Bridging the Gap Between Computational Photography and Visual Recognition

Bridging the Gap Between Computational Photography and Visual Recognition

What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to cl...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 12 vom: 30. Dez., Seite 4272-4290
1. Verfasser: VidalMata, Rosaura G (VerfasserIn)
Weitere Verfasser: Banerjee, Sreya, RichardWebster, Brandon, Albright, Michael, Davalos, Pedro, McCloskey, Scott, Miller, Ben, Tambo, Asong, Ghosh, Sushobhan, Nagesh, Sudarshan, Yuan, Ye, Hu, Yueyu, Wu, Junru, Yang, Wenhan, Zhang, Xiaoshuai, Liu, Jiaying, Wang, Zhangyang, Chen, Hwann-Tzong, Huang, Tzu-Wei, Chin, Wen-Chi, Li, Yi-Chun, Lababidi, Mahmoud, Otto, Charles, Scheirer, Walter J
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000naa a22002652 4500
001 NLM313260095
003 DE-627
005 20231225150209.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2020.2996538  |2 doi 
028 5 2 |a pubmed24n1044.xml 
035 |a (DE-627)NLM313260095 
035 |a (NLM)32750769 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a VidalMata, Rosaura G  |e verfasserin  |4 aut 
245 1 0 |a Bridging the Gap Between Computational Photography and Visual Recognition 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 03.12.2021 
500 |a Date Revised 14.12.2021 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG 2 dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG 2 Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Banerjee, Sreya  |e verfasserin  |4 aut 
700 1 |a RichardWebster, Brandon  |e verfasserin  |4 aut 
700 1 |a Albright, Michael  |e verfasserin  |4 aut 
700 1 |a Davalos, Pedro  |e verfasserin  |4 aut 
700 1 |a McCloskey, Scott  |e verfasserin  |4 aut 
700 1 |a Miller, Ben  |e verfasserin  |4 aut 
700 1 |a Tambo, Asong  |e verfasserin  |4 aut 
700 1 |a Ghosh, Sushobhan  |e verfasserin  |4 aut 
700 1 |a Nagesh, Sudarshan  |e verfasserin  |4 aut 
700 1 |a Yuan, Ye  |e verfasserin  |4 aut 
700 1 |a Hu, Yueyu  |e verfasserin  |4 aut 
700 1 |a Wu, Junru  |e verfasserin  |4 aut 
700 1 |a Yang, Wenhan  |e verfasserin  |4 aut 
700 1 |a Zhang, Xiaoshuai  |e verfasserin  |4 aut 
700 1 |a Liu, Jiaying  |e verfasserin  |4 aut 
700 1 |a Wang, Zhangyang  |e verfasserin  |4 aut 
700 1 |a Chen, Hwann-Tzong  |e verfasserin  |4 aut 
700 1 |a Huang, Tzu-Wei  |e verfasserin  |4 aut 
700 1 |a Chin, Wen-Chi  |e verfasserin  |4 aut 
700 1 |a Li, Yi-Chun  |e verfasserin  |4 aut 
700 1 |a Lababidi, Mahmoud  |e verfasserin  |4 aut 
700 1 |a Otto, Charles  |e verfasserin  |4 aut 
700 1 |a Scheirer, Walter J  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 43(2021), 12 vom: 30. Dez., Seite 4272-4290  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:43  |g year:2021  |g number:12  |g day:30  |g month:12  |g pages:4272-4290 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2020.2996538  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 43  |j 2021  |e 12  |b 30  |c 12  |h 4272-4290