Gesture Recognition using CNN | Opencv and Python


A hand gesture recognition system provides a natural, innovative and modern way of non verbal communication. It has a wide area of application in human computer interaction and sign language. The intention of this paper is to discuss a novel approach of hand gesture recognition based on detection of some shape based features. The setup consists of a single camera to capture the gesture formed by the user and take this hand image as an input to the proposed algorithm. The overall algorithm divided into some main steps, which includes segmentation, feature extraction and CNN. The proposed algorithm is independent of user characteristics. It does not require any kind of training of sample data


Challenge to involve humans and robots interact. The problem is robot does not understand the human? language directly and HRI requires media for communication which can be both understood by robot and easily done by human, especially to help deaf people, patient, and old people, therefore gesture recognition as communication media is needed to give order to Robot. Machine learning is a part of Artificial Intelligence (AI) which discusses the development of a system that depends on information or data This paper discusses hand gesture recognition as input using two methods, DWT, feature extraction and CNN techniques proposed t

Gesture Recognition using CNN Opencv and Python 3
Gesture Recognition using CNN Opencv and Python 3

he way to clustering some data which applying Euclidean idea of distance between all data elements. The method done by using feature extraction and feature matching concepts. We are going to these techniques and get clear output at the end of this project.

System Analysis

 Existing Systems

  • SVM
  • KNN
  • PCA


  • Difficulties are there to find optimal gradient
  • Poor Edge detection.
  • Time consuming
  • Less accuracy

Proposed Systems

  • Feature extraction
  • DWT
  • CNN


  • Better efficiency and less sensitive to noise
  • Highly Security
  • Automated?recognition and replication system.
  • High accuracy

Block diagram:

Gesture Recognition using CNN Opencv and Python


Image Pre-processing?and video processing is a common name for operations with?images/video frames ?at the lowest level of abstraction. Its input and output are intensity?images. The aim of?pre-processing?is an improvement of the?image?data that suppresses unwanted distortions or enhances some image?features important for further processing.

Image restoration is the operation of taking a corrupted/noisy image and estimating the clean original image. Corruption may come in many forms such as motion blur, noise, and camera misfocus.? Image restoration is different from image enhancement in that the latter is designed to emphasize features of the image that make the image more pleasing to the observer, but not necessarily to produce realistic data from a scientific point of view. Image enhancement techniques (like contrast stretching or de-blurring by a nearest neighbour procedure) provided by “Imaging packages” use no a priori model of the process that created the image.? With image enhancement noise can be effectively be removed by sacrificing some resolution, but this is not acceptable in many applications. In a Fluorescence Microscope resolution in the z-direction is bad as it is. More advanced image processing techniques must be applied to recover the object.? De-Convolution is an example of image restoration method. It is capable of: Increasing resolution, especially in the axial direction removing noise increasing contrast.

?Discrete Wavelet Transform (DWT)

The discrete wavelet remodel (DWT) became superior to use the wavelet rework to the digital international. Filter banks are used to approximate the behaviour of the non-prevent wavelet remodel. The sign is decomposed with a immoderate-skip smooth out and a low-bypass clear out. The coefficients of these filters are computed using mathematical evaluation and made to be had to you. See Appendix B for more records about those computations.

2.2 Discrete Wavelet Transform


LP d: Low Pass Decomposition Filter

HP d: High Pass Decomposition Filter

LP r: Low Pass Reconstruction Filter

HP r: High Pass Reconstruction Filter

?Convolution neural networks (CNN):

Convolutional neural network (CNN) and General Regression Neural Networks (GRNN) have similar architectures, but there is a fundamental difference: Probabilistic networks perform classification where the target variable is categorical, whereas general regression neural networks perform regression where the target variable is continuous. If you select a CNN/GRNN network, DTREG will automatically select the correct type of network based on the type of target variable.

Architecture of a CNN:

All CNN networks have four layers:

Hardware Requirements

  • system
  • 4 GB of RAM
  • 500 GB of Hard disk



[1] J. Han and M. Kamber, Data Mining Concepts and Techniques, United States of America, 2001.
[2] S.Cheng, C. Hsu, and J. Li, “Combined Hand Gesture-Speech Model for Human Action Recognition,” in Sensors,vol 13, 2013.
[3] P. Fankhauser, M. Bloesch, and D.Rodriguez, “Kinect v2 for Mobile Robot Navigation?: Evaluation and Modeling,” in Advanced Robotics (ICAR), International Conference on. IEEE, 2015., 2015.
[4] V. Vapnik, The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.
[5] J.C.Platt, N. Cristianini, J. Shawe-Taylor, “Large margin dags for multiclass classification.,” in Advances in Neural Information
Processing Systems, 2000.
[6] S. P. Lloyd, “Least square quantization in PCM,” in IEEE
Transactions on Information Theory.,2002.

[7] Chiu RWK, Chan KCA, Gao Y, Lau VYM, Zheng W, et al. (2008). Noninvasive prenatal diagnosis of fetal chromosomal aneuploidy by massively parallel genomic sequencing of DNA in maternal plasma. Proc Natl Acad Sci U S A 105: 20458-20463.

[8]. X. Fu and H. Qu, ?Research on semantic segmentation of high-resolution remote sensing image based on full convolutional neural network,? in 2018 12th International Symposium on Antennas, Propagation and EM Theory (ISAPE), Dec 2018, pp. 1?4.

[9]. S. Kumar, A. Negi, J. N. Singh, and H. Verma, ?A deep learning for brain tumor mri images semantic segmentation using fcn,? in 2018 4th International Conference on Computing Communication and Automation (ICCCA), Dec 2018, pp. 1?4

[10]. T.-H. Kim, D.-C. Park, D.-M. Woo, T. Jeong, and S.-Y. Min, ?Multi-class classifier-based adaboost algorithm,? in Proceedings of the Second Sinoforeign-interchange Conference on Intelligent Science and Intelligent Data Engineering, ser. IScIDE?11. Berlin, Heidelberg: Springer-Verlag, 2017, pp. 122?127.


Customer Reviews

There are no reviews yet.

Be the first to review “Gesture Recognition using CNN | Opencv and Python”

Your email address will not be published. Required fields are marked *