shreyas parnerkar. motivation texture analysis is important in many applications of computer image...

13
SHREYAS PARNERKAR

Upload: abbigail-denn

Post on 29-Mar-2015

219 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

SHREYAS PARNERKAR

Page 2: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

MotivationTexture analysis is important in many

applications of computer image analysis for classification or segmentation of images based on local spatial variations of intensity or color.

Applications include industrial and biomedical surface inspection, for example for defects and disease, segmentation of satellite or aerial imagery, segmentation of textured regions in document analysis.

Most texture classification methods derive features based on output of large filter banks (13 – 48 dimensional feature space).

Page 3: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

MotivationTuzel et al. use image intensities and first and

second order derivatives of intensities in both x and y direction for texture classification which results in a 5 dimensional feature space.

These features are used to calculate co-variance matrices using Integral images (P & Q).

Calculation of integral images is computationally intensive because of highly nested loops.

Page 4: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Algorithm: Integral Image Calculations

Page 5: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Dependence GraphROWS

Page 6: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

GPU Utilization concernsSuch scheduling results in a maximum of W or H elements to be executed in parallel.But at other instances, it is always less than the maximum.GPU utilization drops down resulting in slow-down since plenty of

threads are idle.Such scheduling is hence not good for GPU

implementation.

Page 7: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Memory ConcernsShared Memory Limited to 4kB . Cannot put entire image in shared memory.Global memory is slow compared to shared memory.Uploading entire image in global memory causes interference with the

graphic display (??).Put just the required data in shared memory.Required data can be entire image.

Page 8: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Updated Dependence GraphROWS

ROWS

+

=

Page 9: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Results

Page 10: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

ResultsCPU Over-Head

Page 11: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Results

Page 12: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

Yet to come….Scope to improve the speed up

Page 13: SHREYAS PARNERKAR. Motivation Texture analysis is important in many applications of computer image analysis for classification or segmentation of images

In Conclusion…Implement parallel reduction for even more

speed up. (In progress)

Use calculated P-Q integral images to calculate covariance. ( Can be done on CPU )

Read Data from actual images (Currently sample random data is generated).

Compare Memory Usage for CPU vs GPU implementation.