International Journal of Image, Graphics and Signal Processing @ijigsp
Journal articles - International Journal of Image, Graphics and Signal Processing
All articles: 1207
Video Watermarking – Combination of Discrete Wavelet & Cosine Transform to Achieve Extra Robustness
Scientific article
In this paper we worked on the video watermarking technique wherein we took video as a cover medium and some binary images as watermark to be embedded behind the video. Specifically we concentrated on the transform domain technique and we made use of hybridization of the two of the most important and useful transformations, namely Discrete Wavelet Transform and Discrete Cosine Transform, for the purpose of digital watermarking. We evaluated the proposed method with some visual quality matrices and based on the results we concluded that the proposed method provides extra robustness against various attacks as compare to individual use of each transform.
Free
Viewpoint Selection Using Hybrid Simplex Search and Particle Swarm Optimization for Volume Rendering
Scientific article
In this paper we proposed a novel method of viewpoint selection using the hybrid Nelder-Mead (NM) simplex search and particle swarm optimization (PSO) to improve the efficiency and the intelligent level of volume rendering. This method constructed the viewpoint quality evaluation function in the form of entropy by utilizing the luminance and structure features of the two-dimensional projective image of volume data. During the process of volume rendering, the hybrid NM-PSO algorithm intended to locate the globally optimal viewpoint or a set of the optimized viewpoints automatically and intelligently. Experimental results have shown that this method avoids redundant interactions and evidently improves the efficiency of volume rendering. The optimized viewpoints can focus on the important structural features or the region of interest in volume data and exhibit definite correlation with the perception character of human visual system. Compared with the methods based on PSO or NM simplex search, our method has the better performance of convergence rate, convergence accuracy and robustness.
Free
Vision-based Classification of Pakistani Sign Language
Scientific article
Automated sign language recognition is one of the important areas of computer vision today, because of its applicability in vast fields of life. This paper presents automated recognition of signs taken from Pakistani Sign Language (PSL). The paper presents empirical analysis of two statistical and one transformation based shape descriptors for the recognition of PSL. A purely vision based, efficient, signer independent, multi-aspect invariant method is proposed for the recognition of 44 signs of PSL. The method has proved its worth by utilizing a very small shape descriptor and giving promising results for a reasonable size of sign dictionary. The proposed methodology achieved an accuracy of 92%.
Free
Visual Improvement for Hepatic Abscess Sonogram by Segmentation after Curvelet Denoising
Scientific article
A wise automated method for wisely improving the visualization of hepatic abscess sonogram, a modest trial is being done to denoise and reduce the ultrasound scan speckles wisely and effectively. As an effective way for improving the diagnostic decision; improved sonogram for hepatic abscess is reconstructed by ultrasound scan image segmentation after denoising in Curvelet transform domain. Better sonogram visualization is required for better human interpretation. Speckle noise filtering of medical ultrasound images is needed for enhanced diagnosis. Double thresholding segmentation was applied on, an ultrasound scan image for a Liver with amebic abscess, after it had been denoised in Curvelet transform domain. The result is enhanced wise effect on the hepatic abscess sonogram image's visualization which improves physicians' decisions. Moreover, this method effectively reduces the memory storage size for the image which consequently decreases computation processing time.
Free
Visual Object Target Tracking Using Particle Filter: A Survey
Scientific article
This paper gives the survey of the existing developments of Visual object target tracking using particle filter from the last decade and discusses the advantage and disadvantages of various particle filters. A variety of different approaches and algorithms have been proposed in literature. At present most of the work in Visual Object Target Tracking is focusing on using particle filter. The particle filters has the advantage that they deal with nonlinear models and non-Gaussian innovations, and they focus sequentially on the higher density regions of the state space, mostly parallelizable and easy to implement, so it gives a robust tracking framework, as it models the uncertainty and showing good improvement in the recognition performance compared to the kalman filter and other filters like Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF).Various features and classifiers that are used with particle filter are given in this survey.
Free
Visual object tracking by fusion of audio imaging in template matching framework
Scientific article
Audio imaging can play a fundamental role in computer vision, in particular in automated surveillance, boosting the accuracy of current systems based on standard optical cameras. We present here a method for object tracking application that fuses visual image with an audio image in the template-matching framework. Firstly, an improved template matching based tracking is presented that takes care of the chaotic movements in the template-matching algorithm. Then a fusion scheme is presented that makes use of deviations in the correlation scores pattern obtained across the individual frame in each imaging domain. The method is compared with various state of art trackers that perform track estimation using only visible imagery. Results highlight a significant improvement in the object tracking by the assistance of audio imaging using the proposed method under severe challenging vision conditions such as occlusions, object shape deformations, the presence of clutters and camouflage, etc.
