Adatbányászat és Keresés Csoport

News:

CLIFF v0.11:
=========

Open Compute Library Image Feature Framework (CLIFF) is an OpenCL based image feature framework to compute point descriptors and modeling images for classification and retrieval efficiently on GPU-s and multicore CPU-s

CLIFF features

1. local feature extraction
2. local, dense and spatial Fisher vector [1]
3. soft cluster assigment
4. spatial [4] and segmentation based pooling
5. PCA and GMM models for HOG[2] and Color moments

Results on Pascal VOC 2007 dataset:
MAP 0.6415, ColHOG, GMM with 512, spatial pooling (1x1, 3x1)
Used options:

1. -pca models/pca.clch
2. -gmm models/gmm.clch.512
3. -step 8
4. -scales 4
5. -spatial_pool
6. -upscale
7. -pyr 5
8. -colhog
9. -alpha 0.125
10. -norm 2

System requirements :

- x86 compatible Intel/AMD processor

- Linux with AMD APP SDK or Mac OS X 10.7+

- gcc-4.3

- OpenCL 1.2

- OpenCV 2.1+

- pkg-config

CLIFF alpha Rev. 0.11 (see README in the compressed file)

CUDA based Gaussian Mixture Modeling (GMM) and Fisher vector toolkit:
=============================================================

Rev. 0.94 (see README in the compressed file) Download:

This implementation of Gaussian Mixture Model using EM algorithm is an efficient GPU based tool to train GMM models on large dimensional data (100+) within a short time. For details see our report. The source code was implemented fully in C++ compiled with nvcc and gcc-4.3.2. The compressed file also includes a tool and model files to create Fisher vectors[1] from image patches such as HOG[2] or SIFT[3]

Fisher vector Toolkit features:

1. dimension reduction via PCA
2. local Fisher vector for low-level features
3. spatial [4] and segmentation based pooling
4. PCA and GMM models for LBP[5], SIFT[3], HOG[2] and Color moments

System requirements :

- x86 compatible Intel/AMD processor

- gcc-4.3

- Cuda 1.0 compute compatibly GPU (see CUDA programming guide : http://developer.nvidia.com/object/gpucomputing.html)

- Nvidia CUDA SDK 1.3

References

1. F. Perronnin and C. Dance. Fisher kernels on visual vocabularies for image categorization. In IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR’07, pages 1–8, 2007.
2. Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. CVPR 2005
3. D.G. Lowe. Object recognition from local scale-invariant features. In International Conference on Computer Vision, volume 2, pages 1150–1157, 1999.
4. C. Schmid S. Lazebnik and J. Ponce. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, June 2006, 2006.
5. T. Ojala, M. Pietikäinen, and D. Harwood (1996), "A Comparative Study of Texture Measures with Classification Based on Feature Distributions", Pattern Recognition, vol. 29, pp. 51-59.

Contact

Bálint Daróczy
MTA SZTAKI, Data Mining and Search Group
Lágymányosi str. 11, Budapest, Hungary
daroczyb_at_ilab.sztaki.hu