A genetic programming-based convolutional neural network for image quality evaluations

Neural Computing and Applications - Monitoring the perceptual quality of digital images is fundamentally important since digital image transmissions through the Internet continue to increase...     

Quantum convolutional neural network for image classification

Pattern Analysis and Applications - In this paper we propose two scale-inspired local feature extraction methods based on Quantum Convolutional Neural Network (QCNN) in the Tensorflow quantum...     

A dyadic multi-resolution deep convolutional neural wavelet network for image classification

For almost the past four decades, image classification has gained a lot of attention in the field of pattern recognition due to its application in various fields. Given its importance, several approaches have been proposed up to now. In this paper, we will present a dyadic multi-resolution deep convolutional neural wavelets’ network approach for image classification. This approach consists of performing the classification of one class versus all the other classes of the dataset by the reconstruction of a Deep Convolutional Neural Wavelet Network (DCNWN). This network is based on the Neural Network (NN) architecture, the Fast Wavelet Transform (FWT) and the Adaboost algorithm. It consists, first, of extracting features using the FWT based on the Multi-Resolution Analysis (MRA). These features are used to calculate the inputs of the hidden layer. Second, those inputs are filtered by using the Adaboost algorithm to select the best ones corresponding to each image. Third, we create an AutoEncoder (AE) using wavelet networks of all images. Finally, we apply a pooling for each hidden layer of the wavelet network to obtain a DCNWN that permits the classification of one class and rejects all other classes of the dataset. Classification rates given by our approach show a clear improvement compared to those cited in this article.

     

A brain-like neural network for periodicity analysis.

This paper introduces a brain-like neural model for sound processing. The periodicity analyzing network (PAN) is a bio-inspired neural network of spiking neurons. The PAN consists of complex models of neurons, which can be used for understanding the dynamics of individual neurons and neuronal networks. On a technical level, the PAN is able to compute the ratio of modulation and carrier frequency of harmonic sound signals. The PAN model may, therefore, be used in audio signal processing applications, such as sound source separation, periodicity analysis, and the cocktail party problem.     

Bi-branch deconvolution-based convolutional neural network for image classification

With the rise of deep neural network, convolutional neural networks show superior performances on many different computer vision recognition tasks. The convolution is used as one of the most efficient ways for extracting the details features of an image, while the deconvolution is mostly used for semantic segmentation and significance detection to obtain the contour information of the image and rarely used for image classification. In this paper, we propose a novel network named bi-branch deconvolution-based convolutional neural network (BB-deconvNet), which is constructed by mainly stacking a proposed simple module named Zoom. The Zoom module has two branches to extract multi-scale features from the same feature map. Especially, the deconvolution is borrowed to one of the branches, which can provide distinct features differently from regular convolution through the zoom of learned feature maps. To verify the effectiveness of the proposed network, we conduct several experiments on three object classification benchmarks (CIFAR-10, CIFAR-100, SVHN). The BB-deconvNet shows encouraging performances compared with other state-of-the-art deep CNNs.     

A neural network-based novelty detector for image sequence analysis

This paper proposes a new model of "novelty detection” for image sequence analysis using neural networks. This model uses the concept of artificially generated negative data to form closed decision boundaries using a multilayer perceptron. The neural network output is novelty filtered by thresholding the output of multiple networks (one per known class) to which the sample is input and clustered for determining which clusters represent novel classes. After labeling these novel clusters, new networks are trained on this data. We perform experiments with video-based image sequence data containing a number of novel classes. The performance of the novelty filter is evaluated using two performance metrics and we compare our proposed model on the basis of these with five baseline novelty detectors. We also discuss the results of retraining each model after novelty detection. On the basis of Chi-square performance metric, we prove at 5 percent significance level that our optimized novelty detector performs at the same level as an ideal novelty detector that does not make any mistakes.     

A robust hybrid method for image encryption based on Hopfield neural network

In this paper, a robust hybrid image encryption algorithm with permutation-diffusion structure is proposed, based on chaotic control parameters and hyper-chaotic system. In the proposed method, a chaotic logistic map is employed to generate the control parameters for the permutation stage which results in shuffling the image rows and columns to disturb the high correlation among pixels. Next, in the diffusion stage, another chaotic logistic map with different initial conditions and parameters is employed to generate the initial conditions for a hyper-chaotic Hopfield neural network to generate a keystream for image homogenization of the shuffled image. The new hybrid method has been compared with several existing methods and shows comparable or superior robustness to blind decryption.     

Three-dimensional medical image analysis of the heart by the revised GMDH-type neural network self-selecting optimum neural network architecture

In this study, a revised group method of data handling (GMDH)-type neural network algorithm which self-selects the optimum neural network architecture is applied to 3-dimensional medical image analysis of the heart. The GMDH-type neural network can automatically organize the neural network architecture by using the heuristic self-organization method, which is the basic theory of the GMDH algorism. The heuristic self-organization method is a kind of evolutionary computation method. In this revised GMDH-type neural network algorithm, the optimum neural network architecture was automatically organized using the polynomial and sigmoid function neurons. Furthermore, the structural parameters, such as the number of layers, the number of neurons in the hidden layers, and the useful input variables, are selected automatically in order to minimize the prediction error criterion, defined as the prediction sum of squares (PSS).     

