There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

A review on image segmentation techniques

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

Review: Digital image steganography: Survey and analysis of current methods

Genetic algorithm-based clustering technique

The proliferation of the digitized media (audio, image and video) introduces a challenging problem for data transmission in the network environment In this paper, a novel, simple and low cost algorithm that serves the purpose of distortion free covert image-in-image communication is proposed Its very large scale integration (VLSI) implementation using field programmable gate array (FPGA) is also developed A binary equivalent message signal is developed first from the combination of the auxiliary gray scale image information and the carrier gray scale image (original) using channel coding and spatial bi-phase modulation scheme The auxiliary image information is then decoded from the distorted/distortion free version of the original image using binary message under certain noise constraint Implementation of the proposed low cost algorithm can be speeded up significantly by hardware realization The developed hardware design allows data transmission at the rate of 4706 Mbits/s at 80 MHz clock frequency

Distortion free image-in-image communication with implementation in FPGA

Content Based Image Retrieval (CBIR) system is an emerging research area in effective digital data management and retrieval paradigm. In this article, a novel CBIR system based on a new Multiscale Geometric Analysis (MGA)-tool, called Ripplet Transform Type-I (RT) is presented. To improve the retrieval result and to reduce the computational complexity, the proposed scheme utilizes a Neural Network (NN) based classifier for image pre-classification, similarity matching using Manhattan distance measure and relevance feedback mechanism (RFM) using fuzzy entropy based feature evaluation technique. Extensive experiments were carried out to evaluate the effectiveness of the proposed technique. The performance of the proposed CBIR system is evaluated using a 2 £ 5-fold cross validation followed by a statistical analysis. The experimental results suggest that the proposed system based on RT, performs better than many existing CBIR schemes based on other transforms, and the difference is statistically significant.

/pdf/novel-cbir-system-based-on-ripplet-transform-using-2zq9zzf1db.pdf

Novel CBIR system based on Ripplet Transform using interactive Neuro-Fuzzy technique

In this paper, a novel multimodality Medical Image Fusion (MIF) method, based on Ripplet Transform Type-I (RT) using Pulse-Coupled Neural Network (PCNN) is presented. The proposed MIF scheme exploits the advantages of both RT and PCNN to obtain better results. The source medical images are first decomposed by discrete RT (DRT). The low-frequency subbands (LFSs) are fused using the ‘max selection’ rule. For the fusion of high-frequency subbands (HFSs) a PCNN model is utilized. Modified Spatial Frequency (MSF) in DRT domain is input to motivate the PCNN and coefficients in DRT domain with large firing times are selected as coefficients of the fused image. Then inverse DRT (IDRT) is applied to the fused coefficients to get the fused image. The performance of the proposed scheme is evaluated by various quantitative measures like Mutual Information (MI), Spatial Frequency (SF), and Entropy (EN) etc. Visual and quantitative analysis and comparisons show the effectiveness of the proposed scheme in fusing multimodality medical images.

Ripplet based multimodality Medical Image Fusion using Pulse-Coupled Neural Network and Modified Spatial Frequency

The paper proposes an image watermarking scheme using wavelet domain. Wavelet transform, due to its sub bands decomposition, offers better trade-off between embedding strength and robustness performance compared to other unitary transforms such as DCT, DFT, Fourier-Mellin, Walsh-Hadamard etc. Data embedding in different sub bands of the cover image offers resiliency against various types of image impairments. Degree of resiliency is increased further by embedding the same watermark information in multi-level wavelet coefficients of the cover image. Experiment results show that the scheme is resilient to various linear and non linear filtering, image sharpening, cropping, rescaling, noise addition, JPEG and JPEG 2000 compression operations etc. Compression adaptive negative modulation increases robustness against low quality compression. The proposed algorithm shows better visual as well as statistical imperceptibility and resiliency against JPEG and JPEG 2000 compression compared to two popular DCT domain algorithms and data recovery process does not require the cover image, watermarked image and/or watermark message unlike the latter two schemes.

https://www.isical.ac.in/~malay/Papers/Conf/INDICON_2004_410.pdf

Robust image watermarking using multiresolution analysis

This paper presents a robust technique for Content Based Image Retrieval (CBIR) using fuzzy edge map of an image. Fuzzy compactness vector is computed from fuzzy edge map thresholded at different levels of the unsegmented image, which also incorporates gray level contrast information embedded in the edges. The resemblance of two images is defined as the similarity between the computed feature vectors.

Malay K. Kundu

Papers

Distortion free image-in-image communication with implementation in FPGA

Novel CBIR system based on Ripplet Transform using interactive Neuro-Fuzzy technique

Ripplet based multimodality Medical Image Fusion using Pulse-Coupled Neural Network and Modified Spatial Frequency

Robust image watermarking using multiresolution analysis

Content based image retrieval with fuzzy geometrical features