Object-oriented image analysis for very-low-bitrate video-coding systems using the CNN universal machine

The CNN universal machine (CNNUM) is applied to object-oriented video compression and proves its universality for future applications in the field of very-low-bitrate coding. This proposal joins recent work of Venetianer and Roska in unfolding the enormous computational abilities of the CNNUM for a wide class of video compression techniques. Here a novel image analysis technique is considered and realized in the form of analogic CNN algorithms. The specific features of the scheme, among them the extensive use of dynamic (finite running time) CNN cloning templates, are outlined and discussed through different computer simulations. When implemented on the CNNUM, its performances outdo those of equivalent digital systems and qualify the CNNUM as a serious competitor for future video coding hardware. © 1997 John Wiley & Sons, Ltd.     

Automatic detection and tracking of moving image target with CNN‐UM via target probability fusion of multiple features

A high speed target detection and tracking algorithm for a CNN‐UM chip is presented in this paper. The target confidence value is computed based on the fusion of target existence probabilities of features using products of weighted sums. The target decision is done with such a confidence value and target initiation is done through the temporal accumulation of the confidence. The probability of the target existence for each feature is created in the region of influence depending on the reliability and the strength of the feature. By virtue of the analogic parallel processing structure of the CNN‐UM (Roska T, Chua LO. The CNN universal machine: an analogic array computer. IEEE Trans. Circuits Systems II 1993; CAS‐40 : 163–173), real time tracking can be achieved with presently available technologies with the speed of several kilo‐frames per second. Due to the utilization of multiple features of target, robust target detection is possible via the proposed algorithm. On‐chip experiments of the proposed target‐tracking algorithm have been done and properties of the proposed approach are disclosed through the various experiments. Copyright © 2003 John Wiley & Sons, Ltd.     

DYNAMIC ANALOGIC CNN ALGORITHMS FOR A COMPLEX RECOGNITION TASK—A FIRST STEP TOWARDS A BIONIC EYEGLASS

Complex, dynamic, analogic CNN algorithms are presented for detecting some objects and features in a natural scene. Though the problem is well defined, the variations in the arrangements of features and objects and the illumination cause significant problems. The task is to find doors, door-handles, signs, etc. in a given floor of a house. The solution is a first step towards making a bionic CNN eyeglass.     

Cellular neural networks for real-time DNA microarray analysis

A new methodology for real-time processing of DNA chip images is proposed. The idea developed here is to use the cellular neural network (CNN) array to analyze the DNA microarray. A CNN is an analog dynamic processor array that reflects this property: the processing elements interact directly within a finite local neighborhood. Due to its architecture, a two-dimensional CNN array is widely used to solve image processing and pattern recognition problems; moreover, the parallelism characteristic of this structure allows one to perform the most computationally expensive image analysis tasks three orders of magnitude faster than a classical CPU-based computer. This approach, thanks to the supercomputing capabilities of the CNN architecture, makes the whole DNA chip methodology fully parallel and also makes the processing phase, until now very time consuming, a real-time step. We discuss the results of testing an algorithm based on the CNN universal machine (CNN-UM) that has been designed to classify the image data. The algorithm is implemented in an analogic (analog and logic) microprocessor.     

Spatial logic algorithms using basic morphological analogic CNN operations

The CNN implementation of basic scale-, rotation- and translation-invariant morphological functions and novel types of analogic CNN algorithms using spatial logic are introduced for object recognition (detection) purposes. The power of the technique is illustrated on bank-note recognition tasks.     

The network behind spatio‐temporal patterns: building low‐complexity retinal models in CNN based on morphology,pharmacology and physiology

In this paper, a vertebrate retina model is described based on a cellular neural network (CNN) architecture. Though largely built on the experience of previous studies, the CNN computational framework is considerably simplified: first‐order RC cells are used with space‐invariant nearest‐neighbour interactions only. All non‐linear synaptic connections are monotonic continuous functions of the pre‐synaptic voltage. Time delays in the interactions are continuous represented by additional first‐order cells. The modelling approach is neuromorphic in its spirit relying on both morphological and pharmacological information. However, the primary motivation lies in fitting the spatio‐temporal output of the model to the data recorded from biological cells (tiger salamander). In order to meet a low‐complexity (VLSI) implementation framework some structural simplifications have been made. Large‐neighbourhood interaction (neurons with large processes), furthermore inter‐layer signal propagation are modelled through diffusion and wave phenomena. This work presents novel CNN models for the outer and some partial models for the inner (light adapted) retina. It describes an approach that focuses on efficient parameter tuning and also makes it possible to discuss adaptation, sensitivity and robustness issues on retinal ‘image processing’ from an engineering point of view. Copyright © 2001 John Wiley & Sons, Ltd.     

