Person Identification & Classification using LBP & Hog | Matlab

Ask For Price



In this conception efficient Pedestrian organization is introduced to sight the multiple road face walking persons in the processing of serial frames changes and classification of the pedestrian over the other moving objects. Texture and color unit a pair of primitive types of choices which will be won’t explain a scene. Whereas normal local binary pattern (LBP) texture-based background subtraction performs well on texture flush regions achieving person protection at intervals in the sector of computer vision. Here the task of person detection (PD) involves stages like pre-processing, ROI choice, feature extraction, classification, verification/refinement, and trailing. Of all the steps involved at intervals in the framework, the paper presents the work done towards implementing the feature extraction and classification stages notably. It’s of predominant importance that the extracted choices classifier distinguishes between a person and a non-person. The given work focuses on the implementation of the LBP abstract background changes obtaining and histogram of orientated Gradients (HOG) choices with modified parameters to Classifying is achieved exploitation Support Vector Machine (SVM).


The identification of objects during an image and would altogether probability begin with image methodology techniques like noise removal, followed by (low-level) feature extraction to hunt outlines, regions, and probably unit-like positive textures. One reason typically bean flinch is that degree object will seem terribly altogether distinction once viewed from wholly altogether totally different completely different angles or at a lower place different lighting. an image might be a few of your time and taken as a two-dimensional array of brightness values and is most familiarly pictured by such patterns as those of pictures, sliders, diode LCD TV screen, or show screen.

System Analysis

Existing Systems

  • Sift based sparse features representation
  • Feature descriptor algorithms such as BRIEF

Drawbacks of Exisitng System

  • The sparse illustration doesn’t contain data concerning texture.
  • It has poor discriminatory power
  • It is poor to characterize the excellence of data

Proposed Systems

  • LBP based background learning
  • HOG based Feature extraction
  • SVM classification


  • Robust to Illumination changes
  • Low complexity
  • Retain Contrast Information

Block Diagram

Person Identification Classification using LBP

Requirement Specifications

Hardware Requirements

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


  • MATLAB 2018b


[1] R. Cutler, L. Davis,?Robust Real-Time Periodic Motion Detection, Analysis, and Applications,? IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 781-796, 2000.

[2] Bertozzi, M. Broggi, A. Cellario, M. Fascioli, A. Lombardi, P. Porta, ?Artificial vision in road vehicles,? Proceedings of the IEEE, vol. 90, no. 7, pp.1258 -1271, 2002.

[3] C. Stauffer, W. E. L. Grimson, ?Learning Patterns of Activity Using Real-time Tracking,? IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 747-757, 2000.

[4] A. Elgammal, R. Duraiswami, D. Harwood, L. Davis,?Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance,? Proceedings of the IEEE, vol. 90, pp.1151-1163, 2000

[5] M. Lalonde, M. Beaulieu, and L. Gagnon, ?Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching,? IEEE Trans. Med. Imag., vol. 20, no. 11, pp. 1193?1200, Nov. 2001


Customer Reviews

There are no reviews yet.

Be the first to review “Person Identification & Classification using LBP & Hog | Matlab”

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