Search results for: A complexity-based approach in image compression using neural networks

Authors: Hadi Veisi, Mansour Jamzad

Abstract:

In this paper we present an adaptive method for image compression that is based on complexity level of the image. The basic compressor/de-compressor structure of this method is a multilayer perceptron artificial neural network. In adaptive approach different Back-Propagation artificial neural networks are used as compressor and de-compressor and this is done by dividing the image into blocks, computing the complexity of each block and then selecting one network for each block according to its complexity value. Three complexity measure methods, called Entropy, Activity and Pattern-based are used to determine the level of complexity in image blocks and their ability in complexity estimation are evaluated and compared. In training and evaluation, each image block is assigned to a network based on its complexity value. Best-SNR is another alternative in selecting compressor network for image blocks in evolution phase which chooses one of the trained networks such that results best SNR in compressing the input image block. In our evaluations, best results are obtained when overlapping the blocks is allowed and choosing the networks in compressor is based on the Best-SNR. In this case, the results demonstrate superiority of this method comparing with previous similar works and JPEG standard coding.

Keywords: Adaptive image compression, Image complexity, Multi-layer perceptron neural network, JPEG Standard, PSNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2176

Authors: S. Anna Durai, E. Anna Saro

Abstract:

In general the images used for compression are of different types like dark image, high intensity image etc. When these images are compressed using Counter Propagation Neural Network, it takes longer time to converge. The reason for this is that the given image may contain a number of distinct gray levels with narrow difference with their neighborhood pixels. If the gray levels of the pixels in an image and their neighbors are mapped in such a way that the difference in the gray levels of the neighbor with the pixel is minimum, then compression ratio as well as the convergence of the network can be improved. To achieve this, a Cumulative Distribution Function is estimated for the image and it is used to map the image pixels. When the mapped image pixels are used the Counter Propagation Neural Network yield high compression ratio as well as it converges quickly.

Keywords: Correlation, Counter Propagation Neural Networks, Cummulative Distribution Function, Image compression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1631

Authors: S. Anna Durai, E. Anna Saro

Abstract:

Image Compression using Artificial Neural Networks is a topic where research is being carried out in various directions towards achieving a generalized and economical network. Feedforward Networks using Back propagation Algorithm adopting the method of steepest descent for error minimization is popular and widely adopted and is directly applied to image compression. Various research works are directed towards achieving quick convergence of the network without loss of quality of the restored image. In general the images used for compression are of different types like dark image, high intensity image etc. When these images are compressed using Back-propagation Network, it takes longer time to converge. The reason for this is, the given image may contain a number of distinct gray levels with narrow difference with their neighborhood pixels. If the gray levels of the pixels in an image and their neighbors are mapped in such a way that the difference in the gray levels of the neighbors with the pixel is minimum, then compression ratio as well as the convergence of the network can be improved. To achieve this, a Cumulative distribution function is estimated for the image and it is used to map the image pixels. When the mapped image pixels are used, the Back-propagation Neural Network yields high compression ratio as well as it converges quickly.

Keywords: Back-propagation Neural Network, Cumulative Distribution Function, Correlation, Convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2513

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2135

Authors: Saudagar Abdul Khader Jilani, Syed Abdul Sattar

Abstract:

Image compression plays a vital role in today-s communication. The limitation in allocated bandwidth leads to slower communication. To exchange the rate of transmission in the limited bandwidth the Image data must be compressed before transmission. Basically there are two types of compressions, 1) LOSSY compression and 2) LOSSLESS compression. Lossy compression though gives more compression compared to lossless compression; the accuracy in retrievation is less in case of lossy compression as compared to lossless compression. JPEG, JPEG2000 image compression system follows huffman coding for image compression. JPEG 2000 coding system use wavelet transform, which decompose the image into different levels, where the coefficient in each sub band are uncorrelated from coefficient of other sub bands. Embedded Zero tree wavelet (EZW) coding exploits the multi-resolution properties of the wavelet transform to give a computationally simple algorithm with better performance compared to existing wavelet transforms. For further improvement of compression applications other coding methods were recently been suggested. An ANN base approach is one such method. Artificial Neural Network has been applied to many problems in image processing and has demonstrated their superiority over classical methods when dealing with noisy or incomplete data for image compression applications. The performance analysis of different images is proposed with an analysis of EZW coding system with Error Backpropagation algorithm. The implementation and analysis shows approximately 30% more accuracy in retrieved image compare to the existing EZW coding system.

