Retina-imitation sampling based binary descriptor
The existing binary descriptors，generated from random or uniform point pairs sampling，suffer from low robustness and high computation.A novel sampling method,named RBS (retina-imitation based sampling),was proposed， which combines different densities sampling,multi-scale smoothing and reception fiel...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2019-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019021/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539470074052608 |
|---|---|
| author | Qingsheng YUAN Guoqing JIN Dongming ZHANG Xiuguo BAO |
| author_facet | Qingsheng YUAN Guoqing JIN Dongming ZHANG Xiuguo BAO |
| author_sort | Qingsheng YUAN |
| collection | DOAJ |
| description | The existing binary descriptors，generated from random or uniform point pairs sampling，suffer from low robustness and high computation.A novel sampling method,named RBS (retina-imitation based sampling),was proposed， which combines different densities sampling,multi-scale smoothing and reception field overlapping to imitate the converting from light signal to vision of ganglion cells of human retina cells,and further selects most discriminative comparison pairs based on learning on training data.Finally，compact binary descriptor was generated based on comparisons between the neighbor mean instead of singe sampled point.The experimental results show the RBS-128 with 128 bit outperforms FREAK and BRSIK with 512 bit about 16.4% and 5.3% in precision on the dataset provided by Mikolajczyk. |
| format | Article |
| id | doaj-art-f34b6f005fbd467caf82cfea35262c71 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2019-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-f34b6f005fbd467caf82cfea35262c712025-01-14T07:16:04ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2019-01-0140152359724257Retina-imitation sampling based binary descriptorQingsheng YUANGuoqing JINDongming ZHANGXiuguo BAOThe existing binary descriptors，generated from random or uniform point pairs sampling，suffer from low robustness and high computation.A novel sampling method,named RBS (retina-imitation based sampling),was proposed， which combines different densities sampling,multi-scale smoothing and reception field overlapping to imitate the converting from light signal to vision of ganglion cells of human retina cells,and further selects most discriminative comparison pairs based on learning on training data.Finally，compact binary descriptor was generated based on comparisons between the neighbor mean instead of singe sampled point.The experimental results show the RBS-128 with 128 bit outperforms FREAK and BRSIK with 512 bit about 16.4% and 5.3% in precision on the dataset provided by Mikolajczyk.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019021/binary descriptorretina-imitation based samplingganglion cellcomparison pairs |
| spellingShingle | Qingsheng YUAN Guoqing JIN Dongming ZHANG Xiuguo BAO Retina-imitation sampling based binary descriptor Tongxin xuebao binary descriptor retina-imitation based sampling ganglion cell comparison pairs |
| title | Retina-imitation sampling based binary descriptor |
| title_full | Retina-imitation sampling based binary descriptor |
| title_fullStr | Retina-imitation sampling based binary descriptor |
| title_full_unstemmed | Retina-imitation sampling based binary descriptor |
| title_short | Retina-imitation sampling based binary descriptor |
| title_sort | retina imitation sampling based binary descriptor |
| topic | binary descriptor retina-imitation based sampling ganglion cell comparison pairs |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019021/ |
| work_keys_str_mv | AT qingshengyuan retinaimitationsamplingbasedbinarydescriptor AT guoqingjin retinaimitationsamplingbasedbinarydescriptor AT dongmingzhang retinaimitationsamplingbasedbinarydescriptor AT xiuguobao retinaimitationsamplingbasedbinarydescriptor |