International Journal of Computer and Applications

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Fast Fourier Transform

Computed tomography (CT) imaging is an essential tool in various clinical diagnoses and radiotherapy treatment planning. Since CT image intensities are directly related to positron emission tomography (PET) attenuation coefficients, they are indispensable for attenuation correction (AC) of the PET images. However, due to the relatively high dose of radiation exposure in CT scan, it is advised to limit the acquisition of CT images. In addition, in the new PET and magnetic resonance (MR) imaging scanner, only MR images are available, which are unfortunately not directly applicable to AC. These issues greatly motivate the development of methods for reliable estimate of CT image from its corresponding MR image of the same subject. In this paper, we propose a learning-based method to tackle this challenging problem. Specifically, we first partition a given MR image into a set of patches. Then, for each patch, we use the structured random forest to directly predict a CT patch as a structured output, where a new ensemble model is also used to ensure the robust prediction. Image features are innovatively crafted to achieve multi-level sensitivity, with spatial information integrated through only rigid-body alignment to help avoiding the error-prone inter-subject deformable registration. Moreover, we use an auto-context model to iteratively refine the prediction. Finally, we combine all of the predicted CT patches to obtain the final prediction for the given MR image. We demonstrate the efficacy of our method on two datasets: human brain and prostate images. Experimental results show that our method can accurately predict CT images in various scenarios, even for the images undergoing large shape variation, and also outperforms two state-of-the-art methods.

Estimating CT Image From MRI Data Using Structured Random Forest and Auto-Context Model

Nearly all nontrivial real-world systems are nonlinear dynamical systems. Chaos describes certain nonlinear dynamical systems that have a very sensitive dependence on initial conditions. Chaotic systems are always deterministic and may be very simple, yet they produce completely unpredictable and divergent behavior. Systems of nonlinear equations are difficult to solve analytically, and scientists have relied heavily on visual and qualitative approaches to discover and analyze the dynamics of nonlinearity. Indeed, few fields have drawn as heavily from visualization methods for their seminal innovations: from strange attractors, to bifurcation diagrams, to cobweb plots, to phase diagrams and embedding. Although the social sciences are increasingly studying these types of systems, seminal concepts remain murky or loosely adopted. This article has three aims. First, it argues for several visualization methods to critically analyze and understand the behavior of nonlinear dynamical systems. Second, it uses these visualizations to introduce the foundations of nonlinear dynamics, chaos, fractals, self-similarity and the limits of prediction. Finally, it presents Pynamical, an open-source Python package to easily visualize and explore nonlinear dynamical systems' behavior.

Visual Analysis of Nonlinear Dynamical Systems: Chaos, Fractals, Self-Similarity and the Limits of Prediction

Orthogonal Transforms and Wavelets can be used to extract features of a biometric in frequency domain. They also exhibit the property of energy compaction which can be used to select few coefficients as features of an image. Here we make use of a Hybrid wavelet, generated by using Kronecker product of two existing orthogonal transforms, Walsh and DCT to identify multi-spectral palmprints. A threshold energy value is chosen to select all coefficients whose total energy is above that value. One-to-many identification on a large database containing 3 sets of 6000 multi-spectral palmprint images from 500 different palms is used to validate the performance of the proposed method and matching accuracy in terms of genuine acceptance ratio of 99.979% using score level fusion has been obtained. Hence this method can significantly improve the identification rates for palmprint images.

Identification of multi-spectral palmprints using energy compaction by Hybrid wavelet

Image inpainting is a technique to recover lost data or manually remove data from an image. This process is carried out in such a way that it seems reasonable to human eyes. The lost part of the image is filled with the remaining available data of the image. Inpainting can be done using various techniques, mainly variation based, exemplar based and wavelet based. In this paper, exemplar based image inpainting techniques is used and an algorithm which improves and extends the previously proposed algorithm is presented. Instead of searching the entire image, the proposed approach has reduced the search region by searching the nearby pixels since most of the relevant information lies in neighbouring pixels which reduces time to complete inpainting. This technique is mainly used for removing objects and cracks from the image. General Terms Image processing, Inpainting, Object removal.

/pdf/exemplar-based-image-inpainting-with-reduced-search-region-2trg8h6rjs.pdf

Exemplar based Image Inpainting with Reduced Search Region

This paper aims to provide different approaches to text dependent speaker identification using various transformation techniques such as DCT, Walsh and Haar transform along with use of spectrograms. Set of spectrograms obtained from speech samples is used as image database for the study undertaken. This image database is then subjected to various transforms. Using Euclidean distance as measure of similarity, most appropriate speaker match is obtained which is declared to be identified speaker. Each transform is applied to spectrograms in two different ways: on full image and on Row Mean of an image. In both the ways, effect of different number of coefficients of transformed image is observed. Further, comparison of all three transformation techniques on spectrograms in both the ways shows that numbers of mathematical computations required for Walsh transform is much lesser than number of mathematical computations required in case of DCT on spectrograms. Whereas, use of Haar transform on spectrograms drastically reduces the number of mathematical computation with almost equal identification rate. Transformation techniques on Row Mean give better identification rate than transformation technique on full image.

/pdf/performance-comparison-of-speaker-identification-using-dct-ulind9ebg6.pdf

Performance Comparison of Speaker Identification Using DCT, Walsh, Haar on Full and Row Mean of Spectrogram

This paper presents a technique of digital image watermarking using DCT wavelet transform. Use of Haar wavelet is very common in watermarking. However, here DCT wavelet transform of size 256*256 is generated using existing well known orthogonal transform DCT of dimension 128*128 and 2*2. This DCT Wavelet transform is used in combination with the orthogonal transform DCT and SVD to increase the robustness of watermarking. HL2 sub-band is selected for watermark embedding. Performance of the proposed watermarking scheme is evaluated against various image processing attacks like contrast stretching, image cropping, resizing, histogram equalization and Gaussian noise. DCT wavelet transform performs better than our previously proposed DWT-DCT-SVD based watermarking scheme wherein Haar functions are used as basis functions for wavelet transform.

Hybrid watermarking of color images using dct- wavelet, dct and svd

Using biometrics to verify a person’s identity has several advantages over the present practices of personal identification numbers (PINs) and passwords. Minutiae-based automated fingerprint identification systems are more popular, but they are more computationally complex and time consuming. In this paper we propose a simple yet effective technique for fingerprint identification. This method is image-based in which feature vectors of a fingerprint are extracted after sectorization of the cepstrum of a fingerprint. They are matched with those stored in the database. The experimental results show that this algorithm could correctly identify fingerprints with accuracy more than 96% in case of larger number of sectors.

/pdf/fingerprint-identification-using-sectorized-cepstrum-complex-5cnsaa11ao.pdf

Tanuja Sarode

Papers

Identification of multi-spectral palmprints using energy compaction by Hybrid wavelet

Exemplar based Image Inpainting with Reduced Search Region

Performance Comparison of Speaker Identification Using DCT, Walsh, Haar on Full and Row Mean of Spectrogram

Hybrid watermarking of color images using dct- wavelet, dct and svd

Fingerprint Identification using Sectorized Cepstrum Complex Plane