Adaptive Resonance Theory Microchips

Serrano-Gotarredona, Teresa; Linares-Barranco, B.; Andreou, Andreas G.

doi:10.1007/978-1-4419-8710-5

Cited by 39 publications

(23 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All arrays are normalized by dividing each input vector by its norm. An input vector is said to be normalized when there exists a constant such that for all input vectors [10]. Complement-coding rule [3] is applied for the normalization of the input vectors.…”

Section: A Preprocessing By Fuzzy-art Clusteringmentioning

confidence: 99%

“…2 shows the flow diagram of the Fuzzy-ART operation. Interested reader can refer to [3], [10], [18] for more details. …”

Section: A Preprocessing By Fuzzy-art Clusteringmentioning

confidence: 99%

“…We envisage that the amount of information that can be embedded is very image dependent and a good balance between imperceptibility and robustness is hard to strive by compelling to embed watermark information globally. In our proposed watermarking scheme, the DCT coefficients in selected regions of the host image are adaptively modulated by the watermark information with the help of Fuzzy adaptive resonance theory (Fuzzy-ART) [3], [5], [10], [18]. Thus, the strength of the watermark can be increased to enhance the robustness without introducing noticeable degradation to the visual quality of the host image.…”

mentioning

confidence: 99%

“…Fig. 1 shows the architecture of the Fuzzy-ART network [10]. It consists of two layers of computing cells or neurons, and a vigilance subsystem controlled by an adjustable vigilance parameter .…”

mentioning

confidence: 99%

“…The input vectors are applied to the Fuzzy-ART network one by one. The network seeks for the "nearest" cluster that "resonates" with the input pattern according to a "winner-take-all" strategy and updates the cluster to become "closer" to the input vector [3], [10], [18]. In the process, the vigilance parameter determines the similarity of the inputs belonging to the same cluster.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Fuzzy-ART based adaptive digital watermarking scheme

Chang

Liu

Zhang³

2005

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-In this paper, a novel transform domain digital watermarking scheme that uses visually meaningful binary image as watermark has been developed. The method embeds the watermark information adaptively with localized embedding strength according to the noise sensitivity level of the host image. Fuzzy adaptive resonance theory (Fuzzy-ART) classification is used to identify appropriate locations for watermark insertion and its control parameters add agility to the clustering results to thwart counterfeiting attacks. The scalability of visually recognizable watermark is exploited to devise a robust weighted recovery method with composite watermark. The proposed watermarking schemes can also be employed for oblivious detection. Unlike most oblivious watermarking schemes, our methods allow the use of visually meaningful image as watermark. For automation friendly verification, a normalized correlation metric that suits well with the statistical property of our methods is used. The experimental results show that the proposed techniques can survive several kinds of image processing attacks and the JPEG lossy compression.

show abstract

Section: A Preprocessing By Fuzzy-art Clusteringmentioning

confidence: 99%

“…2 shows the flow diagram of the Fuzzy-ART operation. Interested reader can refer to [3], [10], [18] for more details. …”

Section: A Preprocessing By Fuzzy-art Clusteringmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%