Free
Voice Comparison Using Acoustic Analysis and Generative Adversarial Network for Forensics
Scientific article
Forensic Voice Comparison (FVC) is a scientific analysis that examines audio recordings to determine whether they come from the same or different speakers in digital forensics. In this research work, the experiment utilizes three different techniques, like pre-processing, feature extraction, and classification. In preprocessing, the stationery noise reduction algorithm is used to remove unwanted background noise by increasing the clarity of the speech. This in turn helps to improve the overall audio quality by reducing distractions. Further, acoustic features like Mel Frequency Cepstral Coefficients (MFCC) are used to extract relevant and distinctive features from audio signals to characterize and analyze the unique vocal patterns of different individual. Later, the Generative Adversarial Network (GAN) is used to generate synthetic MFCC features and also for augmenting the data samples. Finally, the Logistic Regression (LR) is realized using UK framework for the classification of the model to predict whether the result is true or false. The results achieved in terms of accuracy are 62% considering 3899 samples and 85% when considering set of 985 samples for the Australian English datasets.
Free
WOA Enabled Fuzzy-C-Means Segmentation for Accurate Detection of Polycystic Kidney Disease
Scientific article
Polycystic Kidney disease (PKD) is often caused due to inherited condition and it forms many cysts around the kidney, and it is damaged when it grow. Accurate segmentation of PKD is very crucial for a persistent MRI diagnostics. Because many people have no symptoms, they can lead to complications until the surgery is done to remove the cyst. Methods: For accurate detection PKD, the heap of MRI images have been considered, In this work, A novel method includes feature based Fuzzy C means (FFCM) with whale optimization algorithm (WOA) for accurate segmentation of kidney cyst. WOA is used to optimally attach the cluster centroids of FCM. In the conventional methods like mountain models and fuzzy C-shells models are used to identify the regions of interest (ROI). Result: The outcomes of FFCM and WOA based process are compared with the results from existing methods using IB-FCM and Fuzzy K-means and FCM model. Conclusion: However, an exact boundary of the region is obtained and computed an experimental dispersal of the image by Feature extraction based Fuzzy C-Means Clustering segmentation. A detection process is based on the FFCM and WOA segmentation is accomplished to discriminate the normal cyst and the kidney disease. The experimental evaluation is accomplished through the use of Ischemic kidney Disease (IKD) database.
Free
Wavelet Based Image Fusion for Detection of Brain Tumor
Scientific article
Brain tumor, is one of the major causes for the increase in mortality among children and adults. Detecting the regions of brain is the major challenge in tumor detection. In the field of medical image processing, multi sensor images are widely being used as potential sources to detect brain tumor. In this paper, a wavelet based image fusion algorithm is applied on the Magnetic Resonance (MR) images and Computed Tomography (CT) images which are used as primary sources to extract the redundant and complementary information in order to enhance the tumor detection in the resultant fused image. The main features taken into account for detection of brain tumor are location of tumor and size of the tumor, which is further optimized through fusion of images using various wavelet transforms parameters. We discuss and enforce the principle of evaluating and comparing the performance of the algorithm applied to the images with respect to various wavelets type used for the wavelet analysis. The performance efficiency of the algorithm is evaluated on the basis of PSNR values. The obtained results are compared on the basis of PSNR with gradient vector field and big bang optimization. The algorithms are analyzed in terms of performance with respect to accuracy in estimation of tumor region and computational efficiency of the algorithms.
Free
Wavelet Based Intentional Blurring Variance Scheme for Blur Detection in Barcode Images
Scientific article
Blur is an undesirable phenomenon which appears as one of the most frequent causes of image degradation. Automatic blur detection is extremely enviable to restore barcode image or simply utilize them. That is to assess whether a given image is blurred or not. To detect blur, many algorithms have been proposed. These algorithms are different in their performance, time complexity, precision, and robustness in noisy environments. In this paper, we present an efficient method blur detection in barcode images, with no reference perceptual blur metric using wavelets.
Free
Scientific article
Discrimination of protein coding regions called exons from noncoding regions called introns or junk DNA in eukaryotic cell is a computationally intensive task. But the dimension of the DNA string is huge; hence it requires large computation time. Further the DNA sequences are inherently random and have vast redundancy, hidden regularities, long repeats and complementary palindromes and therefore cannot be compressed efficiently. The objective of this study is to present an integrated signal processing algorithm that considerably reduces the computational load by compressing the DNA sequence effectively and aids the problem of searching for coding regions in DNA sequences. The presented algorithm is based on the Discrete Wavelet Transform (DWT), a very fast and effective method used for data compression and followed by comb filter for effective prediction of protein coding period-3 regions in DNA sequences. This algorithm is validated using standard dataset such as HMR195, Burset and Guigo and KEGG.
