Hypercomplex Fourier Transform Research Articles

An improved saliency detection method based on hypercomplex Fourier transform

Saliency detection is a challenging direction in the field of computer vision. It can help us quickly obtain important information of image and video, and plays an important role in image compression, image segmentation, target recognition and other applications. Based on the Hypercomplex Fourier Transform (HFT) model, median filter and threshold segmentation are employed to obtain the image salient region, which solves the problem that the boundary is not clear and multiple targets cannot be separated, and achieves more accurate and stable detection effect.

Saliency Detection by Adaptive Channel Fusion

Saliency detection has received tremendous attention from the research community and has become an increasingly important preprocessing tool in many computer vision tasks, such as object recognition. Saliency detection in the frequency domain possesses great advantages compared with that in the spatial domain due to its computational efficiency and succinct model design. Many excellent frequency domain based models, such as SR, phase spectrum of quaternion Fourier transform, hypercomplex Fourier transform (HFT), have made great progress in predicting human eye fixations. However, there still exists a vital drawback among them—ignoring the different contributions of image channels to saliency detection. In our observation, chrominance component of an image may play an unequally important role as luminance component in different situations. In this letter, we propose a frequency domain based framework, which exploits HFT -based saliency algorithm and finds a way to weigh the importance of different channels in saliency detection across space. In the first step, saliency maps corresponding to different channels are generated independently. In the second step, a combination of both saliency maps is performed using an adaptive entropy-based uncertainty weighting approach. We provide an extensive evaluation and show that our proposed method outperforms nine outstanding eye fixation prediction models on four most commonly-used datasets.

On Detectors and Descriptors based Techniques for Face Recognition

Out of all forms of biometrics, Face Recognition (FR) emerges as the most incredible one. Apart from offering revolutionary applications for business and law-enforcement purposes, it has also opened numerous research avenues in various domains like security, surveillance and social network. One of the many factors critical to having an efficient face recognition system is having at hand, a suitable combination of feature descriptor and feature detector. A feature detector makes use of methods that make local decisions regarding the presence/absence of image features of a given type. A feature descriptor, on the other hand, simplifies the image by extracting useful information and disposing irrelevant information. Our research discusses the goodness of various feature descriptor-detector combination. We do this by simply carrying out the process of feature matching using various combinations of detectors and descriptors. This experiment includes incorporation of dimensionality reduction on the images using Hypercomplex Fourier Transform (HFT) and RANSAC for noise reduction. Out of the diverse options available, we chose to test LGHD, PCEHD and EHD for feature descriptors; for feature detectors, we chose the ones that make use of popular algorithms like Harris-Stephen Algorithm, Minimum Eigen Value and SURF. A series of strict and thorough experiments on popularly available datasets - Faces94 and Grimace led us to an astonishing observation - an accuracy of 90.67% for the former and 71.3% for the latter for Minimum Eigen Value paired with LGHD! This in comparison to those for all other combinations is a lot superior. We thereby conclusively state that feature detector using Minimum Eigen Value algorithm paired with feature descriptor - LGHD outplays other combinations making this combination the best choice for Face Recognition.

Copyright protection for elemental image array by hypercomplex Fourier transform and an adaptive texturized holographic algorithm.

In practical applications of three-dimensional integral imaging, the captured elemental image array (EIA) needs to be stored and delivered through the Internet. Therefore, there is an urgent need for protecting the copyright of EIA against piracy and malicious manipulation. In our work, we propose a copyright protection algorithm for EIA by combining the use of the modified hypercomplex Fourier transform (HFT) and the adaptive texturized holographic algorithm. The modified HFT can accurately extract the features from each elemental image. According to these features, we embed watermark into the visually less noticeable regions of the EIA to increase the visual perception. In addition, an adaptive texturized holographic algorithm is proposed to increase the robustness. Finally, the analytical performances are contrasted with simulation results where the imperceptibility and robustness of the proposed method are evaluated against standard attacks.

Visual saliency based on frequency domain analysis and spatial information

Saliency detection plays an important role in computer vision field. In this paper, a saliency detection model for images is proposed based on frequency domain analysis and spatial information. Saliency is detected in the proposed model via the following main steps: coefficients of the input hyper complex image are designed in Hyper Complex Fourier Transform (HFT); then, during the analysis of the spectrum scale space in frequency domain, a series of saliency maps at different scales are obtained; finally, considering spatial relationship, the spatial contrast function is taken for selecting the optimal saliency map. Experimental results show that the proposed model can achieve high performance in terms of the average AUC and F-measure evaluation metrics and outperform state-of-the-art baselines.

A novel combination of second-order statistical features and segmentation using multi-layer superpixels for salient object detection

Salient object detection is one of the outstanding capabilities of the human visual system (HVS). The researcher community aims at developing a salient object detection model that matches the detection accuracy as well as computation time taken by the humans. These models can be developed in either spatial domain or frequency domain. Spatial domain models provide good detection accuracy at the cost of high computational time while frequency domain models offer fast computational speed to meet real-time requirements at the cost of poor detection accuracy. In order to induce a trade-off between computational time and accuracy, we propose a model which provides high detection accuracy without taking much of computation time. To detect the salient object with an accurate shape, we first segment the given image by utilizing a bipartite graph partitioning approach which aggregates multi-layer superpixels in a principled and effective manner. Second, the saliency of each segmented region is computed based on a hypercomplex Fourier transform (HFT) saliency map reconstructed using amplitude spectrum, filtered at an appropriate scale chosen using statistical features extracted from grey- level co-occurrence matrix and original phase spectrum. Finally, a saliency map is generated by taking average of the HFT coefficients of each region in the segmented image and then using the average HFT intensity value of the entire image as a threshold to clearly separate salient object from the background. The performance of the proposed model is evaluated in terms of F---measure, area under curve (AUC), and computation time using six publicly available image datasets. Both qualitative and quantitative evaluations on six publicly available datasets demonstrate the robustness and efficiency of the proposed model against twenty popular state-of-the-art methods.

Scale Space Reduction with Interpolation to Speed up Visual Saliency Detection

The scale of salient object in an image is not a known priori, therefore to detect salient objects accurately multiple scale analysis is used by saliency detection models. However, multiple scale analysis makes the saliency detection slow. Fast and accurate saliency detection is essential to obtain Region of Interest in image processing applications. This paper proposes a scale space reduction with interpolation to speed up the saliency detection. To demonstrate the concept, this method is integrated with Hypercomplex Fourier Transform saliency detection which reduced the computational complexity from O(N) to O(N/2).

Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of nonsaliency. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space analysis of the amplitude spectrum of natural images. We show that the convolution of the image amplitude spectrum with a low-pass Gaussian kernel of an appropriate scale is equivalent to an image saliency detector. The saliency map is obtained by reconstructing the 2D signal using the original phase and the amplitude spectrum, filtered at a scale selected by minimizing saliency map entropy. A Hypercomplex Fourier Transform performs the analysis in the frequency domain. Using available databases, we demonstrate experimentally that the proposed model can predict human fixation data. We also introduce a new image database and use it to show that the saliency detector can highlight both small and large salient regions, as well as inhibit repeated distractors in cluttered images. In addition, we show that it is able to predict salient regions on which people focus their attention.