Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : DWT


A combining two ksvm classifiers based on True pixel values and Discrete wavelet transform for mri-based brain tumor detection and Classification

Ali A. Mohammed; Mohammed A. Noaman; Hassan M. Azzawi

Engineering and Technology Journal, 2022, Volume 40, Issue 2, Pages 322-333
DOI: 10.30684/etj.v40i2.2180

The studies on brain tumor detection and classification are continuing to improve
the specialists’ ability in diagnosis. Magnetic Resonance Imaging (MRI) is one of
the most common techniques used to evaluate brain tumors diagnosis. However,
brain tumors diagnosis is a difficult process due to congenital malformations and
possible errors in diagnosing benign from malignant tumors. Therefore, this
research aims to propose an integrated algorithm to classify brain tumors following
two stages using the Kernel Support Vector Machine (KSVM) classifier. First
stage classifies the tumors as normal and abnormal, and the second classifies
abnormal tumors as benign and malignant. The first KSVM employs extraction
features by considering the pixel values to classify images as a shape. In contrast,
the second KSVM uses the Discrete Wavelet Transform (DWT), followed by the
Principal Component Analysis (PCA) technique to extract and reduce features and
improve the model performance. Also, K-means clustering algorithm is used to
segment, isolate and calculate the tumor area. The KSVM classifiers use two
kernels (linear and Radial Basis Function (RBF)). Obtained results showed that
the linear kernel achieved 97.5% accuracy and 98.57% accuracy in the first and
second classifier, respectively. For all linear classifiers, a 100% sensitivity level is
achieved. This work validates the proposed model based on the (K-fold) strategy


Improvement of Image Steganography Using Discrete Wavelet Transform

Manal K. Oudah; Aqeela N. Abed; Rula S. Khudhair; Saad M. Kaleefah

Engineering and Technology Journal, 2020, Volume 38, Issue 1, Pages 83-87
DOI: 10.30684/etj.v38i1A.266

Recently the Discrete-Wavelet-Transform (DWT) has been represented as signal processing powerful tool to separate the signal into its band frequency components. In this paper, improvement of the steganography techniques by hiding the required message into the suitable frequency band is presented. The results show that the increase of the message length will reduce the Peak Signal to Noise Ratio (PSNR), while the PSNR increases with the increasing the DWT levels. It should be noted that the PSNR reduction was from -13.8278 to -17.77208 when increasing the message length from 161 to 505 characters. In this context, the PSNR is increased from -13.8278 to 7.0554 and from -17.7208 to 1.7901 when the DWT increased from level (1) to level (2).

Biometric Privacy Using Secret Image Sharing

A.T. Hashim; D.A. Noori

Engineering and Technology Journal, 2017, Volume 35, Issue 7, Pages 701-708

Biometric technique includes uniquely identifying person based on their physical or behavioral characteristics. It is mainly used for authentication. Iris scanning is one of the most secure techniques among all biometrics because of its uniqueness and stability (i.e., no two persons in the world can have same iris). For authentication, the feature template in the database and the user template should be the same method for extracting iris template in this proposed system. Also storing the template in the database securely is not a secure approach, because it can be stolen or tampered. To deal with this security issue, the proposed system is securely storing the template in the database by firstly using randomness to scramble the bits of template based on chaos system. Secondly, a hiding technique is utilized to hide the scrambled templates in host images randomly. Finally, a secret sharing based on linear system is implemented on the iris template in database to protect it and adding extra layer of iris authentication system. The proposed secret sharing system has been generated a meaningful shares which overcomes the problem in traditional methods. Also in proposed system, two approaches of iris extraction have been presented.

Color Image Compression Using DPCM with DCT, DWT and Quadtree Coding Scheme

Ashwaq T. Hashim; Suhad A. Ali

Engineering and Technology Journal, 2016, Volume 34, Issue 4, Pages 585-597

This paper is concerned with the design and implementation of a compression method for color image. This method based on Differential Pulse Code Modulation (DPCM), Discrete Cosine Transform (DCT) , Discrete Wavelet Transform (DWT) and Quadtree Coding Scheme. As a first step the DPCM technique is used to isolate blocks of an image into correlated and uncorrelated blocks. The isolated correlated blocks have been compressed using DCT based compression method then each block has been embedded with zeros on the original image. Each uncorrelated block has been compressed using DWT based method and put the compressed block in its location on the original image. Then, the result (i.e., the zeros blocks and compressed blocks with DWT) coded using Quadtree spatial coding. The output from DWT based and DCT based passed through shift coding stage to gain a possible further compression. The performance results of proposed hybrid algorithms produces better quality of image in terms of Peak-Signal-to-Noise Ratio (PSNR) with a higher Compression Ratio (CR) compared to standalone DCT or DWT. The PSNR values of the reconstructed images after applying proposed system are ranged from 30.62 to 40.95dB and CR on average, have been reduced to be around 1:19.6 of the size of the original image.

Hybrid Techniques for Proposed Intelligent Digital Image Watermarking

Bashar S Mahdi; Alia K. Abdul Hassan

Engineering and Technology Journal, 2015, Volume 33, Issue 4, Pages 702-713

Digital watermarking provides a solution of the recent problems such as a copyright protection and digital content authentication, as well as the balancing between the copyright protection and authentication requirements are the challenge of the many watermarking methods. In this paper, which is proposed a new intelligent watermarking methodto solve that problem by usingproposed hybrid techniques.
The proposed method can be describe by three phases, first one is employ the hybrid approach of visual cryptography and one way hash function which providing the security and authenticity to the watermarking system. Second one is concerned with intelligent embedding of watermark data in the cover image data by using three basics techniques which are the genetic algorithm, artificial neural networks and the human visual system model which obtains the effective balancing between the robustness and imperceptibility of the digital imageusing the middle frequency coefficients. Finally phase is depending on the extracting of the encrypted watermark by using the same operations of embedding stage and by using the overlapping approach in the visual cryptography. Experimental results demonstrates that the proposed methodprovidesa secure adaptive intelligent system which can apply in the different filed of application that need the reliable copyright protection with highly security and authenticity. Moreover, Obtaininga highly balancing among imperceptibility, robustness and security, that are showed by surviving the extracted watermark fromdifferent types of malicious and adaptive attacks.

Image Watermarking Using DWT_DCT

Bassim Abdulbaki Jumaa; Arwa Aladdin

Engineering and Technology Journal, 2010, Volume 28, Issue 23, Pages 6662-6675

Digital watermarking has been developed to protect digital images from
illegal manipulation. Discrete wavelet Transform (DWT) and Discrete Cosine Transform (DCT) are techniques used for digital watermarking. A combination of DWT and DCT techniques are used in this paper to meet imperceptibility, robustness and security requirements. Peak Signal to Noise Ratio (PSNR) and Bit Correct Ratio (BCR) measurements are used to study the effect of parameters: gain factor, threshold value, sub band, and image size on the watermark image. Many images are used to
embed the watermark image and the effects of parameters on the extracted
watermark image are studied. Then the optimal parameter values has been
specified.