Strategies and best practice for neural network image classification

This paper examines a number of experimental investigations of neural networks used for the classification of remotely sensed satellite imagery at the Joint Research Centre over a period of five years, and attempts to draw some conclusions about 'best practice' techniques to optimize network training and overall classification performance. The paper examines best practice in such areas as: network architecture selection; use of optimization algorithms; scaling of input data; avoidance of chaos effects; use of enhanced feature sets; and use of hybrid classifier methods. It concludes that a vast body of accumulated experience is now available, and that neural networks can be used reliably and with much confidence for routine operational requirements in remote sensing.     

BP神经网络在图像边缘检测中的应用

为实现数字图像边缘的有效检测与提取,借助BP神经网络,采用了改进的最速梯度下降法,通过对动量项的合理选择,有效地实现算法的快速收敛。为提高算法的执行效率,采用直接编程和对图像采用分块的思想,并给出了算法实现的方法和步骤。用Matlab软件对灰度图像进行了仿真,并将仿真结果和传统的方法进行了比较,结果表明,所设计的网络边缘检测优于传统方法,并具有较好的泛化能力。     

Artificial neural network visual model for image quality enhancement

An artificial neural network visual model is developed, which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate for the coding distortions. This provides a generic postprocessing technique that can be applied to all the main coding methods. Experimental results involving postprocessing of the JPEG and quadtree coding systems show that the proposed artificial neural network visual model significantly enhances the quality of reconstructed images, both in terms of the objective peak signal-to-noise ratio and subjective visual assessment.     

An improved pulse coupled neural network for image processing

To develop new image processing applications for pulse coupled neural network (PCNN), this paper proposes an improved PCNN model by redesigning the linking input, activity strength, linking weight, pulse threshold and pixel update rule. Two typical image processing examples based on such a model, namely fingerprint orientation field estimation and noise removal, are presented for explaining how to use the PCNN and determine parameters in image processing. Experiments show that the improved model is quite useful, and the PCNN-based approaches achieve better image processing results than the traditional ones. This work was supported by National Science Foundation of China under Grant 60471055 and Specialized Research Fund for the Doctoral Program of Higher Education under Grant 20040614017.     

Skip-connection convolutional neural network for still image crowd counting

In recent years, crowd counting in still images has attracted many research interests due to its applications in public safety. However, it remains a challenging task for reasons of perspective and scale variations. In this paper, we propose an effective Skip-connection Convolutional Neural Network (SCNN) for crowd counting to overcome the issue of scale variations. The proposed SCNN architecture consists of several multi-scale units to extract multi-scale features. Each multi-scale unit including three convolutional layers builds connections between the input and each convolutional layer. In addition, we propose a scale-related training method to improve the accuracy and robustness of crowd counting. We evaluate our method on three crowd counting benchmarks. Experimental results verify the efficiency of the proposed method, and it achieves superior performance compared with other methods.     

Memristive continuous Hopfield neural network circuit for image restoration

Neural Computing and Applications - Image restoration (IR) methods based on neural network algorithms have shown great success. However, the hardware circuits that can perform real-time IR task...     

A board system for high-speed image analysis and neural networks

Two ANNA neural-network chips are integrated on a 6U VME board, to serve as a high-speed platform for a wide variety of algorithms used in neural-network applications as well as in image analysis. The system can implement neural networks of variable sizes and architectures, but can also be used for filtering and feature extraction tasks that are based on convolutions. The board contains a controller implemented with field programmable gate arrays (FPGA's), memory, and bus interfaces, all designed to support the high compute power of the ANNA chips. This new system is designed for maximum speed and is roughly 10 times faster than a previous board. The system has been tested for such tasks as text location, character recognition, and noise removal as well as for emulating cellular neural networks (CNN's). A sustained speed of up to two billion connections per second (GC/s) and a recognition speed of 1000 characters per second has been measured.     

A neural network construction algorithm with application to image compression

We propose an algorithm for constructing a feedforward neural network with a single hidden layer. This algorithm is applied to image compression and it is shown to give satisfactory results. The neural network construction algorithm begins with a simple network topology containing a single unit in the hidden layer. An optimal set of weights for this network is obtained by applying a variant of the quasi-Newton method for unconstrained optimisation. If this set of weights does not give a network with the desired accuracy then one more unit is added to the hidden layer and the network is retrained. This process is repeated until the desired network is obtained. We show that each addition of the hidden unit to the network is guaranteed to increase the signal to noise ratio of the compressed image.     

A region-based multi-sensor image fusion scheme using pulse-coupled neural network

For most image fusion algorithms split relationship among pixels and treat them more or less independently, this paper proposes a region-based image fusion scheme using pulse-coupled neural network (PCNN), which combines aspects of feature and pixel-level fusion. The basic idea is to segment all different input images by PCNN and to use this segmentation to guide the fusion process. In order to determine PCNN parameters adaptively, this paper brings forward an adaptive segmentation algorithm based on a modified PCNN with the multi-thresholds determined by a novel water region area method. Experimental results demonstrate that the proposed fusion scheme has extensive application scope and it outperforms the multi-scale decomposition based fusion approaches, both in visual effect and objective evaluation criteria, particularly when there is movement in the objects or mis-registration of the source images.     

Improving the performance of convolutional neural network for skin image classification using the response of image analysis filters

Neural Computing and Applications - In this work, we focus in the analysis of dermoscopy images using convolutional neural networks (CNNs). More specifically, we investigate the value of augmenting...