PMID- 28410096
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20190213
LR  - 20190215
IS  - 1939-3539 (Electronic)
IS  - 0098-5589 (Linking)
VI  - 40
IP  - 3
DP  - 2018 Mar
TI  - Leave-One-Out Kernel Optimization for Shadow Detection and Removal.
PG  - 682-695
LID - 10.1109/TPAMI.2017.2691703 [doi]
AB  - The objective of this work is to detect shadows in images. We pose this as the 
      problem of labeling image regions, where each region corresponds to a group of 
      superpixels. To predict the label of each region, we train a kernel Least-Squares 
      Support Vector Machine (LSSVM) for separating shadow and non-shadow regions. The 
      parameters of the kernel and the classifier are jointly learned to minimize the 
      leave-one-out cross validation error. Optimizing the leave-one-out cross 
      validation error is typically difficult, but it can be done efficiently in our 
      framework. Experiments on two challenging shadow datasets, UCF and UIUC, show 
      that our region classifier outperforms more complex methods. We further enhance 
      the performance of the region classifier by embedding it in a Markov Random Field 
      (MRF) framework and adding pairwise contextual cues. This leads to a method that 
      outperforms the state-of-the-art for shadow detection. In addition we propose a 
      new method for shadow removal based on region relighting. For each shadow region 
      we use a trained classifier to identify a neighboring lit region of the same 
      material. Given a pair of lit-shadow regions we perform a region relighting 
      transformation based on histogram matching of luminance values between the shadow 
      region and the lit region. Once a shadow is detected, we demonstrate that our 
      shadow removal approach produces results that outperform the state of the art by 
      evaluating our method using a publicly available benchmark dataset.
FAU - Vicente, Tomas F Yago
AU  - Vicente TFY
FAU - Hoai, Minh
AU  - Hoai M
FAU - Samaras, Dimitris
AU  - Samaras D
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PT  - Research Support, U.S. Gov't, Non-P.H.S.
DEP - 20170406
PL  - United States
TA  - IEEE Trans Pattern Anal Mach Intell
JT  - IEEE transactions on pattern analysis and machine intelligence
JID - 9885960
EDAT- 2017/04/15 06:00
MHDA- 2017/04/15 06:01
CRDT- 2017/04/15 06:00
PHST- 2017/04/15 06:00 [pubmed]
PHST- 2017/04/15 06:01 [medline]
PHST- 2017/04/15 06:00 [entrez]
AID - 10.1109/TPAMI.2017.2691703 [doi]
PST - ppublish
SO  - IEEE Trans Pattern Anal Mach Intell. 2018 Mar;40(3):682-695. doi: 
      10.1109/TPAMI.2017.2691703. Epub 2017 Apr 6.