-c., Design of High Accuracy Detector for MNIST Handwritten Digit Recognition Based on Convolutional Neural Network, 2019 12th International Conference on Intelligent Computation Technology and Automation (ICICTA), (2019) 658-662.
- [12] Gope B., Pande S., Karale N., Dharmale S., Umekar P., Handwritten Digits Identification Using Mnist Database Via Machine Learning Models, IOP Conference Series: Materials Science and Engineering, 1022 (2021) 1-11.
- [13] KARAKAYA K., Handwriting Recognation Using Machine Learning, Master Thesis, Sakarya Üniversitesi, Institute of Natural Sciences, 2020.
- [14] GitHub, Mahanteshambi/Clustering-MNIST page, 2020, NOS. Available at: https://github.com/Mahanteshambi/Clustering-MNIST, Retrieved August 8, 2023.
- [15] Pythonawesome, A 1D analogue of the MNIST dataset for measuring spatial biases page, NOS. Available at: https://pythonawesome.com/a-1d-analogue-of-the-mnist-dataset-for-measuring-spatial-biases. Retrieved August 8, 2023.
- [16] Hochuli A.G., Oliveira L.S., Britto Jr A.S., Sabourin R., Handwritten Digit Segmentation: Is it Still Necessary?, Pattern Recognition, 78 (2018) 1-11.
- [17] Gattal A., Chibani Y., Hadjadji B., Segmentation and Recognition System for Unknown-length Handwritten Digit Strings, Pattern Analysis and Applications, 20 (2017) 307-323.
- [18] Elkhayati M., Elkettani Y., Mourchid M., Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations, Pattern Recognition, 122 (2022) (108288) 1-15.
- [19] Renton G., Soullard Y., Chatelain C., Adam S., Kermorvant C., Paquet T., S Fully Convolutional Network With Dilated Convolutions for Handwritten Text Line Segmentation, International Journal on Document Analysis and Recognition (IJDAR), 21 (2018) 177-186.
- [20] Sharma M. K., Dhaka V. S., Segmentation of Handwritten Words Using Structured Support Vector Machine, Pattern Analysis and Applications, 23 (2020) 1355-1367.
- [21] P. Jindal, B. Jindal, Line and Word Segmentation of Handwritten Text Documents Written in Gurmukhi Script Using Mid Point Detection Technique, 2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences (RAECS), (2015) 1-6.