Harmonic Lyrebird Optimization with PyramidNet for Interested Region Selection-Based Image Steganography with Elliptic Curve Cryptography

Image steganography is the technique of embedding a hidden message inside an image file in a manner that makes the message difficult to detect. This technique enables covert communication by embedding data into the least significant bits of the image pixels, preserving the image’s overall appearance. Most of the previous research did not provide adequate protection against sophisticated attacks aimed at extracting or altering hidden information. Also, many existing algorithms did not adapt well to varying image characteristics or content, limiting their effectiveness. These issues are overcome by developing a new Harmonic Lyrebird Optimization Algorithm (HLOA) method to train the PyramidNet to identify regions of interest in cover images for steganography. Initially, the cover image is passed through a gridding process. Next, the cover image is converted into the frequency domain by applying the Discrete Cosine Transform (DCT). In the next step, the interested region selection is carried out by applying PyramidNet, which is fine-tuned by utilizing the designed HLOA. HLOA is the integration of harmonic analysis and the Lyrebird Optimization Algorithm (LOA). In the subsequent embedding stage, the secret image undergoes encryption. The result is subjected to inverse DCT, and the grids are then integrated to obtain the final embedded image. Later, in the extraction phase, the embedded image is passed through DCT. Further, the keymap is attained, the interested region is determined and subjected to decryption, and finally, the resultant decrypted image is forwarded for the extraction of the original image. Furthermore, the HLOA-PyramidNet attains a maximal Structural Index Similarity (SSIM) of 0.980, Peak Signal-to-Noise Ratio (PSNR) of 46.178[Formula: see text]dB, minimal Root Mean Square Error (RMSE) of 0.108 and Mean Square Error (MSE) of 0.012.

Authors

Institutions

Publication Details

Journal
Journal of Circuits Systems and Computers
Published
2026-11-14
DOI
https://doi.org/10.1142/s021812662650307x
Primary Topic
Advanced Steganography and Watermarking Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Harmonic Lyrebird Optimization with PyramidNet for Interested Region Selection-Based Image Steganography with Elliptic Curve Cryptography

A. S. N. Chakravarthy, G. Suryakala Eswari
Journal of Circuits Systems and Computers
Advanced Steganography and Watermarking Techniques
article

Harmonic Lyrebird Optimization with PyramidNet for Interested Region Selection-Based Image Steganography with Elliptic Curve Cryptography

A. S. N. Chakravarthy, G. Suryakala Eswari
article en

Abstract

Image steganography is the technique of embedding a hidden message inside an image file in a manner that makes the message difficult to detect. This technique enables covert communication by embedding data into the least significant bits of the image pixels, preserving the image’s overall appearance. Most of the previous research did not provide adequate protection against sophisticated attacks aimed at extracting or altering hidden information. Also, many existing algorithms did not adapt well to varying image characteristics or content, limiting their effectiveness. These issues are overcome by developing a new Harmonic Lyrebird Optimization Algorithm (HLOA) method to train the PyramidNet to identify regions of interest in cover images for steganography. Initially, the cover image is passed through a gridding process. Next, the cover image is converted into the frequency domain by applying the Discrete Cosine Transform (DCT). In the next step, the interested region selection is carried out by applying PyramidNet, which is fine-tuned by utilizing the designed HLOA. HLOA is the integration of harmonic analysis and the Lyrebird Optimization Algorithm (LOA). In the subsequent embedding stage, the secret image undergoes encryption. The result is subjected to inverse DCT, and the grids are then integrated to obtain the final embedded image. Later, in the extraction phase, the embedded image is passed through DCT. Further, the keymap is attained, the interested region is determined and subjected to decryption, and finally, the resultant decrypted image is forwarded for the extraction of the original image. Furthermore, the HLOA-PyramidNet attains a maximal Structural Index Similarity (SSIM) of 0.980, Peak Signal-to-Noise Ratio (PSNR) of 46.178[Formula: see text]dB, minimal Root Mean Square Error (RMSE) of 0.108 and Mean Square Error (MSE) of 0.012.

Journal of Circuits Systems and Computers
Jawaharlal Nehru Technological University, Kakinada (IN)
Advanced Steganography and Watermarking Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon