Narrow Results

A biologically inspired image fusion mechanism is analyzed in this paper. A pseudo-color image fusion method is proposed based on the improvement of a traditional method. The proposed model describes the fusion process using several abstract definitions which correspond to the detailed behaviors of neurons. Firstly, the infrared image and visible image are respectively ON against enhanced and OFF against enhanced. Secondly, we feed back the enhanced visible images given by the ON-antagonism system to the active cells in the center-surrounding antagonism receptive field. The fused $+$VIS$+$IR signal are obtained by feeding back the OFF-enhanced infrared image to the corresponding surrounding-depressing neurons. Then we feed back the enhanced visible signal from OFF-antagonism system to the depressing cells in the center-surrounding antagonism receptive field. The ON-enhanced infrared image is taken as the input signal of the corresponding active cells in the neurons, then the cell response of infrared-enhance-visible is produced in the process, it is denoted as $+$IR$+$VIS. The three kinds of signal are considered as R, G and B components in the output composite image. Finally, some experiments are performed in order to evaluate the performance of the proposed method. The information entropy, average gradient and objective image fusion measure are used to assess the performance of the proposed method objectively. Some traditional digital signal processing-based fusion methods are also evaluated for comparison in the experiments. In this paper, the Quantitative assessment indices show that the proposed fusion model is superior to the classical Waxman’s model, and some of its performance is better than the other image fusion methods.

At present, some achievements have been made in the research of plant leaf classification such as the introduction of artificial intelligence algorithm. But there are still some problems. First, the existing achievements do not consider the subjective perception mechanism and role of human visual system in leaf classification data labels. Second, the implementation of the deep learning algorithm completely depends on the computing power level of the high-cost machine hardware and the large-scale image database. Finally, these research results rarely consider the noise pollution of leaf image samples. In order to solve the above problems, the paper fully considered the subjective perception principle and characteristics of human vision system (HVS), and proposed a lightweight classification method of noisy plant leaves (LCM-NPLs) based on visual domain perception. First, the most suitable HVS front-end perception characteristics were applied to the physical visual processing of leaves. Then the plant leaves were denoised through the information processing mechanism of HVS back-end. The visual effect of regular and orderly plant leaves is obtained. Finally, the classification is realized by principal component analysis (PCA) and third-order nearest neighbor algorithm. The results of ablation contrast experiments show that the classification accuracy of the method in this paper is 82.50% for plant leaves in the presence of serious noise interference with PSNR of 10.2421, more than 90% for plant leaves with general noise pollution transmission with PSNR of more than 15.3759, and 98.33% for plant leaves of light pollution with PSNR of 20.5659. The proposed method has achieved very good results. The proposed method can not only accurately classify plant leaves in different growth periods, but also maintain a high classification accuracy rate in the presence of serious noise interference.

Many different techniques for visualizing data exist, and often users must experiment with several before selecting the most effective one for their problem. Knowledge of the characteristics of the human visual system can assist in our choice of visualization techniques. Limits imposed by our visual "cognitive bandwidth" mean that only detail up to these limits needs to be generated in a visualization scene. Some aspects of our visual process will be discussed and an approach will be described for modeling scene detail, which takes visual limits of such aspects into account.

The human vision system is a very sophisticated image processing and objects recognition mechanism. However, it is a challenge to simulate the human or animal vision system to automate visual function in machines, because it is difficult to account for the view-invariant perception of universals such as environmental objects or processes and the explicit perception of featural parts and wholes in visual scenes. In this paper, we first present an introduction to the importance of biologically inspired computer vision and review general and key vision functions from neuroscience perspective. And most significantly, we give an important summarization to and discussion on the specific applications of biologically inspired modeling, including biologically inspired image pre-processing, image perception, and objects recognition. In the end, we give some important and challenging topics of computer vision for future work.

