The problem addressed by this project is to recognize the images of similar types using the best available data structure to store image feature and machine learning algorithm to produce the best result based on the input image searched.
Section 1: Extract Features :
Extract Features based on Color/ Texture/Edges Create a Feature File Section 2: Index the Images:
Implement Indexing techniques to store Image object in Hash Map Use Hashing techniques Section 3: Apply Machine Learning Algorithm:
Clustering using K –Means Clustering using K- Nearest Neighbor Based on Distance Function (Euclidean Distance) Section 4: Search Image:
Extract Features of the image to be compared
Section 5: Display Best Results
We have use the following Machine Learning Algorithm to train and test our Model namely:
K – Means Clustering : k-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. This results in a partitioning of the data space into Voronoi cells.
K- Nearest Neighbors : In pattern recognition, the k-nearest neighbors algorithm (k-NN) is a non-parametric method used for classification and regression. In both cases, the input consists of the k closest training examples in the feature space. The output depends on whether k-NN is used for classification or regression
Euclidean Distance : Euclidean distance or Euclidean metric is the "ordinary" straight-line distance between two points in Euclidean space.