Keywords: Accuracy, Compression, EZW, JPEG2000, Performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1877

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, neural networks have shown good results for detection of a certain pattern in a given image. In our previous papers [1-5], a fast algorithm for pattern detection using neural networks was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Image conversion into symmetric shape was established so that fast neural networks can give the same results as conventional neural networks. Another configuration of symmetry was suggested in [3,4] to improve the speed up ratio. In this paper, our previous algorithm for fast neural networks is developed. The frequency domain cross correlation is modified in order to compensate for the symmetric condition which is required by the input image. Two new ideas are introduced to modify the cross correlation algorithm. Both methods accelerate the speed of the fast neural networks as there is no need for converting the input image into symmetric one as previous. Theoretical and practical results show that both approaches provide faster speed up ratio than the previous algorithm.

Keywords: Fast Pattern Detection, Neural Networks, Modified Cross Correlation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1696

Authors: Yasser F. Hassan

Abstract:

The reduction or removal of noise in a color image is an essential part of image processing, whether the final information is used for human perception or for an automatic inspection and analysis. This paper describes the modeling system based on the rough neural network model to adaptive cellular automata for various image processing tasks and noise remover. In this paper, we consider the problem of object processing in colored image using rough neural networks to help deriving the rules which will be used in cellular automata for noise image. The proposed method is compared with some classical and recent methods. The results demonstrate that the new model is capable of being trained to perform many different tasks, and that the quality of these results is comparable or better than established specialized algorithms.

Keywords: Rough Sets, Rough Neural Networks, Cellular Automata, Image Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1902

Authors: Hamed Vahdat Nejad, Hossein Deldari

Abstract:

Wavelet transforms are multiresolution decompositions that can be used to analyze signals and images. Image compression is one of major applications of wavelet transforms in image processing. It is considered as one of the most powerful methods that provides a high compression ratio. However, its implementation is very time-consuming. At the other hand, parallel computing technologies are an efficient method for image compression using wavelets. In this paper, we propose a parallel wavelet compression algorithm based on quadtrees. We implement the algorithm using MatlabMPI (a parallel, message passing version of Matlab), and compute its isoefficiency function, and show that it is scalable. Our experimental results confirm the efficiency of the algorithm also.

Keywords: Image compression, MPI, Parallel computing, Wavelets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1983

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, fast neural networks for object/face detection were presented in [1-3]. The speed up factor of these networks relies on performing cross correlation in the frequency domain between the input image and the weights of the hidden layer. But, these equations given in [1-3] for conventional and fast neural networks are not valid for many reasons presented here. In this paper, correct equations for cross correlation in the spatial and frequency domains are presented. Furthermore, correct formulas for the number of computation steps required by conventional and fast neural networks given in [1-3] are introduced. A new formula for the speed up ratio is established. Also, corrections for the equations of fast multi scale object/face detection are given. Moreover, commutative cross correlation is achieved. Simulation results show that sub-image detection based on cross correlation in the frequency domain is faster than classical neural networks.

Keywords: Conventional Neural Networks, Fast Neural Networks, Cross Correlation in the Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2408

Authors: Wenbin Zhang, Hantian Wu, Jian Tang

Abstract:

An artificial neural network is a mathematical model inspired by biological neural networks. There are several kinds of neural networks and they are widely used in many areas, such as: prediction, detection, and classification. Meanwhile, in day to day life, people always have to make many difficult decisions. For example, the coach of a soccer club has to decide which offensive player to be selected to play in a certain game. This work describes a novel Neural Network using a combination of the General Regression Neural Network and the Probabilistic Neural Networks to help a soccer coach make an informed decision.