In this paper, we present a novel adaptive thresholding-based color reduction algorithm. The proposed algorithm supports creation of a common palette for multiple images and transparent alpha images. This method was extensively tested for a large set of images and the results are reported here. The applications of proposed algorithm like qualitative image description, digital broadcasting, and bandwidth reduction are discussed in detail. The quality metric values of the experimental results show that the proposed method produces excellent results and outperforms existing state-of-the-art color reduction methods.

As the performance indicator of the image processing algorithms or systems, image quality assessment (IQA) has attracted the attention of many researchers. Aiming to the widely used compression standards, JPEG and JPEG2000, we propose a new no reference (NR) metric for compressed images to do IQA. This metric exploits the causes of distortion by JPEG and JPEG2000, employs the directional discrete cosine transform (DDCT) to obtain the detail and directional information of the images and incorporates with the visual perception to obtain the image quality index. Experimental results show that the proposed metric not only has outstanding performance on JPEG and JPEG2000 images, but also applicable to other types of artifacts.

Semantic scene understanding is one of the several significant goals of robotics. In this paper, we propose a framework that is able to construct geometric invariants for simultaneous object detection and segmentation using a simple pairwise interactive context term, for the sake of achieving a preliminary milestone of Semantic scene understanding. The context is incorporated as pairwise interactions between pixels, imposing a prior on the labeling. Our model formulates the multi-class image segmentation task as an energy minimization problem and finds a globally optimal solution using belief propagation and neural network. We experimentally evaluate the proposed method on three publicly available datasets: the MSRC-1, the CorelB datasets, and the PASCAL VOC database. Results show the applicability and efficacy of the proposed method to the multi-class segmentation problem.

Reversible watermarking methods are used for copyright protection and are able to recover the host image without distortion. Robust reversible watermarking technique should resist against intentional and unintentional image processing attacks. Robust reversible watermarking techniques should have three features namely imperceptibility, reversibility and robustness. In this paper, it is proposed to develop a new robust reversible blind watermarking for color images based on histogram construction of the wavelet coefficients constructed from the cover image. In the proposed approach, the red component of a host color image is decomposed into wavelet coefficients. Motivated by the excellent spatio-frequency localization properties of wavelets, this technique is proposed in the wavelet domain. The pixels are adjusted before watermark embedding such that both overflow and underflow of pixels during embedding is avoided and image is recovered without distortion. Based on histogram construction and the local sensitivity of Human Visual System (HVS) in wavelet domain, the watermark is embedded. For watermark extraction without host image, k-means clustering algorithm is proposed. The experimental results show that the proposed technique has good performance in terms of reversibility and robustness with the high quality of the watermarked image. The PSNR value of the recovered image is around 48dB which proves that the quality of the recovered image is not degraded.

Image quality is a key characteristic in image processing,^10,11 image retrieval,^12,13 and biometrics.¹⁴ In this paper, a novel reduced-reference image quality assessment method is proposed based on wavelet transform. By simulating the human visual system, we take the variance of the visual sensitive coefficients into account to measure a distorted image. The computational complexity of the proposed method is much lower compared with some existing methods. Experimental results demonstrate its advantages in terms of correlation coefficient, outlier ratio, transmitted information, and CPU cost. Moreover, it is also illustrated that the proposed method has a good accordance with human subjective perception.

A wavelet-based perceptual image coder for the compression of color images is proposed here in which the coding structure is coupled with Human Visual System models to produce high quality images. The major contribution is the development of a new model for the compression of the color components based on psychovisual experiments, which quantifies the optimum amount of compression that can be applied to the color components for a given rate. The model is developed for YCbCr color space and the perceptually uniform CIE Lab color space. A complete coding structure for the compression of color images is developed by incorporating the new perceptual model. The performance of the proposed coder is compared with a wavelet-based coder that uses the quantization stage of the JPEG2000 standard. The perceptual quality of the compressed images is tested using the wavelet-based subjective and objective perceptual quality matrices such as Mean Opinion Score, Visual Information Fidelity and Visual Signal to Noise Ratio. Though the model is developed for a perceptually lossless high quality image compression, results obtained reveal that the proposed structure gives very good perceptual quality compared to the existing schemes for lower bit rates. These advantages make the proposed coder a candidate for replacing the encoder stage of the current image compression standards.