Application of a cellular neural network to facial expression animation and high-level image processing

The cellular neural network (CNN) is used to animate facial expressions of a human being. First, the change in facial expressions is regarded as a smooth 2D transformation which is restricted by a bending energy function and displacements of some key-points. Second, the parameters of the CNN are determined by comparing the bending energy function with the energy function of the CNN. Finally, the CNN is used to realize the transformation by minimizing its energy function. Also, the CNN is used to model some visual illusions which are frequently used in psychological tests. First, the retinal induction field is modelled by using a template. The comparison of this CNN model with the real physiological measurements is presented. Then, based on this template, the CNN universal machine is used to model four types of visual illusions: subjective contour illusion (Kanizsa illusion), size illusion (Mueller-Lyer illusion, Ponzo illusion), direction and location illusion (angular illusion of location, Poggendorff illusion) and contrast illusion (Herring illusion). Computer simulations are provided for animating facial expressions and modelling visual illusions.     

Analysis of the interaction between the retinal ON and OFF channels using CNN‐UM models

Quantitative retinal modeling is an important tool for analyzing the circuitry underlying the functional organization of the retina, and developing neuromorphic signal processing for retinal prostheses. The Cellular Neural Network (CNN) is a suitable tool for both purposes due to its structure. Using multilayer CNN models we analyzed two phenomena: First the signal distortion caused by nonlinear synapses and secondly the use of inhibitory interaction between ON and OFF channels. Our simulations show that the ON–OFF interaction can reduce the signal distortion caused by nonlinear synapses. Copyright © 2008 John Wiley & Sons, Ltd.     

SPATIAL DEPTH EXTRACTION USING RANDOM STEREOGRAMS IN ANALOGIC CNN FRAMEWORK

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.     

A CNN UNIVERSAL CHIP IN CMOS TECHNOLOGY

This paper describes the design of a programmable cellular neural network (CNN) chip with added functionalities similar to those of the CNN universal machine. The prototype contains 1024 cells and has been designed in a 1·0 μm, n-well CMOS technology. Careful selection of the topology and design parameters has resulted in a cell density of 31 cells mm⁻² and around 7–8 bits accuracy in the weight values. Adaptive techniques have been employed to ensure accurate external control and system robustness against process parameter variations.     

Analogic CNN algorithms for textile applications

Some novel CNN analogic algorithms are proposed, which are useful in the context of textile industry. They concern the detection of stains and defects, and the recognition of the labels on a cloth. Copyright © 2000 John Wiley & Sons, Ltd.     

Analogic CNN algorithm for estimating position and size of moving objects

An analogic CNN algorithm is proposed for detection of multiple moving objects in high resolution, grey‐scale images taken from a fixed camera. The algorithm, based on simple 3 × 3 templates, can be implemented using CNN hardware, providing the real‐time operation required in surveillance and traffic control applications. Efficient separation of moving objects from the background is obtained through automatic threshold selection. The performance of the proposed method is shown using real‐life indoor and outdoor video sequences. Copyright © 2004 John Wiley & Sons, Ltd.     

CNN-based difference-controlled adaptive non-linear image filters

In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical–statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given throughout the text using various intensity images. © 1998 John Wiley & Sons, Ltd.     

A rigorous design method for binary cellular neural networks

In order to be able to take full advantage of the great application potential that lies in cellular neural networks (CNNs) we need to have successful design and learning techniques as well. In almost any analogic CNN algorithm that performs an image processing task, binary CNNs play an important role. We observed that all binary CNNs reported in the literature, except for a connected component detector, exhibit monotonic dynamics. In the paper we show that the local stability of a monotonic binary CNN represents sufficient condition for its functionality, i.e. convergence of all initial states to the prescribed global stable equilibria. Based on this finding, we propose a rigorous design method, which results in a set of design constraints in the form of linear inequalities. These are obtained from simple local rules similar to that in elementary cellular automata without having to worry about continuous dynamics of a CNN. In the end we utilize our method to design a new CNN template for detecting holes in a 2D object. © 1998 John Wiley Sons, Ltd.     

Methods for constructing physiologically motivated neuromorphic models in CNNs

We introduce a collection of techniques, which we propose to denote ‘neuromorphic CNN’, for applying cellular neural networks to the physiologically-detailed modelling of biological neural systems. Examples will be given of the application of these methods to the construction of highly biologically-faithful models of the vertebrate retina, and the utility of such models to neurobiological research will be discussed.     