Keywords: General Regression Neural Network, Probabilistic Neural Networks, Neural function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3718

Authors: Sepehr M.H.Jamarani, M.H.Moradi, H.Behnam, G.A.Rezai Rad

Abstract:

This paper presents an approach for early breast cancer diagnostic by employing combination of artificial neural networks (ANN) and multiwaveletpacket based subband image decomposition. The microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands,, reconstructing the mammograms from the subbands containing only high frequencies. For this approach we employed different types of multiwaveletpacket. We used the result as an input of neural network for classification. The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases and images collected from local hospitals. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve.

Keywords: Breast cancer, neural networks, diagnosis, multiwavelet packet, microcalcification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1361

Authors: M. Kutila, J. Viitanen

Abstract:

This paper presents image compression with wavelet based method. The wavelet transformation divides image to low- and high pass filtered parts. The traditional JPEG compression technique requires lower computation power with feasible losses, when only compression is needed. However, there is obvious need for wavelet based methods in certain circumstances. The methods are intended to the applications in which the image analyzing is done parallel with compression. Furthermore, high frequency bands can be used to detect changes or edges. Wavelets enable hierarchical analysis for low pass filtered sub-images. The first analysis can be done for a small image, and only if any interesting is found, the whole image is processed or reconstructed.

Keywords: image compression, jpeg, wavelet, vlc

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1739

Authors: Jiann-Ming Wu, Hsiao-Chang Chen, Chun-Chang Wu, Pei-Hsun Hsu

Abstract:

This work explores blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that a degraded image is linear convolution of an original source image through a linear shift-invariant (LSI) blurring matrix. Supervised learning of neural networks of radial basis functions (RBF) is employed to construct an embedded recursive function within a blurring image, try to extract non-deterministic component of an original source image, and use them to estimate hyper parameters of a linear image degradation model. Based on the estimated blurring matrix, reconstruction of an original source image from a blurred image is further resolved by an annealed Hopfield neural network. By numerical simulations, the proposed novel method is shown effective for faithful estimation of an unknown blurring matrix and restoration of an original source image.

Keywords: Blind image deconvolution, linear shift-invariant(LSI), linear image degradation model, radial basis functions (rbf), recursive function, annealed Hopfield neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2009

Authors: K.Sowmyan, A.Siddarth, D.Menaka

Abstract:

Several methods have been proposed for color image compression but the reconstructed image had very low signal to noise ratio which made it inefficient. This paper describes a lossy compression technique for color images which overcomes the drawbacks. The technique works on spatial domain where the pixel values of RGB planes of the input color image is mapped onto two dimensional planes. The proposed technique produced better results than JPEG2000, 2DPCA and a comparative study is reported based on the image quality measures such as PSNR and MSE.Experiments on real time images are shown that compare this methodology with previous ones and demonstrate its advantages.

Keywords: Color Image compression, spatial domain, planereduction, root mean square, image restoration

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589

Authors: Naiqin Feng, Fang Wang, Yuhui Qiu

Abstract:

A new approach to promote the generalization ability of neural networks is presented. It is based on the point of view of fuzzy theory. This approach is implemented through shrinking or magnifying the input vector, thereby reducing the difference between training set and testing set. It is called “shrinking-magnifying approach" (SMA). At the same time, a new algorithm; α-algorithm is presented to find out the appropriate shrinking-magnifying-factor (SMF) α and obtain better generalization ability of neural networks. Quite a few simulation experiments serve to study the effect of SMA and α-algorithm. The experiment results are discussed in detail, and the function principle of SMA is analyzed in theory. The results of experiments and analyses show that the new approach is not only simpler and easier, but also is very effective to many neural networks and many classification problems. In our experiments, the proportions promoting the generalization ability of neural networks have even reached 90%.

