Computer Vision Work Summary
Lior Zilpa, guided by Dr. Lior Wolf
A short overview of my work:
- I worked on the implementation of "Fisher Kernel" for classifying images by training the GMM on large dataset. The implementation divided into the following steps, assuming a set of images for each image class:
- Generate sifts descriptors for each image. This set is generated for each image in all the classes and called - feaset - descriptor of the image.
- Train the GMM classifier on all the generated sifts.
- Generate a Fisher Vector using the GMM.
----—For more information see Improving the Fisher Kernel for Large-Scale Image Classification
- I read an article about SCC-Spectral Curvature Clustering and overviewed on its implementation. This article deals with improving the performance of multi-way spectral clustering. The article suggests some nice application using that kind of clustering:
- Motion Segmentation under Affine Camera Models
- Face Clustering under Varying Lighting Condition
- Temporal Segmentation of Video Sequences
----—For more information see Spectral Curvature Clustering
- I also read a nice article about Object Detection: Object Detection with Discriminatively Trained Part Based Models
Throughout the work in this course I was exposed to machine learning, Pattern Recognition ,data mining and some interesting algorithms of Computer Vision. In addition, I got familiar with the research world in general, and with the Computer Vision field, in particular.
page revision: 4, last edited: 21 Nov 2010 22:28