Free
Wavelet Based Some Julia Sets of Rational Maps Having Zhukovskii Function
Scientific article
The dynamics of rational maps and their properties are interesting because of the presence of poles and zeros. In this paper we have computed Julia sets of rational maps having Zhukovskii Function for which the double of the first derivative has no Herman rings. The data points out of the Julia set in Matlab workspace were imported to Matlab Signal Processing Tool for their analysis. We have sampled the data points with the sampling frequency of 8192 Hz and obtained complex signals. We have then applied the band pass filter to these complex signals. The effect of the band pass filter has generated complex analogue modulated signals.
Free
Wavelet Transform Techniques for Image Compression – An Evaluation
Scientific article
A vital problem in evaluating the picture quality of an image compression system is the difficulty in describing the amount of degradation in reconstructed image, Wavelet transforms are set of mathematical functions that have established their viability in image compression applications owing to the computational simplicity that comes in the form of filter bank implementation. The choice of wavelet family depends on the application and the content of image. Proposed work is carried out by the application of different hand designed wavelet families like Haar, Daubechies, Biorthogonal, Coiflets and Symlets etc on a variety of bench mark images. Selected benchmark images of choice are decomposed twice using appropriate family of wavelets to produce the approximation and detail coefficients. The highly accurate approximation coefficients so produced are further quantized and later Huffman encoded to eliminate the psychovisual and coding redundancies. However the less accurate detailed coefficients are neglected. In this paper the relative merits of different Wavelet transform techniques are evaluated using objective fidelity measures- PSNR and MSE, results obtained provide a basis for application developers to choose the right family of wavelet for image compression matching their application.
Free
Wavelet and Blend maps for texture synthesis
Scientific article
Blending is now a popular technology for large realtime texture synthesis .Nevertheless, creating blend map during rendering is time and computation consuming work. In this paper, we exploited a method to create a kind of blend tile which can be tile together seamlessly. Note that blend map is in fact a kind of image, which is Markov Random Field, contains multiresolution signals, while wavelet is a powerful way to process multiresolution signals, we use wavelet to process the traditional blend tile. After our processing steps, the result blend tile become smooth and suitable for tiling, with no important features lost. Using this kind blend tile, many computation resources for computing blend map during texture synthesizing is saved. The experimental results shows that our method may successfully process many traditional blend tiles.
Free
Wavelet based multimodal biometrics with score level fusion using mathematical normalization
Scientific article
Biometric based authentication is playing a very important role in various security related applications. A novel multimodal biometric verification based on fingerprint, palmprint and iris with matching score level fusion using Mathematical Normalization is proposed in this paper. In feature extraction stage of unimodal, features of each modality are extracted by applying wavelet decomposition using 6 different wavelet families and 35 respective wavelet family members. Further, the three optimal combinations of unimodal systems based on equal error rate achieved by wavelet(s) are chosen for development of multimodal biometric system. In matching score level fusion, along with well-known normalization techniques- Min-max, Tan-h and Z-score, the performance of multimodal systems are also analyzed using Mathematical Normalization (Math-norm) followed by product, weighted product, sum and average fusion rule. The experiments are conducted on database of 100 different subjects from publically available FVC2006, CASIA V1 and IITD database of fingerprint, palmprint and iris, respectively. The experimental results clearly show that Mathematical Normalization followed by weighted product has given promising accuracy with equal error rate (EER) of 0.325%.
Free
Wavelet, Gabor Filters and Co-occurrence Matrix for Palmprint Verification
Scientific article
Authentication through the palmprint is a field of biometrics. Palmprint-based personal verification has quickly entered the biometric family. It has become increasingly popular in the recent years due to its ease of acquisition, reliability and high user acceptance. In this paper, we present an authentication system based on the palmprint. We are particularly interested in the feature extraction step. Three feature extraction techniques based on the discrete wavelet transform, the Gabor filters and the co-occurrence matrix are evaluated. The support vector machine is used for the classification step. The results have been validated on the PolyU database related to 400 users. The best results have been achieved with the wavelet decomposition.