Keywords: Fuzzy theory, generalization, misclassification rate, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1495

Authors: Hazem M. El-Bakry

Abstract:

Neural processors have shown good results for detecting a certain character in a given input matrix. In this paper, a new idead to speed up the operation of neural processors for character detection is presented. Such processors are designed based on cross correlation in the frequency domain between the input matrix and the weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single faster neural processor. Furthermore, faster character detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of faster neural networks. In contrast to using only faster neural processors, the speed up ratio is increased with the size of the input image when using faster neural processors and image decomposition. Moreover, the problem of local subimage normalization in the frequency domain is solved. The effect of image normalization on the speed up ratio of character detection is discussed. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

Keywords: Fast Character Detection, Neural Processors, Cross Correlation, Image Normalization, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1496

Authors: Shimal Das, Dibyendu Ghoshal

Abstract:

Fractal based digital image compression is a specific technique in the field of color image. The method is best suited for irregular shape of image like snow bobs, clouds, flame of fire; tree leaves images, depending on the fact that parts of an image often resemble with other parts of the same image. This technique has drawn much attention in recent years because of very high compression ratio that can be achieved. Hybrid scheme incorporating fractal compression and speedup techniques have achieved high compression ratio compared to pure fractal compression. Fractal image compression is a lossy compression method in which selfsimilarity nature of an image is used. This technique provides high compression ratio, less encoding time and fart decoding process. In this paper, fractal compression with quad tree and DCT is proposed to compress the color image. The proposed hybrid schemes require four phases to compress the color image. First: the image is segmented and Discrete Cosine Transform is applied to each block of the segmented image. Second: the block values are scanned in a zigzag manner to prevent zero co-efficient. Third: the resulting image is partitioned as fractals by quadtree approach. Fourth: the image is compressed using Run length encoding technique.

Keywords: Fractal coding, Discrete Cosine Transform, Iterated Function System (IFS), Affine Transformation, Run length encoding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1532

Authors: C. Rajan, K. Geetha, S. Geetha

Abstract:

The motivation of image compression technique is to reduce the irrelevance and redundancy of the image data in order to store or pass data in an efficient way from one place to another place. There are several types of compression methods available. Without the help of compression technique, the file size is knowingly larger, usually several megabytes, but by doing the compression technique, it is possible to reduce file size up to 10% as of the original without noticeable loss in quality. Image compression can be lossless or lossy. The compression technique can be applied to images, audio, video and text data. This research work mainly concentrates on methods of encoding, DCT, compression methods, security, etc. Different methodologies and network simulations have been analyzed here. Various methods of compression methodologies and its performance metrics has been investigated and presented in a table manner.

Keywords: Image compression techniques, encoding, DCT, lossy compression, lossless compression, JPEG.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1156

Authors: Y.Chakrapani, K.Soundera Rajan

Abstract:

In this paper a hybrid technique of Genetic Algorithm and Simulated Annealing (HGASA) is applied for Fractal Image Compression (FIC). With the help of this hybrid evolutionary algorithm effort is made to reduce the search complexity of matching between range block and domain block. The concept of Simulated Annealing (SA) is incorporated into Genetic Algorithm (GA) in order to avoid pre-mature convergence of the strings. One of the image compression techniques in the spatial domain is Fractal Image Compression but the main drawback of FIC is that it involves more computational time due to global search. In order to improve the computational time along with acceptable quality of the decoded image, HGASA technique has been proposed. Experimental results show that the proposed HGASA is a better method than GA in terms of PSNR for Fractal image Compression.

Keywords: Fractal Image Compression, Genetic Algorithm, HGASA, Simulated Annealing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1637

Authors: Khalid Salhi, El Miloud Jaara, Mohammed Talibi Alaoui

Abstract:

In this paper, we present a neural approach for unsupervised natural color-texture image segmentation, which is based on both Kohonen maps and mathematical morphology, using a combination of the texture and the image color information of the image, namely, the fractal features based on fractal dimension are selected to present the information texture, and the color features presented in RGB color space. These features are then used to train the network Kohonen, which will be represented by the underlying probability density function, the segmentation of this map is made by morphological watershed transformation. The performance of our color-texture segmentation approach is compared first, to color-based methods or texture-based methods only, and then to k-means method.

