Fast algorithm for the computation of moment invariants
Pattern Recognition
An introduction to computing with neural nets
ACM SIGARCH Computer Architecture News
On Image Analysis by the Methods of Moments
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital image processing algorithms
Digital image processing algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Classification Using the Inner-Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape-based image retrieval using k-means clustering and neural networks
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
| Hi-index | 0.00 |
Shape is one of the most important image features for retrieval of images in a Content-Based Image Retrieval system. However, due to inherent difficulties and limitations of processes to describe a shape, this feature is fairly less commonly used. We propose a neural network-based shape retrieval system in which moment invariants and/or Zernike moments form a feature vector to describe the shape of an object. Fuzzy k-means clustering groups similar images in an image collection into k-clusters whereas neural network facilitates efficient retrieval of similar images. Neural network is trained by the clustering results of all of the images in the data collection such that its input is the feature vector obtained through the calculated moments and its output dictates the degree of membership among the k-clusters. Retrieval results and performance of the proposed system is compared and analyzed against an earlier proposed system.