RECOGNITION OF HANDWRITTEN DIGITS/ CHARACTERS USING MACHINE LEARNING

Pallavi Sanjay Farande; Sakshi Bhausaheb Shinde; Priti Ramesh Shinde; Shivani Satish Pachpute; Prof. N. G. Gunaware

doi:10.17605/OSF.IO/B8GPM

Authors

Pallavi Sanjay Farande Department of Computer Engineering, HSBPVT’S GOI Parikrama College of Engineering Kashti , Maharashtra,India
Sakshi Bhausaheb Shinde Department of Computer Engineering, HSBPVT’S GOI Parikrama College of Engineering Kashti , Maharashtra,India
Priti Ramesh Shinde Department of Computer Engineering, HSBPVT’S GOI Parikrama College of Engineering Kashti , Maharashtra,India
Shivani Satish Pachpute Department of Computer Engineering, HSBPVT’S GOI Parikrama College of Engineering Kashti , Maharashtra,India
Prof. N. G. Gunaware HSBPVT’S GOI Parikrama College of Engineering, Maharashtra, India

DOI:

https://doi.org/10.17605/OSF.IO/B8GPM

Keywords:

- Machine Learning, Image Process- ing, YOLO, Classification,TensorFlow, Nodejs, Pose Estimation

Abstract

Handwritten Digits/Characters an idea of recognize digit which is used for the computers.Object detection technique is used for detecting the digits and characters in English language i.e. digits from 0-9 and characters from (A-Z)(a-z)Capital letters and small letters.Object detection is performed by Cascade classifier. Cascade classifier class to detect objects in a video stream.The cascades are a bunch of XML files that contain OpenCV data used to detect objects. There area unit 2 rule area unit employed in this technology. i.e. create rule and YOLO rule.Pose estimation refers to laptop vision techniques that discover human figures in pictures and videos.The rule is just estimating wherever key body joints area unit.Human create estimation is the method of estimating the configuration of the body (pose) from one, usually monocular, image.YOLO is associate abbreviation for the term ‘You solely Look Once’. this is often associate rule that detects and acknowl- edges numerous objects in a very image (in real-time). Object detection in YOLO is completed as a regression downside and provides the category possibilities of the detected pictures.YOLO is associate rule that uses neural networks to supply time period object detection. This rule is widespread attributable to its speed and accuracy. it’s been employed in numerous applications to discover traffic signals, people, parking meters, and animals.

Downloads

Download data is not yet available.

References

Jianan Li,jianshu Li. “Multi-stage object detection with group recursive learning(2018)”. IEEE Tranction

”Detecting Affect from Non-stylised Body Motions” Daniel Bernhardt, Peter Robinson (2017).

Guanbin Li, Yukang Gan, Hejun Wu, ”Cross-Modal Attentional Context Learning for RGB-D Object Detection(2019)”. IEEE Tranction

J. Dorner, s. Kozak, F. Dietze, Object recognition by effective methods and means of computer vision

Ke Zhao, ”Handwritten Digit Recognition and Classification Using Machine Learning”, Technological University Dublin,2018.

Peng Chen and Guang-Da Hu,”A Simple Algorithm for Camera Pose Estimation.”IEEE International Conference on Automation.

’Shikhar Tandon’,’Shadab Akhter’,’Vaibhav Pratap Singh’,’Mr. Nizam Uddin Khan’,”Handwritten Digits Recognition Using Machine learn- ing”,International Journal of Information Sciences and Application (IJISA)2019.

Bapu Chendage,Rajivkumar Mente,”A Study Of Digital Image Process- ing Techniques For Character Recognition”(2020).

J.Pradeep, E.Srinivasan and S.Himavathi,”Diagonal based feature extrac- tion for Handwritten alphabets recognition System using neural network ”(2011).

J.Pradeep, E.Srinivasan and S.Himavathi,”Neural network based hand- written character recognition system without feature extraction ”(2011).

Qichang Hu, Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel, and Fatih Porikli “Fast Detection of Multiple Objects in Traffic Scenes with a standard detection framework” IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 4, April 2016.

Hanxi Li, Yi Li, and Fatih Porikli “DeepTrack: Learning Discrimi- native Feature Representations Online for Robust Visual Tracking ”. IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 4, APRIL 2016.

Jaebum Choi and Markus Maurer” Local Volumetric Hybrid-Map-Based Simultaneous Localization and Mapping With Moving Object Track- ing” IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTA- TION SYSTEMS 2016.

Stefan Duffner and Christophe Garcia” Using discriminative motion context for on-line visual object tracking”IEEE Transaction On Circuit And System for Video Technology 2105.

Shan Gao, Zhenjun Han dynasty, Ce Li, Qixiang Ye, Member, IEEE, and Jianbin Jiao” period of time Multipedestrian pursuit in Traffic Scenes via associate RGB-D-Based stratified Graph Model” IEEE transactions on intelligent transportation systems one ,2015.

Li, Devesh K. Jha, Asok Ray and Thomas A. Wetter- gren“Information Fusion of Passive Sensors for Detection of Moving Targets in Dynamic Environments” IEEE TRANSACTIONS ON CY- BERNETICS 2016 .

Zhenyu He, Xin Li, Xinge You, Dacheng Tao” Connected Component Model for Multi-Object Tracking “JOURNAL OF LATEX CLASS FILES Yue, VOL. 11, NO. 4, MAY 2016

Kunqian Li, Wenbing ,” Adaptive Optimal Shape Prior for Easy Inter- active Object Segmentation” IEEE Transactions on multimedia 2015. [19]Shunli Zhang, Sicong Zhao, Yao Sui, and Li Zhang” Single Object

Tracking with Fuzzy Least Squares Support Vector Machine”JOURNAL OF LATEX CLASS FILES, VOL. 11, NO. 4, December 2012.

Dalal, N., Triggs, B. (n.d.). Histograms of Oriented Gradi- ents for Human Detection. 2005 IEEE Computer Society Confer- ence on Computer Vision and Pattern Recognition(CVPR05),886-893. doi:10.1109/cvpr.2005.177