Keywords: Segmentation, color-texture, neural networks, fractal, watershed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1338

Authors: Mario Mastriani

Abstract:

In this work, we present a comparison between different techniques of image compression. First, the image is divided in blocks which are organized according to a certain scan. Later, several compression techniques are applied, combined or alone. Such techniques are: wavelets (Haar's basis), Karhunen-Loève Transform, etc. Simulations show that the combined versions are the best, with minor Mean Squared Error (MSE), and higher Peak Signal to Noise Ratio (PSNR) and better image quality, even in the presence of noise.

Keywords: Haar's basis, Image compression, Karhunen-LoèveTransform, Morton's scan, row-rafter scan.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1713

Authors: Dibyendu Ghoshal, Shimal Das

Abstract:

Image compression based on fractal coding is a lossy compression method and normally used for gray level images range and domain blocks in rectangular shape. Fractal based digital image compression technique provide a large compression ratio and in this paper, it is proposed using YUV colour space and the fractal theory which is based on iterated transformation. Fractal geometry is mainly applied in the current study towards colour image compression coding. These colour images possesses correlations among the colour components and hence high compression ratio can be achieved by exploiting all these redundancies. The proposed method utilises the self-similarity in the colour image as well as the cross-correlations between them. Experimental results show that the greater compression ratio can be achieved with large domain blocks but more trade off in image quality is good to acceptable at less than 1 bit per pixel.

Keywords: Fractal coding, Iterated Function System (IFS), Image compression, YUV colour space.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1935

Authors: Anupama Pande, Vishik Goel

Abstract:

A complex valued neural network is a neural network, which consists of complex valued input and/or weights and/or thresholds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in image and vision processing. In Neural networks, radial basis functions are often used for interpolation in multidimensional space. A Radial Basis function is a function, which has built into it a distance criterion with respect to a centre. Radial basis functions have often been applied in the area of neural networks where they may be used as a replacement for the sigmoid hidden layer transfer characteristic in multi-layer perceptron. This paper aims to present exhaustive results of using RBF units in a complex-valued neural network model that uses the back-propagation algorithm (called 'Complex-BP') for learning. Our experiments results demonstrate the effectiveness of a Radial basis function in a complex valued neural network in image recognition over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error on a neural network model with RBF units. Some inherent properties of this complex back propagation algorithm are also studied and discussed.

Keywords: Complex valued neural network, Radial BasisFunction, Image recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2367

Authors: Madhuri Khambete, Madhuri Joshi

Abstract:

Quality evaluation of an image is an important task in image processing applications. In case of image compression, quality of decompressed image is also the criterion for evaluation of given coding scheme. In the process of compression -decompression various artifacts such as blocking artifacts, blur artifact, ringing or edge artifact are observed. However quantification of these artifacts is a difficult task. We propose here novel method to quantify blur and ringing artifact in an image.

Keywords: Blur, Compression, Objective Quality assessment, Ringing artifact.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4814

Authors: Sumathi Poobal, G. Ravindran

Abstract:

Image compression is one of the most important applications Digital Image Processing. Advanced medical imaging requires storage of large quantities of digitized clinical data. Due to the constrained bandwidth and storage capacity, however, a medical image must be compressed before transmission and storage. There are two types of compression methods, lossless and lossy. In Lossless compression method the original image is retrieved without any distortion. In lossy compression method, the reconstructed images contain some distortion. Direct Cosine Transform (DCT) and Fractal Image Compression (FIC) are types of lossy compression methods. This work shows that lossy compression methods can be chosen for medical image compression without significant degradation of the image quality. In this work DCT and Fractal Compression using Partitioned Iterated Function Systems (PIFS) are applied on different modalities of images like CT Scan, Ultrasound, Angiogram, X-ray and mammogram. Approximately 20 images are considered in each modality and the average values of compression ratio and Peak Signal to Noise Ratio (PSNR) are computed and studied. The quality of the reconstructed image is arrived by the PSNR values. Based on the results it can be concluded that the DCT has higher PSNR values and FIC has higher compression ratio. Hence in medical image compression, DCT can be used wherever picture quality is preferred and FIC is used wherever compression of images for storage and transmission is the priority, without loosing picture quality diagnostically.

