The two-volume set LNAI 9119 and LNAI 9120 constitutes the refereed proceedings of the 14th International conference on artificial Intelligence and Soft Computing, ICAISC 2015, held in Zakopane, Poland in June 2015. T...
ISBN:
(数字)9783319193687;9783319193694
ISBN:
(纸本)9783319193687;9783319193694
The two-volume set LNAI 9119 and LNAI 9120 constitutes the refereed proceedings of the 14th International conference on artificial Intelligence and Soft Computing, ICAISC 2015, held in Zakopane, Poland in June 2015. The 142 revised full papers presented in the volumes, were carefully reviewed and selected from 322 submissions. These proceedings present both traditional artificial intelligence methods and soft computing techniques. The goal is to bring together scientists representing both areas of research. The first volume covers topics as follows neuralnetworks and their applications, fuzzy systems and their applications, evolutionary algorithms and their applications, classification and estimation, computer vision, image and speech analysis and the workshop: large-scale visual recognition and machine learning. The second volume has the focus on the following subjects: data mining, bioinformatics, biometrics and medical applications, concurrent and parallel processing, agent systems, robotics and control, artificial intelligence in modeling and simulation and various problems of artificial intelligence.
This paper presents a new lossy image compression technique using Logic-based Weightless neuralnetworks, which underwrite two novel network architectures. The system endorses three processing phases, image optimizati...
详细信息
ISBN:
(纸本)9781665434430
This paper presents a new lossy image compression technique using Logic-based Weightless neuralnetworks, which underwrite two novel network architectures. The system endorses three processing phases, image optimization, inflation, and skimming. This research demonstrates an untraditional approach of auto-compression network guided by horizontal and vertical pixel intensity wavering trend. The performance of this new approach aligns with human's perception of singularities in a certain pattern. The potential of trend analysis in image compression incorporates with information storage techniques and knowledge accumulation. The weightless network models generate images underlying enough distinct features that preserve the originality of a particular pattern but give superior levels of compression.
In recent years, deep learning widely used in imageprocessing field, has introduced many new applications related to the agricultural field. In this study, for apricot disease detection were used deep learning models...
详细信息
ISBN:
(纸本)9781538668788
In recent years, deep learning widely used in imageprocessing field, has introduced many new applications related to the agricultural field. In this study, for apricot disease detection were used deep learning models such as AlexNet, Vgg16, and Vgg19 based on pre-trained deep Convolutional neuralnetworks (CNN). The deep attributes obtained from these models are classified by K-Nearest Neighbour (KNN) method. To calculate the performance of the proposed methods was applied 10- fold cross-validation test. The dataset consists of 960 images including healthy and diseased apricot images. According to the obtained results, the highest accuracy was obtained as 94.8% by using Vgg16 model.
Noisy incoherent objects, which are too close to be remotely separated by optically imaging beyond the Rayleigh diffraction limit, might be resolved by employing the artificialneural Network (ANN) smart pixel post pr...
详细信息
ISBN:
(纸本)0819440868
Noisy incoherent objects, which are too close to be remotely separated by optically imaging beyond the Rayleigh diffraction limit, might be resolved by employing the artificialneural Network (ANN) smart pixel post processing and its mathematical framework, Independent Component Analysis (ICA). It is shown that ICA ANN approach to superresolution based on information maximization principle could be seen as a part of the general approach called space-bandwidth (SW) product adaptation method. Our success is perhaps due to the Blind Source Separation (BSS) Smart-Pixel Detectors (SPD) behind the imaging lens (inverse adaptation), while the Rayleigh diffraction limit remains valid for a single instance of the deterministic imaging systems' realization. The blindness is due to the unknown objects, and the unpredictable propagation effect on the net imaging point spread function. Such a software/firmware enhancement of imaging system may have a profound implication to the designs of the new (third) generation imaging systems as well as other non-optical imaging systems.
Instance segmentation of images is an important tool for automated scene understanding. neuralnetworks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such a...
详细信息
ISBN:
(纸本)9781665408981
Instance segmentation of images is an important tool for automated scene understanding. neuralnetworks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an overlooked pedestrian seems more harmful than a falsely detected one. In this work, we present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances given the availability of image sequences in online applications. As the number of instances can be greatly increased by this algorithm, we apply a false positive pruning using uncertainty estimates aggregated over instances. To this end, instance-wise metrics are constructed which characterize uncertainty and geometry of a given instance or are predicated on depth estimation. The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only. In our tests, we obtain an improved trade-off between false negative and false positive instances by our fused detection approach in comparison to the use of an ordinary score value provided by the instance segmentation network during inference.
