Image recognition improvement
Bag-of-features (BoF) has already become one of the most popular models in image classification over the years. Applying spatial pyramid matching (SPM) together with BoF has shown to achieve much better classification accuracy and was widely used in image categorization. In recent years, sp...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/54342 |
| _version_ | 1826121532189966336 |
|---|---|
| author | Cai, Baoou |
| author2 | Chua Chin Seng |
| author_facet | Chua Chin Seng Cai, Baoou |
| author_sort | Cai, Baoou |
| collection | NTU |
| description | Bag-of-features (BoF) has already become one of the most popular models in image
classification over the years. Applying spatial pyramid matching (SPM) together with
BoF has shown to achieve much better classification accuracy and was widely used
in image categorization. In recent years, spatial pyramid matching with sparse coding
of SIFT (ScSPM) kernel evolved from SPM with sparse coding of SIFT features and
max pooling approach greatly improve the image classification accuracy basing on
common image databases testing. This report presents three new approaches as the
optimization and supplementation of ScSPM kernel, which can be applied in the
spatial matching process before max pooling in ScSPM. They are respective diagonal
segmentation (DS) approach, max pooling with Gaussian parameter (GPMP)
approach and overlapping segmentation (OS) approach. The experiments on
classification accuracy of these approaches were implemented and further analysis
was conducted to discuss the effect of each approach. Finally the result showed that
the overlapping segmentation method can one step further increase the image
classification accuracy on the basis of conventional ScSPM. Diagonal segmentation
approach working together with the quadrate segmentation approach of conventional
ScSPM also achieved better performance for some databases. However, it is just a
start of ScSPM approach improvement. There is a board space in the advancement of
existing approaches and algorithms of image recognition. |
| first_indexed | 2024-10-01T05:33:47Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/54342 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:33:47Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/543422023-07-07T16:26:15Z Image recognition improvement Cai, Baoou Chua Chin Seng School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Bag-of-features (BoF) has already become one of the most popular models in image classification over the years. Applying spatial pyramid matching (SPM) together with BoF has shown to achieve much better classification accuracy and was widely used in image categorization. In recent years, spatial pyramid matching with sparse coding of SIFT (ScSPM) kernel evolved from SPM with sparse coding of SIFT features and max pooling approach greatly improve the image classification accuracy basing on common image databases testing. This report presents three new approaches as the optimization and supplementation of ScSPM kernel, which can be applied in the spatial matching process before max pooling in ScSPM. They are respective diagonal segmentation (DS) approach, max pooling with Gaussian parameter (GPMP) approach and overlapping segmentation (OS) approach. The experiments on classification accuracy of these approaches were implemented and further analysis was conducted to discuss the effect of each approach. Finally the result showed that the overlapping segmentation method can one step further increase the image classification accuracy on the basis of conventional ScSPM. Diagonal segmentation approach working together with the quadrate segmentation approach of conventional ScSPM also achieved better performance for some databases. However, it is just a start of ScSPM approach improvement. There is a board space in the advancement of existing approaches and algorithms of image recognition. Bachelor of Engineering 2013-06-19T04:29:01Z 2013-06-19T04:29:01Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/54342 en Nanyang Technological University 71 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Cai, Baoou Image recognition improvement |
| title | Image recognition improvement |
| title_full | Image recognition improvement |
| title_fullStr | Image recognition improvement |
| title_full_unstemmed | Image recognition improvement |
| title_short | Image recognition improvement |
| title_sort | image recognition improvement |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/54342 |
| work_keys_str_mv | AT caibaoou imagerecognitionimprovement |