Development of improved whale optimization-based FCM clustering for image watermarking
| Autor: | N. Subhash Chandra, Kavitha Soppari |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
General Computer Science
Computer science business.industry Feature vector Pattern recognition Watermark 0102 computer and information sciences 02 engineering and technology computer.file_format Lossy compression 01 natural sciences JPEG Theoretical Computer Science 010201 computation theory & mathematics 0202 electrical engineering electronic engineering information engineering Discrete cosine transform Image scaling 020201 artificial intelligence & image processing Artificial intelligence Cluster analysis business computer Digital watermarking |
| Zdroj: | Computer Science Review. 37:100287 |
| ISSN: | 1574-0137 |
| Popis: | With the growing interest in copyright protection of multimedia, digital watermarking has been introduced and widely researched. The digital image watermarking approaches are generally adopted in the spatial or transform domain. Most of the transform-domain watermarking approaches are based on Discrete Cosine Transforms (DCT) and robust to JPEG lossy compression. Few contributions have been done using the clustering technique using for robust watermarking, and it still seeks for further improvement. Hence, this paper plans to develop an effective digital watermarking framework using an optimized clustering approach. The proposed model consists of several phases like image scaling, block separation, computation of feature vectors, spotting of regions for watermarking, message transformation, watermark embedding, IDCT, and message restoration. After image scaling, the block separation is done by DCT, and further, the feature vectors correspond to the pixel values are extracted. The optimized FCM clustering is adopted to categorize the blocks into suitable and unsuitable watermarking regions. The optimized FCM with Least Favorable-based Whale Optimization Algorithm (LF-WOA) enabled initial centroid selection takes the decision regarding the regions where the watermark can be inserted. After the watermarking embedding, the message is restored by the reverse process. Finally, the experimental results will achieve a higher demand for watermarking in terms of robustness and sensitivity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect