Image Recognition with Machine Learning
Authors: Jyoti Choya, Ashish Ranjan
Published in: IJRRETAS, Volume 4, Issue 11, pp. 1-7 (01 Nov 2018)
Impact Factor: 3.8 (2018)
License:
CC BY 4.0 (Open Access)
Certificate: View Certificate
Abstract
The goal of this project is to use machine learning for image detection. Object detection suggests that finding the situation of the item and recognizing what it\'s. The techniques used for the item detection measure feature matching rule, pattern comparison and boundary detection. The featurematching rule is employed to seek out the most effective matching object within the knowledge domain and to implement the reconstruction of the item recognized. In the pre-treatment method we tend to 1st crop the image. once this we tend to convert the colour image to grey level image. once changing into grey level that image is filtered mistreatment 3 differing kinds of filters. they\'re average, Median, Weiner filters. once deciding the great filter we\'ll apply the segmentation method mistreatment edge detection. Template matching technique uses the correlation procedure. we\'ll realize the coefficient of correlation between the 2 templates. Relying upon the coefficient of correlation we will realize that what proportion the 2 templates are just like one another. Machine learning teaches computers to do what comes naturally humans and animals: learn from experience. Machine learning algorithms use computational methods to “learn” information directly from data without relying on a predetermined equation as a model. MATLAB provides an excellent platform to work with machine learning. it\'s wide selection of API’s help in image recognition, processing and detection. It performs a platform to experiment with images and find the best solution.
Keywords
- Image Recognition with Machine Learning
- MATLAB
- Weiner
- Median
References
- A hierarchically combined classifier for license plate recognition Lihong Zheng; Xiangjian He; Qiang Wu; Wenjing Jia; Samali, B.; Palaniswami, M.; Computer and Information Technology, 2008. CIT 2008. 8th IEEE International Conference on 8-11 July 2008 Page(s):372 - 377 Digital Object Identifier 10.1109/CIT.2008.4594704.
- A high performance license plate recognition system based on the web technique Dai Yan; Ma Hongqing; Liu Jilin; Li Langang; Intelligent Transportation Systems, 2001. Proceedings. 2001 IEEE 25-29 Aug. 2001 Page(s):325 – 329 Digital Object Identifier 10.1109/ITSC.2001.948677
- A Macao license plate recognition system Cheokman Wu; Lei Chan On; Chan Hon Weng; Tong Sio Kuan; Kengchung Ng; Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on Volume 7, 18-21 Aug. 2005 Page(s):4506 - 4510 Vol. 7 Digital Object Identifier 10.1109/ICMLC.2005.1527732
- Character recognition using parallel BP neural network Feng Yang; Fan Yang; Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on 7-9 July 2008 Page(s):1595 - 1599 Digital Object Identifier 10.1109/ICALIP.2008.4590169
- Efficient Embedded Neural-Network-Based License ISSN Online:- (2455-4723) Volume IV Issue XI November 2018 Plate Recognition System Caner, H.; Gecim, H. S.; Alkar, A. Z.; Vehicular Technology, IEEE Transactions on Digital Object Identifier 10.1109/TVT.2008.915524
- Graphical Models for Joint Segmentation and Recognition of License Plate Characters Xin Fan; Guoliang Fan; Signal Processing Letters, IEEEVolume 16, Issue 1, Jan. 2009 Page(s):10 – 13 Digital Object Identifier 10.1109/LSP.2008.2008486
- Agnes Borr`as et al. “High-Level Clothes Description Based on Color-Texture and Structural Features”. In: Lecture Notes in Computer Science. Vol. 2652. Iberian Conference, Pattern Recognition and image Analysis (IBPRIA’03). Palma (Spain): Springer- Verlag, June 2003, pp. 108–116.
- Lukas Bossard et al. “Apparel classification with style”. In: Computer Vision–ACCV 2012. Springer, 2013, pp. 321–335.
- Yangqing Jia et al. “Caffe: Convolutional Architecture for Fast Feature Embedding”. In: arXiv preprint arXiv:1408.5093 (2014).
- Andrej Karpathy. Convolutional Neural Networks. 2015.
- Carlton W Niblack et al. “QBIC Project: Querying Images by Content, using Color, Texture, and Shape”. In: IS&T/SPIE’s Symposium on Electronic Imaging: Science and Technology. International Society for Optics and Photonics. 1993, pp. 173–187.
- K. Simonyan and A. Zisserman. “Very Deep Convolutional Networks for Large-Scale Image Recognition”. In: CoRR abs/1409.1556 (2014).
- A. Yu and K. Grauman. “Fine-Grained Visual Comparisons with Local Learning”. In: Computer Vision and Pattern Recognition (CVPR). June 2014. 7
How to Cite
More from this Issue
- Internet of things Using MQTT ProtocolBhimraj Verma, Ashish Ranjan
- Multi-channel UART with auto baud rate detectionMayuri Patil, Ashish Ranjan
More by these Authors
- Indian Fruits Recorgization And Saturation Enhancement Using Deep Learning Method2022 • Vol. 8, Issue 4
- Internet of things Using MQTT Protocol2018 • Vol. 4, Issue 11
- Multi-channel UART with auto baud rate detection2018 • Vol. 4, Issue 11