In the present work an adaptation of the Cellular neural Network (CNN) model to grey scale imageprocessing is proposed. This task is performed programming the network to work as a classical spatial filter, taking adv...
详细信息
ISBN:
(纸本)0852967217
In the present work an adaptation of the Cellular neural Network (CNN) model to grey scale imageprocessing is proposed. This task is performed programming the network to work as a classical spatial filter, taking advantage of the neural Network structure in order to improve the filtering effects. This enhancement is carried out by the inclusion of the feedback of the state variables and the adaptation of the input bias of every neuron based on the brightness of the image. A proper choice of the gain of the output function may also improve some of the network capabilities.
The proceedings contain 57 papers. The special focus in this conference is on Computing Languages with Bio-Inspired Devices, Brain-Computer Interfaces, Multi-Robot Systems, Video and imageprocessing. The topics inclu...
ISBN:
(纸本)9783319192574
The proceedings contain 57 papers. The special focus in this conference is on Computing Languages with Bio-Inspired Devices, Brain-Computer Interfaces, Multi-Robot Systems, Video and imageprocessing. The topics include: Grammatical inference model for measuring language complexity;a proposal for contextual grammatical inference;training in realistic virtual environments;real-time monitoring of biomedical signals to improve road safety;authentication of brain-computer interface users in network applications;a first step toward a possibilistic swarm multi-robot task allocation;a bottom-up robot architecture based on learnt behaviors driven design;from human eye fixation to human-like autonomous artificial vision;a mini robot for scientific applications;visualization of complex datasets with the self-organizing spanning tree;a detection system for vertical slot fishways using laser technology and computer vision techniques;interactive relevance visual learning for image retrieval;scene classification based on local binary pattern and improved bag of visual words;a novel framework for hyperemia grading based on artificialneuralnetworks;finding the texture features characterizing the most homogeneous texture segment in the image;bio-inspired motion estimation with event-driven sensors;domain generalization based on transfer component analysis;deep transfer learning ensemble for classification;transfer learning for the recognition of immunogold particles in TEM imaging;improved retrieval for challenging scenarios in clique-based neuralnetworks;deep neuralnetworks for wind energy prediction and convolutional neuralnetworks for detecting and mapping crowds in first person vision applications.
In this paper we study the applicability of Probabilistic neuralnetworks (PNNs) as core classifiers to medium scale speaker recognition over fixed telephone networks. In particular, banking applications with up to 40...
详细信息
ISBN:
(纸本)0780375033
In this paper we study the applicability of Probabilistic neuralnetworks (PNNs) as core classifiers to medium scale speaker recognition over fixed telephone networks. In particular, banking applications with up to 400 enrolled speakers and short training times are targeted. Two PNN-based open-set text-independent systems for Speaker Identification and Speaker Verification correspondingly are presented. The performance of these systems is studied with and without use of a supporting Gaussian Mixture Models classifier. Results from experiments carried out on the Polycost and SpeechDat(ii)-Greek corpus, with training times as short as 43 seconds, are reported.
This paper deals with application of fuzzy and neural techniques to the reversible intraframe compression of grayscale images. With reference to a spatial DPCM scheme, prediction may be accomplished in a space varying...
详细信息
ISBN:
(纸本)0819435805
This paper deals with application of fuzzy and neural techniques to the reversible intraframe compression of grayscale images. With reference to a spatial DPCM scheme, prediction may be accomplished in a space varying fashion following two main strategies: adaptive, i.e., with predictors recalculated at each pixel position, and classified, in which image blocks, or pixels are preliminarily labeled into a number of statistical classes, for which minimum MSE predictors are calculated. Here, a trade off between the above two strategies is proposed, which relies on a space-varying linear-regression prediction obtained through fuzzy techniques, and is followed by context based statistical modeling of prediction errors, to enhance entropy coding. A thorough comparison with the most advanced methods in the literature, as well as an investigation of performance trends to work parameters, highlight the advantages of the fuzzy approach.
Along with the recent development of Convolutional neural Network (CNN) and its multilayering, it is important to reduce the amount of computation and the amount of data associated with convolution processing. Some co...
详细信息
ISBN:
(纸本)9783319686127;9783319686110
Along with the recent development of Convolutional neural Network (CNN) and its multilayering, it is important to reduce the amount of computation and the amount of data associated with convolution processing. Some compression methods of convolutional filters using low-rank approximation have been studied. The common goal of these studies is to accelerate the computation wherever possible while maintaining the accuracy of image recognition. In this paper, we investigate the trade-off between the compression error by low-rank approximation and the computational complexity for the state-of-the-arts CNN model.
暂无评论