Logotype detection to support semantic-based video annotation

Cózar, Julián Ramos; Guil, Nicolás; González-Linares, José María; Zapata, Emilio L.; Izquierdo, Ebroul

doi:10.1016/j.image.2007.05.006

Cited by 16 publications

(13 citation statements)

References 15 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meisinger maximizes a posteriori to optimization the threshold statistically [8]. Cózar uses the percentage of the changing pixels to eliminating undesirable frames [1]. These are effective methods for logo tracking and logo extraction, but may not suitable for logo detection, because in real web-based applications multiple consecutive frames are not available .…”

Section: Related Workmentioning

confidence: 99%

“…These sequences like sports or news may reused with the original station's logo preserved. Hence, TV logo detection can be used as a part of an automatic video classification and annotation system [1]. The existence and absence of a TV logo is a reliable indicator for program segments [10] and commercial segments [4,13], because the TV logo and the program logo disappear in the commercial period.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial HOG based TV logo detection

Zhang

Liu

et al. 2013

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service

View full text Add to dashboard Cite

Most existing TV logo detection methods use temporal correlation of multiple consecutive frames. However, these methods cannot meet the need of real-time system. This paper considers a robust detection method based on single frame. Our TV logo detecting method takes the spatial information of all matching patches as a whole, and presents a new descriptor SHOG (Spatial HOG) to formulate the spatial distribution. It is compact but informative. The proposed geometry voting method achieves fast locating TV logo with geometry verification in the step of detection, which is also competent for the detection of semi-transparent and hollow TV logos. Experiments show that SHOG is robust to occlusion and small deviation of the key points' position and our proposed method outperforms the state-of-art local feature based template matching method for logo detection as performance and speed concerned.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spatial HOG based TV logo detection

Zhang

Liu

et al. 2013

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service

View full text Add to dashboard Cite

show abstract

“…Cózar et al [1] presented a framework for cataloging videos. The authors performed temporal and spatial segmentation by calculating the minimum luminance variance region (MVLR).…”

Section: Related Workmentioning

confidence: 99%

“…Firstly, TV logos with the same owner have the same shape and size. To extract the logo template from each sub-video, the luminance variance image (LVI) of the sub-video is calculated [1]. LVI represents the maximum luminance variance in the sub-video.…”

Section: Logo Extractionmentioning

confidence: 99%

“…This is because logos contain most important information about copyright claims of owners and no additional information, e.g., watermark, is required. Automatic logo detection is also required in various applications: video cataloging, logo removal, distinguishing between an advertisement and a TV program, and replay shot detection in sports videos [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic logo transition detection in digital video contents

Roh

Kang

et al. 2012

Pattern Anal Applic

View full text Add to dashboard Cite

The amount of user created contents has been increasing rapidly and is associated with a serious copyright problem. Automatic logo detection and recognition in videos is a natural and efficient way of overcoming the copyright problem. However, logos have varying characteristics, which make logo detection and recognition very difficult. Moreover, logo transitions between two different logos exist in one video comprising several video contents. This disrupts the automatic logo detection and recognition. Therefore, in order to improve logo detection, it is necessary to take into account the logo transitions explicitly. This paper proposes an accurate logo transition detection method for recognizing logos in digital video contents. The proposed method accurately segments a video according to logo and efficiently recognizes various types of logos. The experimental results demonstrate the effectiveness of the proposed method for logo detection and video segmentation according to logo.

show abstract

Effective burn‐in reduction of organic light‐emitting diode display using perceptual color difference between logo and background

Kim¹,

Seok²,

Lee³

et al. 2022

J Soc Info Display

View full text Add to dashboard Cite

The paper proposes a method to delay the burn‐in effect of an organic light‐emitting diode (OLED) display. Usually, the burn‐in occurs in broadcasting company logo regions. In previous studies, logos were compensated by reducing the logo luminance by a specific ratio. This paper proposes a novel logo‐compensation method regarding the perceptual color difference between a logo and background areas. The proposed method has the advantage of being less affected by changes in the surrounding area than the existing compensation method, minimizing the deterioration of the recognition of the logo, and delaying the burn‐in as much as possible.

show abstract

Logotype detection to support semantic-based video annotation

Cited by 16 publications

References 15 publications

Spatial HOG based TV logo detection

Spatial HOG based TV logo detection

Automatic logo transition detection in digital video contents

Effective burn‐in reduction of organic light‐emitting diode display using perceptual color difference between logo and background

Contact Info

Product

Resources

About