基于电子舌和 WGAN-CNN 模型的小麦贮存 年限快速检测

为了实现对不同贮存年限陈化小麦的快速检测,提出一种伏安电子舌结合卷积神经网络(convolutional neural network, CNN)和基于Wasserstein距离的生成对抗网络(wasserstein generative adversarial nets, WGAN)组合的模式识别模型。使用伏安电子舌对6种不同贮存时间小麦采集电子舌信号。针对电子舌信号信息量大、特征提取困难等问题,设计了一种基于CNN结构的电子舌信号特征自动提取和分类识别模型。为解决CNN模型因训练样本不足而导致泛化能力差等问题,使用WGAN构建电子舌信号样本集,通过对生成信号集的学习,提高了CNN模型对电子舌信号的识别能力。实验结果表明,与AlexNet、VGG16等深度学习模型和随机森林(RM)、极限学习机(ELM)等传统机器学习模型相比,WGAN-CNN模型对电子舌信号的分辨能力更强,其测试集准确率、精确率、召回率和F1-Score分别达到0.98、0.98、0.977和0.988。研究表明电子舌结合WGAN-CNN模型可实现对小麦贮存年限的快速检测,该研究为基于人工智能的感官识别技术提供了一种新的研究思路。     

Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition

The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general‐purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post‐processing recognition results. The high‐level a priori background knowledge is, however, crucial in human reading and similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: geometric and linguistic information are given equal importance. On the geometric side we use word‐level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. Circuits Syst. 1993; 40 :163–173; Cellular Neural Networks and Visual Computing, Foundations and Applications. Cambridge University Press: Cambridge, U.K., New York, 2002). The linguistic side is based on a morpho‐syntactic linguistic system (Proceedings of COLING‐2002, vol. II, Taipei, Taiwan, 2002; 1263–1267). A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists. Copyright © 2008 John Wiley & Sons, Ltd.     

Pixel‐level snakes on the CNNUM: algorithm design,on‐chip implementation and applications

In this paper, a new algorithm for the cellular active contour technique called pixel‐level snakes is proposed. The motivation is twofold: on the one hand, a higher efficiency and flexibility in the contour evolution towards the boundaries of interest are pursued. On the other hand, a higher performance and suitability for its hardware implementation onto a cellular neural network (CNN) chip‐set architecture are also required. Based on the analysis of previous schemes the contour evolution is improved and a new approach to manage the topological transformations is incorporated. Furthermore, new capabilities in the contour guiding are introduced by the incorporation of inflating/deflating terms based on the balloon forces for the parametric active contours. The entire algorithm has been implemented on a CNN universal machine (CNNUM) chip set architecture for which the results of the time performance measurements are also given. To illustrate the validity and efficiency of the new scheme several examples are discussed including real applications from medical imaging. Copyright © 2005 John Wiley & Sons, Ltd.     

An efficient paradigm for wavelet‐based image processing using cellular neural networks

We propose a novel paradigm for cellular neural networks (CNNs), which enables the user to simultaneously calculate up to four subband images and to implement the integrated wavelet decomposition and a subsequent function into a single CNN. Two sets of experiments were designated to test the performance of the paradigm. In the first set of experiments, the effects of seven different wavelet filters and five feature extractors were studied in the extraction of critical features from the down‐sampled low‐low subband image using the paradigm. Among them, the combination of DB53 wavelet filter and the r=2 halftoning processor was determined to be most appropriate for low‐resolution applications. The second set of experiments demonstrated the capacity of the paradigm in the extraction of features from multi‐subband images. CNN edge detectors were embedded in a two‐subband digital wavelet transformation processor to extract the horizontal and vertical line features from the LH and HL subband images, respectively. A CNN logic OR operator proceeds to combine the results from the two subband line‐edge detectors. The proposed edge detector is capable of delineating more subtle details than using typical CNN edge detector alone, and is more robust in dealing with low‐contrast images than traditional edge detectors. The results demonstrate the proposed paradigm as a powerful and efficient scheme for image processing using CNN. Copyright © 2008 John Wiley & Sons, Ltd.     

Gear Transmission Fault Classification using Deep Neural Networks and Classifier Level Sensor Fusion

Gear transmissions are widely used in industrial drive systems. Fault diagnosis of gear transmissions is important for maintaining the system performance, reducing the maintenance cost, and providing a safe working environment. This paper presents a novel fault diagnosis approach for gear transmissions based on convolutional neural networks (CNNs) and decision-level sensor fusion. In the proposed approach, a CNN is first utilized to classify the faults of a gear transmission based on the acquired signals from each of the sensors. Raw sensory data is sent directly into the CNN models without manual feature extraction. Then, classifier level sensor fusion is carried out to achieve improved classification accuracy by fusing the classification results from the CNN models. Experimental study is conducted, which shows the superior performance of the developed method in the classification of different gear transmission conditions in an automated industrial machine. The presented approach also achieves end-to-end learning that can be applied to the fault classification of a gear transmission under various operating conditions and with signals from different types of sensors.