Keywords: DCT, FIC, PIFS, PSNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1789

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 106

Authors: N. Muthukumaran, R. Ravi

Abstract:

The Quad Tree Decomposition based performance analysis of compressed image data communication for lossy and lossless through wireless sensor network is presented. Images have considerably higher storage requirement than text. While transmitting a multimedia content there is chance of the packets being dropped due to noise and interference. At the receiver end the packets that carry valuable information might be damaged or lost due to noise, interference and congestion. In order to avoid the valuable information from being dropped various retransmission schemes have been proposed. In this proposed scheme QTD is used. QTD is an image segmentation method that divides the image into homogeneous areas. In this proposed scheme involves analysis of parameters such as compression ratio, peak signal to noise ratio, mean square error, bits per pixel in compressed image and analysis of difficulties during data packet communication in Wireless Sensor Networks. By considering the above, this paper is to use the QTD to improve the compression ratio as well as visual quality and the algorithm in MATLAB 7.1 and NS2 Simulator software tool.

Keywords: Image compression, Compression Ratio, Quad tree decomposition, Wireless sensor networks, NS2 simulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2353

Authors: Radouane Iqdour, Abdelouhab Zeroual

Abstract:

The Multi-Layered Perceptron (MLP) Neural networks have been very successful in a number of signal processing applications. In this work we have studied the possibilities and the met difficulties in the application of the MLP neural networks for the prediction of daily solar radiation data. We have used the Polack-Ribière algorithm for training the neural networks. A comparison, in term of the statistical indicators, with a linear model most used in literature, is also performed, and the obtained results show that the neural networks are more efficient and gave the best results.

Keywords: Daily solar radiation, Prediction, MLP neural networks, linear model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1282

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In recent years, fast neural networks for object/face detection have been introduced based on cross correlation in the frequency domain between the input matrix and the hidden weights of neural networks. In our previous papers [3,4], fast neural networks for certain code detection was introduced. It was proved in [10] that for fast neural networks to give the same correct results as conventional neural networks, both the weights of neural networks and the input matrix must be symmetric. This condition made those fast neural networks slower than conventional neural networks. Another symmetric form for the input matrix was introduced in [1-9] to speed up the operation of these fast neural networks. Here, corrections for the cross correlation equations (given in [13,15,16]) to compensate for the symmetry condition are presented. After these corrections, it is proved mathematically that the number of computation steps required for fast neural networks is less than that needed by classical neural networks. Furthermore, there is no need for converting the input data into symmetric form. Moreover, such new idea is applied to increase the speed of neural networks in case of processing complex values. Simulation results after these corrections using MATLAB confirm the theoretical computations.

Keywords: Fast Code/Data Detection, Neural Networks, Cross Correlation, real/complex values.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1588

Authors: H. Meradi, S. Bouhouche, M. Lahreche

Abstract:

In this work, we consider an application of neural networks in LD converter. Application of this approach assumes a reliable prediction of steel temperature and reduces a reblow ratio in steel work. It has been applied a conventional model to charge calculation, the obtained results by this technique are not always good, this is due to the process complexity. Difficulties are mainly generated by the noisy measurement and the process non linearities. Artificial Neural Networks (ANNs) have become a powerful tool for these complex applications. It is used a backpropagation algorithm to learn the neural nets. (ANNs) is used to predict the steel bath temperature in oxygen converter process for the end condition. This model has 11 inputs process variables and one output. The model was tested in steel work, the obtained results by neural approach are better than the conventional model.

Keywords: LD converter, bath temperature, neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1796