Free
Wavelet-NARM Based Sparse Representation for Bio Medical Images
Scientific article
Sparse representation based super resolution deals with the problem of reconstructing a high resolution image from one or several of its low resolution counterparts. In this case the low resolution image is modelled as the down-sampled version of its high resolution counterpart after blurring. When the blurring kernel is the Dirac delta function, i.e. the low resolution image is directly down sampled from its high resolution counterpart without blurring and the super-resolution problem becomes an image interpolation problem. In such cases, the conventional sparse representation models become less effective, because the data fidelity term fails to constrain the image local structures. In natural images, the given image patch can be modelled as the linear combination of nonlocal similar neighbours. In this paper image nonlocal self-similarity for image interpolation is introduced. More specifically, wavelet based a nonlocal autoregressive model (NARM) is proposed and taken as the data fidelity term in sparse representation model. Our experimental results on benchmark test images clearly demonstrate that the proposed wavelet-NARM based image interpolation method outperforms the reconstruction of edge structures and suppression of jaggy/ringing artefacts, achieving the best image interpolation results so far in terms of PSNR as well as perceptual quality metrics such as structural similarity index and structural content. The proposed method is applied on bio medical images to emphasis on diagnostic information.
Free
Wavelet-based Video Coding using Advanced Fractional Motion Estimation Technique
Scientific article
The purpose of this paper is to encode a color video by wavelet transformation. Therefore, we propose a new hybrid approach which combines a fractional motion estimation technique. Several studies were carried out to reduce the spatial and temporal redundancies, hence at the level of spatial video coding, we use a new approach based on sub-bands coding through a discrete wavelet transformation. This technique is based on the principle of the EZW algorithm of Shapiro. It proceeds by separating the encoding of the signs and the magnitudes of wavelet coefficients. Then, at the level of temporal compression, we propose a study of motion estimation with different accuracy based on image interpolation to improve the quality of predicted frame. Next, we present a representation reducing the size of the motion vector field and we compress it by two of entropic coding approaches namely Huffman coding and arithmetic coding. The proposed video codec was applied on a video sequence with different sizes (CIF and QCIF) and different dynamics. The obtained results, in terms of objective assessment (PSNR, the SSIM and VQM), were satisfactory compared with other video coding standards. We have also proposed a subjective evaluation and the results are compared to those obtained by H.264/AVC standard.
Free
Scientific article
Environmental pollution resulting from waste is a critical global challenge that significantly affects both the environment and public health, especially in countries like Indonesia. Effective waste management and recycling depend on accurately detecting and classifying different waste types. This study tackles this challenge by evaluating the YOLOv8s algorithm for object detection and conducting a comparative analysis of two mobile-optimized convolutional neural networks (CNNs), MobileNetV2 and EfficientNet, for waste classification. The YOLOv8s model established a promising baseline for detection, achieving a mean Average Precision (mAP@50) of 0.621 on the hold-out test set. MobileNetV2 proved to be the superior architecture in the classification task, attaining a higher accuracy of 94.4% compared to EfficientNet’s 87.8%. Additionally, MobileNetV2 demonstrated significantly greater computational efficiency, with a processing time of 229 ms per step, in contrast to EfficientNet’s 606 ms per step. These findings confirm that combining YOLOv8s for detection and MobileNetV2 for classification provides a robust and efficient pathway for developing automated waste management systems.
Free
Weighted Late Fusion based Deep Attention Neural Network for Detecting Multi-Modal Emotion
Scientific article
In the field of affective computing research, multi-modal emotion detection has gained popularity as a way to boost recognition robustness and get around the constraints of processing a multiple type of data. Human emotions are utilized for defining a variety of methodologies, including physiological indicators, facial expressions, as well as neuroimaging tactics. Here, a novel deep attention mechanism is used for detecting multi-modal emotions. Initially, the data are collected from audio and video features. For dimensionality reduction, the audio features are extracted using Constant-Q chromagram and Mel-Frequency Cepstral Coefficients (MM-FC2). After extraction, the audio generation is carried out by a Convolutional Dense Capsule Network (Conv_DCN) is used. Next is video data; the key frame extraction is carried out using Enhanced spatial-temporal and Second-Order Gaussian kernels. Here, Second-Order Gaussian kernels are a powerful tool for extracting features from video data and converting it into a format suitable for image-based analysis. Next, for video generation, DenseNet-169 is used. At last, all the extracted features are fused, and emotions are detected using a Weighted Late Fusion Deep Attention Neural Network (WLF_DAttNN). Python tool is used for implementation, and the performance measure achieved an accuracy of 97% for RAVDESS and 96% for CREMA-D dataset.
Free
