Unconstrained logo and trademark retrieval in general color image databases using Color Edge Gradient Co-occurrence Histograms

Phan, Raymond; Chia, Jason; Androutsos, Dimitrios

doi:10.1109/icassp.2008.4517836

Cited by 8 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final chromatic-achromatic border is defined as: S ¼ 2ðV À 1Þ 4 þ 0:15 (where S and V are normalized to the range of [0, 1]). Therefore, the chromatic region is when S > 2ðV À 1Þ 4 þ 0:15 and the achromatic region is when S 6 2ðV À 1Þ 4 þ 0:15 [19]. Fig.…”

Section: Hsv Color Quantization Methodsmentioning

confidence: 95%

“…Moving to the HSV space also solves the hue problem mentioned earlier and the true hue is preserved when transforming to the HSV color space. Starting with an adaptation of nearest neighbor for HSV, we introduced thresholds to compensate for the non-linearity of the color space and finally adjusted some thresholds to be non-linear themselves [19]. We partition the HSV color space into 11 regions which correspond to the same basic set of 11 colors seen in Luo and Crandall's work [15].…”

Section: Hsv Color Quantization Methodsmentioning

confidence: 99%

“…As such, we considered a different color space all together, namely the HSV color space [19]. It classifies similar colors under similar hue orientations.…”

Section: Hsv Color Quantization Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Content-based retrieval of logo and trademarks in unconstrained color image databases using Color Edge Gradient Co-occurrence Histograms

Phan

Androutsos

2010

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

Section: Hsv Color Quantization Methodsmentioning

confidence: 95%

Section: Hsv Color Quantization Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Content-based retrieval of logo and trademarks in unconstrained color image databases using Color Edge Gradient Co-occurrence Histograms

Phan

Androutsos

2010

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

“…Then Mori et al constructed a richer descriptor than SC based on oriented edges, called generalized shape contexts (GSCs) [10]. Several authors have proposed the combination of color and shape for logo detection in real world images [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Individualized matching based on logo density for scalable logo recognition

Zhang

Liang

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Although many systems based on global or local descriptors have shown promising results for logo recognition, they have handled all logos with the same structure and not considered their diversities. Therefore, with the logo scale increasing, the general way cannot recognize each logo perfectly. To overcome this limitation, we propose a novel strategy to match query and each logo individually using these features. First, a new conception named logo density is introduced as important semantic information for logos. Second, matching density is given according to the logo density and by utilizing it in logistic function an individualized matching strategy is developed to obtain accurate similarity for query and a logo. Finally, we present a fast recognition algorithm based upon bag-of-words model to realize scalable logo recognition. Our method is evaluated on two challenging datasets (our 10,000-class logo dataset and FlickrLogos-27). Experiments demonstrate its superior performance comparing to previous methods.

show abstract

“…Also, they may undergo perspective transformations and deformations, often be corrupted by noise or lighting effects, or be partially occluded. As a result, automatic logo recognition has drawn great interest from industry as well as various academic institutions [1][2][3][4][5][6][7][8][9][10][11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Remote logo detection using angle-distance histograms

Youn

Baek

et al. 2016

SPIE Proceedings

View full text Add to dashboard Cite

Among all the various computer vision applications, automatic logo recognition has drawn great interest from industry as well as various academic institutions. In this paper, we propose an angle-distance map, which we used to develop a robust logo detection algorithm. The proposed angle-distance histogram is invariant against scale and rotation. The proposed method first used shape information and color characteristics to find the candidate regions and then applied the angle-distance histogram. Experiments show that the proposed method detected logos of various sizes and orientations.

show abstract

Unconstrained logo and trademark retrieval in general color image databases using Color Edge Gradient Co-occurrence Histograms

Cited by 8 publications

References 7 publications

Content-based retrieval of logo and trademarks in unconstrained color image databases using Color Edge Gradient Co-occurrence Histograms

Content-based retrieval of logo and trademarks in unconstrained color image databases using Color Edge Gradient Co-occurrence Histograms

Individualized matching based on logo density for scalable logo recognition

Remote logo detection using angle-distance histograms

Contact Info

Product

Resources

About