Developing Image Search Engine using Content Based Image Retrieval and Haar Cascade Classifier

Motivation

  • Need for Image Search Engine from our experience with Object Recognition.
  • Present application system is uses CBIR but our objective will be to experiment more with Haar cascade classifier.
  • ​Will learn more about Image Processing and its application

Technology Used

  • Redis
  • Python
  • Haar Cascade Classifier
  • OpenCV
  • Flask and Jquery

Research Work Done

  • Current work involves Image Search using MetaData or CBIR
  • Working with CBIR gives preliminary but no accurate result for the samples
  • There is currently no model present that clubs up CBIR, and Haar Cascade
  • Our target will be to present one such model

Algorithm Used

CBIR Parameters to be used

COLOR: Image retrieval based on color actually means retrieval on color descriptors. Most commonly used color descriptors are the color histogram, color coherence vector, color correlogram, and color moments 

TEXTURE: Texture of an image is actually visual patterns that an image possesses and how they are spatially defined. Textures are represented by texels which are then placed into a number of sets, depending on how many textures are detected in the image. 

SHAPE:Shape in image does not mean shape of an image but it means that shape of a particular region or an object. Segmentation and edge detection are prominent tech- niques that can be used in shape detection 

Similarity Measurement :A similarity measurement is always selected to find how similar the two vectors are. The problem can be converted to computing the discrepancy between two vectors x,y ∈ Rd. There are three distance measurements: Euclidean, Mahalanobis, and chord distances 

Using Color

  • Create a Database of Color features
  • Gives user feasibility of own tag creation
  • Used in wide scale application
  • Create a proper bin model

Comparison between Color Histogram

  • Uses Haar feature-based cascade classifiers for Object Recognition.
  • It is a machine learning based approach where a cascade function is trained from a lot of positive and negative images.
  • Need to meet large number of training samples is met by Adaboost Algorithm
  • The paper says even 200 features provide detection with 95% accuracy

Proposed Architecture

WORK IMPLEMENTED

Using Viola-Jones framework we have implemented detection for several object

  • Face detection using haar cascade face classifier
  • Face and eye detection using haar cascade eye and frontalface classifier
  • Hand detection using haar cascade hand classifier
  • Car detection using haar cascade car classifier
  • Used CBIR Feature to extract properties
  • Add Image tagging facility
  • Implement Upvote/Downvote algorithm
  • Implemented Search Engine
  • Implemented User Interface

Screenshots

Biblography:

Project Hosted at:

Thank you :)

Made with Slides.com