MétaCan
Menu
Back to cohort
Record W1983974932 · doi:10.1109/tbc.2015.2419181

Robust Image Chroma-Keying: A Quadmap Approach Based on Global Sampling and Local Affinity

2015· article· en· W1983974932 on OpenAlexafffund
Wenyi Wang, Jiying Zhao

Bibliographic record

VenueIEEE Transactions on Broadcasting · 2015
Typearticle
Languageen
FieldComputer Science
TopicImage Enhancement Techniques
Canadian institutionsUniversity of Ottawa
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsArtificial intelligenceComputer visionColor spaceHueComputer scienceHSL and HSVKeyingColor imageColor depthColor quantizationColor balanceColor histogramMultispectral imageMathematicsImage processingImage (mathematics)Telecommunications

Abstract

fetched live from OpenAlex

Chroma-keying is a technique used to replace solid-colored background of images or video frames. This technique is widely used in TV broadcasting, film production, augmented reality, and virtual environment. This paper proposes a new chroma-keying method, which can automatically remove the background color in an image and accurately segment the foreground objects along with their transparency property. Compared to conventional chroma-keying methods based on color clustering, color difference, or thresholding, the proposed method analyzes the color statistics and color confidence of the image in global range. By analyzing image color statistics, local lightness variation, and experience from human visual perception in HSV color space, a segmentation map called quadmap is automatically generated to segment the image into four types of regions: 1) foreground; 2) background; 3) transparent; and 4) reflective regions. By using quadmap, the proposed chroma-keying system can differentiate between transparent and reflective regions. This has always been a challenging problem in conventional chroma-keying or α matting systems. This improvement generates more reliable foreground colors in reflective regions. As a result, there can be less constrains for foreground scene used in TV-broadcasting or film making. The procedures of the proposed method consist of the following five steps: 1) background region detection based on color statistics and local lightness variation; 2) absolute foreground region detection based on the knowledge of background color and predefined thresholds in Hue channel of HSV color space; 3) reflective region detection based on experience from human visual system; 4) background color propagation based on Laplacian equation; and 5) transparency value and foreground color estimation based on global sampling and color confidence.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.004
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.089
GPT teacher head0.288
Teacher spread0.199 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations15
Published2015
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Transactions on BroadcastingSame topicImage Enhancement TechniquesFrench-language works237,207