Considering that the Human Visual System (HVS) has different perceptual characteristics for different morphological components, a novel image quality metric is proposed by incorporating Morphological Component Analysis (MCA) and HVS, which is capable of assessing the image with different kinds of distortion. Firstly, reference and distorted images are decomposed into linearly combined texture and cartoon components by MCA respectively. Then these components are turned into perceptual features by Just Noticeable Difference (JND) which integrates masking features, luminance adaptation and Contrast Sensitive Function (CSF). Finally, the discrimination between reference and distorted images perceptual features is quantified using a pooling strategy before the final image quality is obtained. Experimental results demonstrate that the performance of the proposed prevails over some existing methods on LIVE database II.

In this paper, a novel image fusion algorithm based on framelet transform is presented. The core idea is to decompose all the images to be fused into low and high-frequency bands using framelet transform. For fusion, two different selection strategies are developed and used for low and high-frequency bands. The first strategy is adaptive weighted average based on local energy and is applied to fuse the low-frequency bands. In order to fuse high-frequency bands, a new strategy is developed based on texture while exploiting the human visual system characteristics, which can preserve more details in source images and further improve the quality of fused image. Experimental results demonstrate the efficiency and better performance than existing image fusion methods both in visual inspection and objective evaluation criteria.

Information distortion in regions of image edge is more perceptible for people than those in other regions. To improve the performance on the edge, we present an improved embedded zero-tree wavelet image compression algorithm with weighted sub-block-trees and adaptive coding order. First, we assign bigger weights to the sub-block-trees around image edge. The weights assigned to the sub-blocks in the same spatial location and the same orientation at different scales are equal so that the zero-tree structure of wavelet coefficients is maintained and only a little extra storage is needed. Then we prefer scanning the coefficients on the neighbor of previous significant coefficients and all of them are refined even they are not significant. Adaptive arithmetic coding is applied to the symbols of these coefficients and others respectively. The proposed method pays more attention to the edge and its neighborhood so that the decoded image on the edge is clearer. Compared with similar algorithms, experimental results show that the proposed method can improve the PSNR and SSIM, as well as the subjective visual experience. The proposed method is applicable to any genre of embedded wavelet image codec.

In this paper, we develop a new approach to mammographic image enhancement and denoising based on redundant wavelet transform. The first part deals with the method of mammographic enhancement. Firstly, we enhance the image using a fast and effective enhancement method by the local standard deviation values, and stretch/compress factitiously the gray interval between neighbor pixel for different gray value according to the human visual curve in Figure 1 considering the character of the human visual system, so as to distribute the redundant gray of some gray value to eye to the wanting fields. The method boosts up the local regions to different degrees rationally. The second part deals with the multiscale image processing for image denosing. The image is decomposed into several subbands by redundant wavelet transform, and then is reconstructed by different weights.

Many different techniques for visualizing data exist, and often users must experiment with several before selecting the most effective one for their problem. Knowledge of the characteristics of the human visual system can assist in our choice of visualization techniques. Limits imposed by our visual “cognitive bandwidth” mean that only detail up to these limits needs to be generated in a visualization scene. Some aspects of our visual process will be discussed and an approach will be described for modeling scene detail, which takes visual limits of such aspects into account.

The fidelity and robustness are two conflicts in digital image watermarking scheme. How to solve their conflicts is an important aspect in digital image watermarking research. Human visual system(HVS) based image watermarking scheme is an appropriate way to solve this problem. However, the way that set several thresholds for classification in the past papers is not accurate enough in simulating human visual system. In this paper, support vector machine is used to simulating human visual system accurately and classify image locations into several types that be determined by human visual system. Besides, the JEPG quantization table is also used to quantize embedding strength for gaining good fidelity in our scheme. The experimental results show that the algorithm this paper proposed has good fidelity and strong robustness.